100% found this document useful (2 votes)

2K views407 pages

AI in Language Teaching Learning and Assessment

Uploaded by

umit.isikli

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

100% found this document useful (2 votes)

2K views407 pages

AI in Language Teaching Learning and Assessment

Uploaded by

umit.isikli

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

You are on page 1/ 407

AI in Language Teaching,

Learning, and Assessment

Fang Pan
London School of Economics and Political Science, UK

A volume in the Advances in Educational

Technologies and Instructional Design (AETID)
Book Series
Published in the United States of America by
IGI Global
Information Science Reference (an imprint of IGI Global)
701 E. Chocolate Avenue
Hershey PA, USA 17033
Tel: 717-533-8845
Fax: 717-533-8661
E-mail: [email protected]
Web site: http://www.igi-global.com

Copyright © 2024 by IGI Global. All rights reserved. No part of this publication may be reproduced, stored or distributed in
any form or by any means, electronic or mechanical, including photocopying, without written permission from the publisher.
Product or company names used in this set are for identification purposes only. Inclusion of the names of the products or
companies does not indicate a claim of ownership by IGI Global of the trademark or registered trademark.
Library of Congress Cataloging-in-Publication Data
Names: Pan, Fang, editor.
Title: AI in language teaching, learning, and assessment / edited
by Fang Pan.
Other titles: Artificial intelligence in language teaching,
learning, and assessment
Description: Hershey, PA : Information Science Reference, 2024. | Includes
bibliographical references and index. | Summary: “The book focuses on
drawbacks of the application of AI in language education, resources
available to ensure the ethical and safe academic deployment of AI, and
benefits of applying AI through language teaching, learning, and
assessment”-- Provided by publisher.
Identifiers: LCCN 2023054112 (print) | LCCN 2023054113 (ebook) | ISBN
9798369308721 (hardcover) | ISBN 9798369308738 (ebook)
Subjects: LCSH: Language and languages--Study and
teaching--Computer-assisted instruction. | Second language
learning--Computer-assisted instruction. | English language--Study and
teaching--Computer-assisted instruction. | English language--Study and
teaching--Computer-assisted instruction for foreign speakers. |
Artificial intelligence--Educational applications.
Classification: LCC P53.28 .C37 2024 (print) | LCC P53.28 (ebook) | DDC
418.00785--dc23/eng/20231226
LC record available at https://lccn.loc.gov/2023054112
LC ebook record available at https://lccn.loc.gov/2023054113

This book is published in the IGI Global book series Advances in Educational Technologies and Instructional Design (AE-
TID) (ISSN: 2326-8905; eISSN: 2326-8913)

British Cataloguing in Publication Data

A Cataloguing in Publication record for this book is available from the British Library.

All work contributed to this book is new, previously-unpublished material. The views expressed in this book are those of the
authors, but not necessarily of the publisher.

For electronic access to this publication, please contact: [email protected].

Advances in Educational
Technologies and Instructional
Design (AETID) Book Series
Lawrence A. Tomei
Robert Morris University, USA
ISSN:2326-8905
EISSN:2326-8913
Mission
Education has undergone, and continues to undergo, immense changes in the way it is enacted and
distributed to both child and adult learners. In modern education, the traditional classroom learning
experience has evolved to include technological resources and to provide online classroom opportunities
to students of all ages regardless of their geographical locations. From distance education, Massive-
Open-Online-Courses (MOOCs), and electronic tablets in the classroom, technology is now an integral
part of learning and is also affecting the way educators communicate information to students.
The Advances in Educational Technologies & Instructional Design (AETID) Book Series explores
new research and theories for facilitating learning and improving educational performance utilizing
technological processes and resources. The series examines technologies that can be integrated into
K-12 classrooms to improve skills and learning abilities in all subjects including STEM education and
language learning. Additionally, it studies the emergence of fully online classrooms for young and adult
learners alike, and the communication and accountability challenges that can arise. Trending topics that
are covered include adaptive learning, game-based learning, virtual school environments, and social
media effects. School administrators, educators, academicians, researchers, and students will find this
series to be an excellent resource for the effective design and implementation of learning technologies
in their classes.

Coverage
• Educational Telecommunications
IGI Global is currently accepting manuscripts
• Instructional Design
for publication within this series. To submit a pro-
• Web 2.0 and Education
posal for a volume in this series, please contact our
• Curriculum Development
Acquisition Editors at [email protected]
• Higher Education Technologies
or visit: http://www.igi-global.com/publish/.
• Online Media in Classrooms
• Collaboration Tools
• Bring-Your-Own-Device
• Game-Based Learning
• Hybrid Learning

The Advances in Educational Technologies and Instructional Design (AETID) Book Series (ISSN 2326-8905) is published by IGI Global, 701 E. Choco-
late Avenue, Hershey, PA 17033-1240, USA, www.igi-global.com. This series is composed of titles available for purchase individually; each title is edited to be
contextually exclusive from any other title within the series. For pricing and ordering information please visit http://www.igi-global.com/book-series/advances-
educational-technologies-instructional-design/73678. Postmaster: Send all address changes to above address. Copyright © 2024 IGI Global. All rights, including
translation in other languages reserved by the publisher. No part of this series may be reproduced or used in any form or by any means – graphics, electronic, or
mechanical, including photocopying, recording, taping, or information and retrieval systems – without written permission from the publisher, except for non com-
mercial, educational use, including classroom teaching purposes. The views expressed in this series are those of the authors, but not necessarily of IGI Global.
Titles in this Series
For a list of additional titles in this series, please visit: www.igi-global.com/book-series

Practices and Implementation of Gamification in Higher Education

Veronica Membrive (University of Almeria, pain)
Information Science Reference • © 2024 • 320pp • H/C (ISBN: 9798369307168) • US $230.00

Optimizing Education Through Micro-Lessons Engaging and Adaptive Learning Strategies

Peter Ilic (University of Aizu, apan)
Information Science Reference • © 2024 • 398pp • H/C (ISBN: 9798369301951) • US $230.00

Fostering Pedagogical Innovation Through Effective Instructional Design

Mohamed Khaldi (Ecole Normale Supérieur, Abdelmalek Essaadi University, Tetouan, Morocco)
Information Science Reference • © 2024 • 467pp • H/C (ISBN: 9798369312063) • US $245.00

Protocols and Tools for Equitable Dual Language Teaching

Esther Gross (The Center for Educational Technology, Israel) and Jenifer Crawford (University of Southern Cali-
fornia, USA)
Information Science Reference • © 2024 • 300pp • H/C (ISBN: 9781799883548) • US $225.00

Utilizing Visuals and Information Technology in Mathematics Classrooms

Hiroto Namihira (Former Otsuma Women’s University, Japan)
Information Science Reference • © 2024 • 300pp • H/C (ISBN: 9781668499870) • US $220.00

Implications of Chatbots on Teaching and Learning

Mohammad Daradkeh (University of Dubai, UAE)
Information Science Reference • © 2024 • 330pp • H/C (ISBN: 9798369302453) • US $230.00

Fostering Foreign Language Teaching and Learning Environments With Contemporary Technologies
Zeynep Çetin Köroğlu (Aksaray University, Turkey) and Abdulvahit Çakır (Ufuk University, Turkey)
Information Science Reference • © 2024 • 338pp • H/C (ISBN: 9798369303535) • US $230.00

Embracing Cutting-Edge Technology in Modern Educational Settings

Ken Nee Chee (Universiti Pendidikan Sultan Idris, Malaysia) and Mageswaran Sanmugam (Universiti Sains Ma-
laysia, Malaysia)
Information Science Reference • © 2024 • 334pp • H/C (ISBN: 9798369310229) • US $240.00

701 East Chocolate Avenue, Hershey, PA 17033, USA

Tel: 717-533-8845 x100 • Fax: 717-533-8661
E-Mail: [email protected] • www.igi-global.com
Table of Contents

Preface.................................................................................................................................................. xiv

Acknowledgment................................................................................................................................. xxi

Section 1
Preview: AI and Language Education

Chapter 1
The Integration of ChatGPT in Language Education: Exploring Contexts, Assessing Impacts, and
Unpacking Implications........................................................................................................................... 1
Weiming Liu, Dublin City University, Ireland

Chapter 2
Enhancing Language Teaching Materials Through Artificial Intelligence: Opportunities and
Challenges.............................................................................................................................................. 22
Surjit Singha, Kristu Jayanti College (Autonomous), India
Ranjit Singha, Christ University, India
Elizabeth Jasmine, Indian Institute of Psychology and Research, India

Chapter 3
The Reality of Artificiality: The Impact of Artificial Intelligence on Language and Culture Course
Assessments and Rubrics....................................................................................................................... 43
Teresa Lobalsamo, University of Toronto Mississauga, Canada
Dellannia Segreti, University of Toronto Mississauga, Canada
Mohammad J. Jamali, University of Toronto, Canada
Sylvia Gaspari, University of Toronto, Canada

Section 2
Perspectives: What People Say About AI

Chapter 4
Enriching the Teaching-Learning Experience by Using AI Tools in the L2 Classroom....................... 61
Dimaris Barrios-Beltran, Mount Holyoke College, USA

Chapter 5
A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence in EFL Education........... 78
Nazmi Dincer, Turkish Air Force Academy, Turkey
Samet Bal, Turkish Airlines, Turkey

Chapter 6
AI-Powered Lesson Planning: Insights From Future EFL Teachers................................................... 101
Banu Çiçek Başaran Uysal, Eskisehir Osmangazi University, Turkey
İlknur Yüksel, Eskisehir Osmangazi University, Turkey

Chapter 7
Discussions of Using AI in Language Education in Hong Kong........................................................ 133
Siu-lun Lee, The Chinese University of Hong Kong, Hong Kong
Yongyin Chen, Independent Researcher, Hong Kong

Chapter 8
What Are Students Saying About AI as an Academic Tool................................................................ 149
Lee Luan Ng, Universiti Malaya, Malaysia
Venosha Ravana, Tunku Abdul Rahman University of Management and Technology,
Malaysia

Section 3
Practice: Use of AI in Language Education

Chapter 9
Integrating ChatGPT Into a Culture-Focused Flipped Curriculum for Chinese as a Foreign
Language: Experiments and Implications............................................................................................ 173
Jianfen Wang, Berea College, USA

Chapter 10
Redefining Traditional Pedagogy: The Integration of Machine Learning in the Contemporary
Language Education Classroom.......................................................................................................... 195
Géraldine Bengsch, University of York, UK

Chapter 11
Creating Stories: Generative Artificial Intelligence Tools as Writing Tutors...................................... 222
Franziska Lys, Northwestern University, USA

Chapter 12
Redesigning a Foreign Language Course With the Help of AI: Benefits and Challenges.................. 244
Natalie Khazaal, Georgia Institute of Technology, USA

Chapter 13
Utilizing a ChatGPT Workshop to Foster Ethical Awareness and Enhance L2 English Writing
Revision Processes in University Academic Settings: ChatGPT Workshop for Effective and
Ethical L2 English Writing.................................................................................................................. 269
Sohyeon Lee, University of Hawaii at Manoa, USA

Chapter 14
Leveraging AI and Pluralistic Approaches for Language Teaching: A Focus on Inter-
Comprehension Between Related Languages...................................................................................... 300
Lourdes Barquín Sanmartín, University College Dublin, Ireland

Chapter 15
Designing Language Learning Experiences With Generative AI Tools.............................................. 324
Betül C. Czerkawski, College of Applied Science and Technology, University of Arizona,
USA

Compilation of References................................................................................................................ 342

About the Contributors..................................................................................................................... 377

Index.................................................................................................................................................... 382
Detailed Table of Contents

Preface.................................................................................................................................................. xiv

Acknowledgment................................................................................................................................. xxi

Section 1
Preview: AI and Language Education

The integration of artificial intelligence (AI) in language education, exemplified by tools like ChatGPT, has
sparked significant discourse. Since its introduction, ChatGPT has established itself as an indispensable
educational tool and its relentless advancement remains undeniable. Therefore, comprehending the
impact and educational potential of AI becomes paramount. This chapter explores the research contexts
that provide insights into the background relevant to the integration of ChatGPT in language education.
It also delves into the benefits and the current research issues in AI-enhanced language education. In
essence, this chapter aims to shed light on the current landscape of AI in language education and its
potential implications for teaching and learning. As the realm of language education experiences evolving
innovation, this chapter emerges as a guiding beacon and illuminates pathways to harness the potential
of AI in language education while upholding ethical standards and ensuring meaningful pedagogical
transformations.

Incorporating artificial intelligence (AI) into language education signifies a paradigm shift that promotes
originality and inclusiveness. The partnership between AI developers and educators effectively tackles
obstacles and establishes a foundation for continuous progress. Anticipating the future, the progression
of AI holds the potential to deliver intricate customization, customizing educational encounters to suit
the unique requirements of each individual. Responsible incorporation of AI into teaching methodologies
transforms them into a collaborative model that empowers educators to engage in individualized interactions.

Ethics remain of the utmost importance, encompassing bias mitigation and privacy. In essence, the
integration of AI into language education signifies an impending era in which the combined powers of
technology and human proficiency foster the development of capable individuals who are prepared to
navigate an interconnected, digitally globalized society.

As artificial intelligence (AI) continues to increase its presence and accessibility within education, the
need to address AI’s impact on assignment design and the production of original coursework is heightened.
Within the context of an undergraduate language and culture course, this chapter thus offers reflections
on the integration of AI tools and their effect on shaping assessment methods. The authors also highlight
that there indeed remains a great need for continued research in the realm of AI and education going
forward, especially where enhanced AI-detection technologies, institutional policies, academic rigour,
and learner expressiveness are concerned.

Section 2
Perspectives: What People Say About AI

Chapter 4
Enriching the Teaching-Learning Experience by Using AI Tools in the L2 Classroom....................... 61
Dimaris Barrios-Beltran, Mount Holyoke College, USA

Artificial intelligence (AI) has emerged as a transformative force in second language (L2) education,
reshaping teaching and learning methodologies. This chapter explores AI’s impact on L2 educators and
learners through insights from questionnaires and a follow-up conversation. Initial apprehension towards
AI is counterbalanced by curiosity about its potential to enhance educational practices. The chapter
provides practical guidance, showcasing how AI tools can be aligned with key language learning skills
and offering structured examples of activities to enhance these skills. It highlights AI’s role in providing
immediate feedback, simplifying complex concepts, and creating inclusive classrooms tailored to individual
learning styles and needs. The discussion also addresses educators’ recognition of AI’s potential and
underscores the need for clear guidelines and training in ethical AI implementation. As AI technology
evolves, it promises a more personalized, dynamic educational journey, enriching the L2 learning process.

Artificial intelligence influences education, particularly language instruction. Despite its expanding
attention, few studies have examined teachers’ views on AI in education. This qualitative study explores
EFL teachers’ AI-related views and insights. The study uses semi-structured interviews with 21 instructors
from diverse universities to uncover complex attitudes toward AI, pedagogical ideologies, perceived

benefits and drawbacks of AI, and privacy concerns. The study highlights four main themes: AI’s capacity
to adapt to individual learning needs, its influence on pedagogical dynamics, the need for technical
proficiency to integrate AI, and ethical and security issues related to AI use. These results highlight the
perceived benefits and challenges educators face when using AI and emphasize the need for continued
research to develop successful AI integration techniques for language instruction.

This chapter explores the integration of artificial intelligence (AI) into language education, focusing on
the perspectives of pre-service English as a foreign language (EFL) teachers. Employing a mixed-methods
approach, the study investigates the effectiveness of AI-powered lesson plans, specifically designed
for teaching writing to 5th-grade students. Through a comprehensive evaluation rubric and qualitative
analysis, the research identifies strengths, areas for improvement, and suggested changes in AI-generated
lesson plans. Findings highlight the tool’s success in engagement, appropriateness, and overall structure,
while indicating challenges in differentiation and assessment. The chapter concludes with implications
for teacher training in AI literacy, emphasizing the need for educators equipped to harness the potential
of AI in diverse language teaching settings.

This chapter sets out to investigate the discussions of using AI in language education in Chinese press in
Hong Kong. From 2018-2023, there are news articles showcasing the AI tools and potential use of AI in
language education in Hong Kong. This chapter discusses the debates on the use of artificial intelligence
in language education and analyses newspaper discourse to investigate the different views of stakeholders
in language education including students, teachers, educators, and policymakers in Hong Kong. A corpus
containing Hong Kong newspaper articles discussing and debating the effectiveness and challenges of
applying artificial intelligence in language education in Hong Kong has been constructed and analysed.

The introduction of artificial intelligence, ChatGPT, and other machine learning technologies has shaken
up numerous industries across the globe. The World Economic Forum Future of Jobs Report 2023 predicts
that due to a combination of macro trends and technology adoption, over the next five years jobs in the
education industry are expected to grow at least by 10%. Many learners in higher education are integrating
the use of AI when attending to their academic work, yet there is not much investigation exploring how
they plan and perceive the use of AI whilst completing their academic tasks. Therefore, this chapter aims
to (1) explore how learners’ intention of using AI affects their language learning behavior and (2) uncover
the factors that influence the learners’ perceptions toward the usefulness of AI as an academic support.

Grounded in the theory of planned behavior (TPB), students from two tertiary education institutions
in Malaysia were asked to respond to a series of questions that explored their perspectives on utilizing
AI-powered tools to aid their academic writing.

Section 3
Practice: Use of AI in Language Education

This chapter explores ChatGPT’s potential for assisting in a culture-focused flipped curriculum to
facilitate the development of intercultural communicative competence, a core value of foreign language
education in the 21st century. Three experiments assess ChatGPT’s performance in generating scenarios
and performance scripts for practicing intercultural communication in Chinese-speaking contexts. While
ChatGPT demonstrates remarkable linguistic accuracy and comprehension abilities, it struggles to
generate scripts that reflect communicative strategies specific to Chinese-speaking contexts, especially
when the prompt lacks explicit instructions about Chinese cultural expectations. The limitation can be
rooted in ChatGPT’s training and the user’s ineffective prompting. The findings suggest that ChatGPT
is better suited as a reference tool than a primary learning resource in the curriculum. The implications
for foreign language education and the integration of AI are also discussed.

The digital transformation of education, accelerated by unforeseen global events like the COVID-19
pandemic, has ushered in a new era in pedagogy, including in language instruction. While the shift
to online platforms has been swift, the evolution of content from static digital forms to dynamic,
interactive experiences driven by artificial intelligence (AI) is still emerging. This chapter explores the
transformative potential of machine learning (ML) in redefining traditional language learning materials
into adaptive, responsive, and personalised educational experiences. The chapter outlines theoretical
applications and presents a prototype app, “TalkToMe,” designed to boost speaking practice in the
target language. Additionally, it addresses ethical concerns surrounding ML integration in education,
ensuring the preservation of academic integrity. This chapter aims to bridge the gap between traditional
methodologies and cutting-edge technology, offering a roadmap for the future of language instruction
through collaboration between pedagogy and technology.

Chapter 11
Creating Stories: Generative Artificial Intelligence Tools as Writing Tutors...................................... 222
Franziska Lys, Northwestern University, USA

This chapter focuses on examining the strengths and limitations of prompt-driven ChatGPT for a creative
writing task using German as a foreign language. College students of German at the advanced level were
asked to develop, write, and illustrate a unique children’s story using ChatGPT as a thinking partner.
Interacting with ChatGPT in German, students engaged in informal and low-stakes writing-to-learn

activities that could help them think through ideas and key concepts for their stories, as well as learn
new vocabulary, expressions, and language patterns. Answering to learner-produced prompts, ChatGPT
provided both explicit and implicit learning situations that focused on vocabulary development and
grammar in a meaning-focused context, creating conditions in which learners could learn according
to their current language proficiency. The author discusses how they set up the project, what tasks and
prompts they used to elicit content, and how they prepared illustrations using an artificial intelligence
image generator.

Chapter 12
Redesigning a Foreign Language Course With the Help of AI: Benefits and Challenges.................. 244
Natalie Khazaal, Georgia Institute of Technology, USA

This chapter evaluates the use of AI for redesigning a foreign (Arabic) language course to significantly
incorporate several SDGs. The course provides conditions for experiential learning where students
examine their impact on the planet, make meaningful improvements to their lifestyles to lower their
carbon footprint, and grow as thoughtful global citizens. It also stimulates students to reflect on the
differences between Western and Arab countries’ engagement with sustainability goals through real-
world scenarios. The analysis focuses on the positive contributions and challenges that AI presents
toward the redesigning goal. In particular, it explores how using AI technology in class and for creating
course materials affects HIPs elements: significant time on task; frequent, timely feedback; substantive
interactions with faculty, peers, and diverse people and ideas; structured reflection and integration of
learning; real-world applications; public demonstration of competence; significant learning elements:
foundational knowledge, application, integration, human dimension, and learning to learn.

This chapter explores the design and implementation of a ChatGPT workshop for multilingual university
students, focusing on enhancing their L2 English academic writing skills. Utilizing the analyze, design,
evaluate (ADE) model, the workshop incorporates practical activities to guide effective, critical, and
ethical use of ChatGPT. It addresses challenges faced by L2 learners, emphasizing the tool’s role in
providing personalized feedback and improving revision processes. Ethical considerations, particularly
in maintaining academic integrity, are highlighted. Insights reveal ChatGPT’s value as an aid in the
writing process, encouraging its use as a facilitator rather than a substitute for students’ work. The chapter
concludes with recommendations for educators and future research directions in AI and language education.

This chapter introduces the pluralistic teaching approach of inter-comprehension utilizing the AI tool
ChatGPT. Its objective is to heighten inter-comprehensive awareness among native English speakers
studying Spanish and facilitate the comprehension of structurally asymmetrical grammatical phenomena
between Romance languages and English. Specifically tailored to the British educational context, where

the typical language sequence comprises L1 English, L2 French, and L3 Spanish, this chapter draws
support from L3 acquisition literature. Focused on the aspectual contrast perfective/imperfective, less
prominent in English compared to Romance languages, the author showcases how to generate parallel
contrastive analyses of Spanish/French/English translations through ChatGPT.

Artificial intelligence (AI), particularly generative AI, can present many opportunities for language
learners to practice and improve their language skills, receive timely feedback on their performance, and
customize their learning based on their needs and language proficiency. AI’s benefits are not limited to
second language (L2) learners. Instructors can also benefit from the novel generative AI technologies
by using them in curriculum and lesson design, developing new teaching and assessment materials, or
addressing diverse learner skills and needs. Despite AI’s advantages, the main issue is how to design L2
environments effectively so learners can receive the best benefits from AI while reducing some associated
drawbacks. This chapter argues that learning experience design (LXD) presents a road map for L2
instructors as they incorporate generative AI into their instruction. If the learning design is random and
left to good intentions, achieving meaningful learning outcomes will also be left to chance. Following
proven LXD guidelines may help alleviate the confusion around AI.

Compilation of References................................................................................................................ 342

About the Contributors..................................................................................................................... 377

Index.................................................................................................................................................... 382
xiv

Preface

Welcome to AI in Language Teaching, Learning, and Assessment. This book marks a pivotal explora-
tion into the dynamic realm of artificial intelligence (AI) within the context of language education. In
recent times, the advent of technologies like ChatGPT has ignited fervent discussions about the role and
impact of AI in educational settings (Kasneci et al., 2023; Perkins, 2023).

WHY AI AND LANGUAGE EDUCATION?

I still vividly remember my first conversation on ChatGPT. I was talking with a Spanish teacher back in
early December 2022. She was deeply impressed by its myriad possibilities extending from simulating
human conversation to generating intricate responses that encompass diverse tasks such as answering
queries, crafting essays, and composing music. But at the same time, she was worried about academic
misconduct and its impact on assessment methods, and even expressed concern over the possible replace-
ment of language teachers in the future, which I greatly empathized with. We did not know how much it
would impact our teaching and how educational systems would respond to it, but we were certain it would
change the current pedagogical environment profoundly and that we must be ready for such changes.
We were right. The introduction of ChatGPT has spurred divergent opinions, both commendations
and apprehensions, within academia (Meyer et al., 2023; Shen et al., 2023). While some educators envi-
sion its potential as an asset for teaching, learning, and assessment (Hong.,2023; Kohnke, 2023; Kohnke
et al., 2023; Rudolph et al., 2023), others voice concerns regarding its effect on academic integrity
and ethical considerations (Cotton et al., 2023; Rane et al., 2023; Teng, 2023), incorrect or misleading
information (Borji, 2023), and other issues such as biased or inappropriate content (Baidoo-Anu et al.,
2023; Sallam, 2023).
Undeniably, the drawbacks associated with AI in education merit attention (Qadir., 2023). However,
the inexorable march of technological advancement necessitates an adaptable educational landscape -
one that embraces emerging technologies while upholding ethical standards (Kamalov., 2023; Perera et
al., 2023). Thus, there arises an imperative need to delve deeper into AI, navigating its complexities to
harness its positive potential in education. Motivated by precisely these points, I set about creating AI
in Language Teaching, Learning, and Assessment.

Preface

EXPLORATION, ASPIRATION, AND COLLABORATION

This book zooms in on the intersection of AI and language education, aiming to explore how AI can be
effectively supervised, ensuring academic integrity while bolstering its role in teaching, learning, and
assessment.
Throughout its chapters, this book endeavors to address pivotal inquiries such as unpacking the chal-
lenges inherent in AI application within language education and strategies to mitigate them, identifying
resources to ensure the ethical and secure deployment of AI in academic settings, scrutinizing the merits
of integrating AI in language teaching, learning, and assessment, presenting and analyzing successful
cases illustrating the effective utilization of AI in educational contexts, and pioneering discussions on
potential advancements and future trajectories for AI in language education.
Chapters from the below countries or regions are included in the book: Canada (Lobalsamo, Segreti,
Jamali & Gaspari), Hong Kong (Lee & Chen), Ireland (Liu, Sanmartín), India (S. Singha, R. Singha &
Jasmine), Malaysia (Ng & Ravana), Turkey (Dincer & Bal, Uysal & Yüksel), United Kingdom (Bengsch),
United States (Barrios-Beltran, Czerkawski, Khazaal, Lee, Lys, Wang). Their objectives are to offer
insights, contemporary research perspectives, and educational cases that stimulate academic dialogues
while advocating for the judicious use of AI in language education. All the chapters aspire to disseminate
best practices within the language teaching community and foster collaboration to navigate potential
biases or discriminatory outcomes arising from AI deployment.
I invite readers on an enlightening journey through the nuances of AI in language education, urging
collaborative efforts toward harnessing its potential for the betterment of educational landscapes worldwide.

STRUCTURE OF THE BOOK

This book caters not only to those passionate about language education but also to language learners,
educators, researchers, scholars, and AI developers seeking to explore and apply AI in educational
domains. It is a comprehensive resource offering a roadmap to bridge the realms of AI technology and
language education.
The chapters encompass a wide spectrum of topics, including but not limited to the synergy between
artificial intelligence and pedagogy, explorations into AI’s influence on teaching materials, assessing the
impact of AI in educational evaluation, the convergence of AI and applied linguistics, and pioneering
advancements in AI-driven language education development.
This book is divided into three sections:

Section 1: Preview - AI and Language Education

Section 2: Perspectives - What People Say About AI
Section 3: Practice - Use of AI in Language Education

There are three chapters in Section 1.

xv
Preface

1. The Integration of ChatGPT in Language Education: Exploring

Contexts, Assessing Impacts, and Unpacking Implications

Liu delves into ChatGPT’s integration in language education, discussing research contexts, benefits, and
current issues. Through comprehensive exploration of AI in language education, Liu offers insights into
its implications for teaching and learning.

2. Enhancing Language Teaching Materials Through

Artificial Intelligence: Opportunities and Challenges

Addressing the paradigm shift in language education, S. Singha, R. Singha, and Jasmine provide a com-
prehensive overview of AI and language education by exploring AI’s potential for personalized learning
and ethical considerations. They emphasize collaboration between AI developers and educators to navigate
biases, privacy, and customization, ultimately fostering capable individuals in a digitally connected world.

3. The Reality of Artificiality: The Impact of Artificial Intelligence

on Language and Culture Course Assessments and Rubrics

Reflecting on AI’s impact on assessment design in a language and culture course, Lobalsamo, Segreti,
Jamali, and Gaspari address AI tools’ influence on assignment creation and original coursework produc-
tion. Their chapter emphasizes the need for continued research in AI and education, especially regarding
AI-detection technologies and academic rigor.
There are five chapters in Section 2.

4. Enriching the Teaching-Learning Experience by

Using AI Tools in the L2 Classroom

Through insights from questionnaires and follow-up conversations, Barrios-Beltrán assesses AI’s impact
on L2 education, presenting insights from questionnaires and activities aligned with language learning
skills. The chapter emphasizes AI’s role in immediate feedback, simplifying complex concepts, and
creating inclusive classrooms, advocating for ethical AI implementation and educator training.

5. A Qualitative Journey on Instructors’ Perceptions

of Artificial Intelligence in EFL Education

Dincer and Bal delve into EFL instructors’ perspectives on AI in education, uncovering intricate attitudes
and concerns through a qualitative study by interviewing 21 diverse university instructors. They reveal
insights into AI’s adaptability, pedagogical impact, technical proficiency requirements, and ethical/
security concerns. Their chapter emphasizes the need for ongoing research to effectively integrate AI in
language instruction while acknowledging the challenges and benefits educators encounter.

xvi
Preface

6. AI-Powered Lesson Planning: Insights From Future EFL Teachers

Focused on pre-service EFL teachers, Uysal and Yüksel examine AI-driven lesson plans designed for
5th-grade writing classes. Using a mixed-methods approach, they assess the efficacy of AI-generated
plans, identifying strengths in engagement and structure while noting areas for improvement in differ-
entiation and assessment. Their chapter underscores the necessity of AI literacy in teacher training for
effective AI utilization in diverse language teaching contexts.

7. Discussions of Using AI in Language Education in Hong Kong

Investigating Hong Kong’s discourse on AI in language education, Lee and Chen analyze newspaper
articles from 2018-2023. They delve into debates and viewpoints from various stakeholders, shedding
light on perceptions of AI’s effectiveness and challenges in language education.

8. What Are Students Saying About AI as an Academic Tool?

Ng and Ravana delve into the impact of AI, including ChatGPT, on the academic experiences of learners.
Their chapter aims to uncover students’ intentions and perceptions regarding the use of AI in language
learning. Grounded in the Theory of Planned Behavior, they present insights from Malaysian tertiary
education institutions, shedding light on how students view AI-powered tools for academic writing and
its influence on their language learning behavior.
There are seven chapters in section 3.

9. Integrating ChatGPT Into a Culture-focused Flipped Curriculum for

Chinese as a Foreign Language: Experiments and Implications

Focusing on ChatGPT’s role in a culture-focused flipped curriculum for Chinese as a foreign language,
Wang discusses its performance in generating scenarios and scripts for intercultural communication
practice. While noting ChatGPT’s linguistic accuracy, Wang explores challenges in generating context-
specific scripts, suggesting its use as a reference tool rather than a primary learning resource.

10. Redefining Traditional Pedagogy: The Integration of Machine

Learning in the Contemporary Language Education Classroom

Examining the shift in language instruction due to digital transformation, Bengsch explores Machine
Learning’s potential in personalized language learning experiences, presents a speaking practice proto-
type app “TalkToMe,” and addresses ethical concerns, aiming to bridge traditional methodologies and
AI-driven education.

11. Creating Stories: Generative Artificial Intelligence Tools as Writing Tutors

Lys explores the use of prompt-driven ChatGPT in developing children’s stories by a group of advanced
German learners. The chapter highlights ChatGPT’s role as a thinking partner, aiding students in brain-

xvii
Preface

storming, vocabulary expansion, and language pattern learning. The discussion focuses on project setup,
prompts used for content elicitation, and the integration of AI-generated illustrations.

12. Redesigning a Foreign Language Course With

the Help of AI: Benefits and Challenges

Focusing on the redesign of a foreign language (Arabic) course, Khazaal evaluates the use of AI to
align with Sustainable Development Goals (SDGs). It explores how AI facilitates experiential learn-
ing, encouraging students to reflect on sustainability issues. Khazaal highlights positive contributions
and challenges of AI in achieving the redesign goals, particularly in elements related to High-Impact
Practices (HIPs) and significant learning.

13. Utilizing a ChatGPT Workshop to Foster Ethical Awareness and

Enhance L2 English Writing Revision Processes in University Academic
Settings: ChatGPT Workshop for Effective and Ethical L2 English Writing

Exploring a ChatGPT workshop’s design for multilingual university students, Lee focuses on enhancing
L2 English writing skills. The chapter emphasizes ethical use, providing personalized feedback, and im-
proving revision processes while offering recommendations for educators and future AI-related research.

14. Leveraging AI and Pluralistic Approaches for Language Teaching:

A Focus on Inter-Comprehension Between Related Languages

Sanmartín introduces pluralistic teaching approach utilizing ChatGPT, aiming to enhance inter-com-
prehensive awareness among English speakers studying Spanish. Sanmartín provides parallel contras-
tive analyses of translations, focusing on structurally asymmetrical grammatical phenomena between
Romance languages and English.

15. Designing Language Learning Experiences With Generative AI Tools

Czerkawski emphasizes the opportunities AI presents for language learners, highlighting its potential for
personalized learning experiences and timely feedback. The chapter underscores the broader applications
for instructors, suggesting ways to leverage generative AI in curriculum design and addressing diverse
learner needs. Despite the advantages, Czerkawski acknowledges the challenges of effective design for
language learning environments using AI and advocates for the adoption of learning experience design
(LXD) principles to ensure meaningful outcomes.

IN SUMMARY

In navigating the nuanced terrain of AI in language education, this book has ventured into diverse realms
and unveiled multifaceted insights and perspectives. Each chapter has contributed a crucial piece to the
mosaic of understanding AI’s impact on language instruction.

xviii
Preface

Through qualitative studies, experimental implementations, and analyses of AI tools like ChatGPT,
our contributors have delineated both the promises and the challenges associated with integrating AI
into language teaching and learning. The discourse on AI’s capacity to adapt to individual learning
needs, its ethical implications, and its potential to revolutionize pedagogical dynamics have been both
enriching and thought-provoking.
We have explored the potential of AI as a creative writing partner, a facilitator for intercultural com-
munication, and a tool for enhancing the quality of language learning materials. As we journeyed through
the evolving landscape of AI in language education, ethical considerations such as privacy, academic
integrity, and bias mitigation, have stood as guiding beacons illuminating the way forward.
However, this exploration is not merely an endpoint but a catalyst for continued discourse and growth.
It underscores the imperative need for ongoing research, pedagogical adaptation, and educator prepared-
ness to harness the potential of AI while safeguarding the integrity of language education.
As the educational horizon continues to evolve, the integration of AI within language education signi-
fies not just a technological shift but a paradigmatic transformation. It signifies a collaborative alliance
between human proficiency and technological prowess, fostering an environment where AI serves as a
catalyst for personalized, dynamic, and inclusive language learning experiences.
I hope this compilation serves as a comprehensive guide, a catalyst for discussions, and an impetus for
further exploration of AI’s role in language education. May it inspire educators, researchers, developers,
and policymakers to collaboratively pave the way for an educational landscape that embraces innovation,
ethics, and inclusive pedagogical practices. Together, let us embark on this transformative journey in
language education, where the synergy of AI and human expertise propels us toward an ever evolving,
empowered educational future.

Fang Pan
London School of Economics and Political Science, UK

REFERENCES

Baidoo-Anu, D., & Ansah, L. O. (2023). Education in the era of generative artificial intelligence (AI):
Understanding the potential benefits of ChatGPT in promoting teaching and learning. Journal of AI,
7(1), 52–62. doi:10.61969/jai.1337500
Borji, A. (2023). A categorical archive of ChatGPT failures. arXiv preprint arXiv:2302.03494.
doi:10.21203/rs.3.rs-2895792/v1
Cotton, D. R., Cotton, P. A., & Shipway, J. R. (2023). Chatting and cheating: Ensuring academic integ-
rity in the era of ChatGPT. Innovations in Education and Teaching International, 1–12. doi:10.1080/1
4703297.2023.2190148
Hong, W. C. H. (2023). The impact of ChatGPT on foreign language teaching and learning: Opportuni-
ties in education and research. Journal of Educational Technology and Innovation, 5(1), 37–45.
Kamalov, F., Santandreu Calonge, D., & Gurrib, I. (2023). New era of artificial intelligence in educa-
tion: Towards a sustainable multifaceted revolution. Sustainability (Basel), 15(16), 12451. doi:10.3390/
su151612451

xix
Preface

Kasneci, E., Seßler, K., Küchemann, S., Bannert, M., Dementieva, D., Fischer, F., Gasser, U., Groh, G.,
Günnemann, S., Hüllermeier, E., Krusche, S., Kutyniok, G., Michaeli, T., Nerdel, C., Pfeffer, J., Poquet,
O., Sailer, M., Schmidt, A., Seidel, T., ... Kasneci, G. (2023). ChatGPT for good? On opportunities and
challenges of large language models for education. Learning and Individual Differences, 103, 102274.
doi:10.1016/j.lindif.2023.102274
Kohnke, L. (2023). L2 learners’ perceptions of a chatbot as a potential independent language learning
tool. International Journal of Mobile Learning and Organisation, 17(1–2), 214–226. doi:10.1504/
IJMLO.2023.128339
Kohnke, L., Moorhouse, B. L., & Zou, D. (2023). ChatGPT for language learning and teaching. RELC
Journal, 1–14.
Meyer, J. G., Urbanowicz, R. J., Martin, P. C., O’Connor, K., Li, R., Peng, P. C., Bright, T. J., Tatonetti,
N., Won, K. J., Gonzalez-Hernandez, G., & Moore, J. H. (2023). ChatGPT and large language models in
academia: Opportunities and challenges. BioData Mining, 16(1), 20. doi:10.1186/s13040-023-00339-9
PMID:37443040
Perera, P., & Lankathilaka, M. (2023). AI in higher education: A literature review of chatgpt and guidelines
for responsible implementation. International Journal of Research and Innovation in Social Science,
VII(VI), 306–314. doi:10.47772/IJRISS.2023.7623
Perkins, M. (2023). Academic Integrity Considerations of AI Large Language Models in the Post-
Pandemic Era: ChatGPT and Beyond. Journal of University Teaching & Learning Practice, 20(2), 7.
Qadir, J. (2023, May). Engineering education in the era of ChatGPT: Promise and pitfalls of generative
AI for education. In 2023 IEEE Global Engineering Education Conference (EDUCON) (pp. 1-9). IEEE.
10.1109/EDUCON54358.2023.10125121
Rane, N. L., Choudhary, S. P., Tawde, A., & Rane, J. (2023). ChatGPT is not capable of serving as an
author: Ethical concerns and challenges of large language models in education. International Research
Journal of Modernization in Engineering Technology and Science, 5(10), 851–874.
Rudolph, J., Tan, S., & Tan, S. (2023). ChatGPT: Bullshit spewer or the end of traditional assessments
in higher education? Journal of Applied Teaching & Learning, 6(1), 342–362.
Shen, Y., Heacock, L., Elias, J., Hentel, K. D., Reig, B., Shih, G., & Moy, L. (2023). ChatGPT and other
large language models are double-edged swords. Radiology, 307(2), e230163. doi:10.1148/radiol.230163
PMID:36700838
Teng, F. (2023). Scientific writing, reviewing, and editing for open-access TESOL journals: The role of
ChatGPT. International Journal of TESOL Studies, 5, 87–91.

xx
xxi

Acknowledgment

Firstly, I would like to acknowledge the contribution of all authors involved in this project. My sincere
gratitude goes to all who contributed their time and expertise. The ideas and contributions that everyone
has put into this book have been truly inspiring.

Secondly, I would like to acknowledge the valuable contributions from the reviewers to improve the
quality, coherence, and content presentation of the chapters. Most of the authors also served as referees
and their valuable input is highly appreciated. I would like to extend special thanks to Prof. Miao-Fen
Tseng, Dr. Alison Standring, and Dr. Peter Skrandies who assisted with the review process. Without
their significant support, this book would not be possible.

Last but not least, I would like to give my sincere thanks and love to my family and friends who sup-
ported me during the process of editing this book.

Section 1
Preview:
AI and Language Education
1

Chapter 1
The Integration of ChatGPT
in Language Education:
Exploring Contexts, Assessing Impacts,
and Unpacking Implications

Weiming Liu
https://orcid.org/0000-0002-2468-6911
Dublin City University, Ireland

ABSTRACT
The integration of artificial intelligence (AI) in language education, exemplified by tools like ChatGPT,
has sparked significant discourse. Since its introduction, ChatGPT has established itself as an indispens-
able educational tool and its relentless advancement remains undeniable. Therefore, comprehending the
impact and educational potential of AI becomes paramount. This chapter explores the research contexts
that provide insights into the background relevant to the integration of ChatGPT in language educa-
tion. It also delves into the benefits and the current research issues in AI-enhanced language education.
In essence, this chapter aims to shed light on the current landscape of AI in language education and
its potential implications for teaching and learning. As the realm of language education experiences
evolving innovation, this chapter emerges as a guiding beacon and illuminates pathways to harness
the potential of AI in language education while upholding ethical standards and ensuring meaningful
pedagogical transformations.

Language education fosters meaningful communication and interaction. At its core, it equips learners
with indispensable skills to bridge linguistic divides and facilitates connections and collaborations
across geographical borders. As teaching and learning innovations continue to be tested and researched,
new insights are gained that influence teaching practices globally (Moeller & Catalano, 2015). Online
platforms, interactive apps and immersive language experiences have opened doors to enhance educa-
tion. In this digital age, technology is reshaping global communication, and digital literacy has become
increasingly significant in foreign language use. This shift necessitates acquiring additional skills and

DOI: 10.4018/979-8-3693-0872-1.ch001

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

The Integration of ChatGPT in Language Education

a nuanced ability to navigate multimodal practices. Such practices include utilising diverse multimedia
channels and creatively exploring newly enhanced technological options to align with the evolving land-
scape of language education (Auer et al., 2022; Golonka et al., 2014; Shadiev & Yang, 2020; Ziegler &
González-Lloret, 2022).
The rapid advancement of technology brings about a transformative era in language education, with
a profound impact stemming from the integration of artificial intelligence (AI). A new wave of AI tools
is emerging. They can be used to create new content, including text, images and computer programmes
(Kukulska-Hulme et al., 2023). One such platform is ChatGPT, a cutting-edge AI language model, de-
veloped by OpenAI. The remarkable ability of ChatGPT to handle complex tasks has garnered signifi-
cant attention in research articles within the domain of language education. While existing research has
examined various aspects of ChatGPT in the context of language education, a noticeable gap persists in
comprehensively understanding its empirical integration. This chapter aims to bridge this gap by ana-
lysing a collection of journal articles. It explores the specific research contexts in which ChatGPT has
been integrated. It also discusses the benefits and challenges of an AI-enhanced learning environment.
Furthermore, the chapter delves into the potential implications of such technologies on teaching and
learning practices. As the field of language education evolves, the chapter emphasises the importance
of adhering to ethical standards and highlights the significant improvements that AI can bring to peda-
gogical practices.

LITERATURE REVIEW

The role of AI in language education continually evolves and reshapes teaching and learning methods
with the goal to enrich the language learning experience. The integration of AI has ignited substantial
interest and debate among educators and researchers (Crompton & Burke, 2023; Huang et al., 2023;
Rebolledo Font De La Vall & González Araya, 2023). The introduction of ChatGPT into language edu-
cation has been hailed as a significant breakthrough in the field of AI (Roumeliotis & Tselikas, 2023).
It is designed to engage in conversations with its users, respond to commands and produce text that
appears to have been created by a human (Kukulska-Hulme et al., 2023). As a prominent AI language
model, ChatGPT has attracted considerable attention in the field of language education and has become
an increasingly prevalent and powerful tool for language learning and teaching.
Numerous researchers (Bai̇doo-Anu & Ansah, 2023; Baskara & Mukarto, 2023; Cai, 2023; Hong,
2023; Kasneci et al., 2023; Kohnke et al., 2023) have collectively underscored ChatGPT’s significant
pedagogical impact, highlighting its wide range of educational affordances. ChatGPT enriches language
learning by providing a dynamic and interactive experience that cultivates authentic conversations with
the chatbot. It serves as both a tutor and teacher for language learners, with a primary focus on enhanc-
ing personalised learning experiences. ChatGPT is capable of offering language instruction, creating
materials and developing activities tailored to individual learners’ needs, interests, pace and language
proficiency level. Another notable affordance of ChatGPT lies in its ability to provide immediate
feedback. Its conversational capabilities enable learners to receive real-time feedback, helping them to
refine their language proficiency and conversational fluency. This feature is invaluable for promptly
identifying and rectifying language errors. Furthermore, ChatGPT supports self-evaluation, allowing
learners to generate quizzes for self-assessment. This self-monitoring feature helps learners to track
their progress and make informed decisions about their language learning journey. In addition, since the

2

The Integration of ChatGPT in Language Education

interactions occur with a machine, the secure and comfortable nature of the practice alleviates learners’
concerns about making mistakes in front of others. This sense of security plays a crucial role in building
confidence and encouraging active participation. Moreover, researchers argue that ChatGPT fosters a
motivating learning environment. It gives learners control and keeps them engaged, further enhancing
the effectiveness of language learning.
ChatGPT is a versatile and competent assistant that plays a notable role in supporting language edu-
cators. It offers a rich repository of content and examples to enhance teaching materials and curriculum
development. Researchers have explored its potential as a teaching tool and its capacity to alleviate
teachers’ workload and provide substantial opportunities for teachers and educational institutions to
enhance foreign language teaching and assessments. They have also shed light on how educators harness
this platform to enhance language education (Hong, 2023). Simultaneously, it frees educators to focus
on delivering personalised instruction and addressing the unique learning needs of individual students.
As a result, ChatGPT serves as a facilitator in the educational process by delivering essential facts and
fundamental knowledge when empowering educators to concentrate on the more nuanced aspects of
teaching (Cai, 2023).
While the potential of ChatGPT in language education is evident, it is essential to acknowledge the
challenges that come with its integration. Kohnke et al. (2023) distil these challenges into three core
debates. The first debate delves into the ethical aspects of the use of ChatGPT in education in relation
to concerns about potential cheating and its impact on assessment methodologies. Their second debate
scrutinises the accuracy of chatbot responses, while their third discussion brings to light the cultural
bias inherent in the source database and algorithms. The limitations of ChatGPT, such as its social bias
and tendency to produce factually incorrect or irrelevant outputs, have been acknowledged by research-
ers (Cai, 2023; Kukulska-Hulme et al., 2023). Furthermore, Cai (2023) argues that ChatGPT lacks the
adaptability of an experienced human teacher who can tailor their approach to specific situations and
consider multifaceted factors and instincts, including dealing with handwritten tests that necessitate con-
version into a digital format. Employing ChatGPT in language learning may also raise concerns about
the potential replacement of human language teachers and the ethical implications surrounding the use
of a machine learning system for generating texts (Baskara & Mukarto, 2023).
Some researchers have explored the practical application of ChatGPT in language education. They
have studied its role as a tool for English language instruction (Kostka & Toncelli, 2023), its usability
in formal English language learning (Shaikh et al., 2023) and its potential to generate chatbot dialogues
for enhancing the process of learning English as a foreign language (EFL) (Young & Shishido, 2023).
Another central theme revolves around comparing EFL learners’ satisfaction when presented with
teacher-mediated writing opportunities versus ChatGPT-assisted ones (Ahmed, 2023). Additional stud-
ies have aimed to uncover students’ experiences with ChatGPT and their perspectives on its role in
language learning (Xiao & Zhi, 2023) and EFL learners’ perception and utilisation of ChatGPT beyond
the classroom (Liu & Ma, 2023). Researchers have also examined the impact of ChatGPT on students
participating in a second language writing practicum (Yan, 2023) and within the context of language
learning videos on YouTube (Li et al., 2023). Furthermore, research has delved into the perceptions of
faculty members (Mohamed, 2023), EFL lecturers (Alexander et al., 2023; Guo & Wang, 2023) and
researchers on ResearchGate (Bin-Hady et al., 2023). However, there has been a noticeable absence of
a comprehensive examination of these studies. This review examines these articles, addressing the fol-
lowing research questions (RQs):

3

The Integration of ChatGPT in Language Education

RQ1: What are the research contexts in which the identified studies were conducted?
RQ2: What are the benefits of using ChatGPT to enhance language learning?
RQ3: What are the challenges with using ChatGPT in language education?
RQ4: What are the implications of integrating ChatGPT in language education in diverse educational
settings?

METHODOLOGY

Building upon the research questions raised in the introduction section, this section details the methodol-
ogy, including the search terms and databases used, the selection criteria for literature and the process of
identifying relevant studies. Furthermore, this section elaborates on the data coding and analysis process
employed to derive meaningful conclusions from the selected studies.

Keywords and Inclusion Criteria

To identify relevant English-language empirical journal articles for this project, a keyword search was
conducted. Specific keywords, such as “ChatGPT language education”, “ChatGPT language learning”
and “ChatGPT language teaching” were chosen because of their direct relevance to language education.
Given its widespread usage, the English language was chosen to ensure broader accessibility of findings
within the global academic community. Additionally, this strategy was designed to circumvent potential
challenges linked to translating and comprehending non-English publications.
The selection process involved the use of the Scopus and Web of Science databases. Complementing
each other, these databases were utilised to identify a comprehensive range of articles on ChatGPT in
language education. In addition, a forward citation search was conducted to further enrich the article
selection process, given the relatively recent emergence of the use of ChatGPT in the field. In summary,
the following inclusion criteria were applied to screen the articles identified through the search:

• Journal articles
• Investigations of the integration of ChatGPT in language education
• Reports of empirical data
• Publications in English

Identification of Journal Articles

The specified search timeframe extended from the initial integration of ChatGPT as a tool for language
education to September 2023. The process of selecting relevant journal articles consisted of three stages.
In Stage 1 (S1), Scopus was used to identify high-quality peer-reviewed journal articles. In the first phase
of Stage 1, the keywords “ChatGPT language education”, “ChatGPT language learning” and “ChatGPT
language teaching” yielded 107, 132 and 37 journal articles, respectively. In the second phase, unrelated
articles were removed from the three lists. The elimination process entailed a comprehensive examination
of the topics and abstracts of each article to ascertain their alignment with ChatGPT’s specific focus on
language education, learning and teaching. The articles under consideration were empirical studies. Any
articles that did not directly pertain to these themes were subsequently excluded. As a result, this phase

4

The Integration of ChatGPT in Language Education

retained 6, 8 and 3 articles on the three lists, respectively. The third phase involved cross-checking for
any duplicates between the articles on the three lists. In the end, nine articles remained. Table 1 indicates
the three search phases and results during the process of identifying and selecting relevant articles.

Table 1. Journal article selection process in Stage 1 (S1) via Scopus

Number of Journal
Phases Activities Keywords Used
Articles Found
ChatGPT language education 107
Phase 1 (S1) Search ChatGPT language learning 132
ChatGPT language teaching 37
ChatGPT language education 6
Topic and abstract
Phase 2 (S1) ChatGPT language learning 8
evaluation
ChatGPT language teaching 3
Phase 3 (S1) Cross-checking N/A 9
Total 9
Note. N/A = not applicable

In Stage 2 (S2) of the process of identifying journal articles, the Web of Science database was used.
“Article” was set as the document type. The same set of keywords were employed as in Stage 1. This
selection process consisted again of three phases. In the first phase, the keywords produced 117, 113 and
26 journal articles, respectively. The second phase removed unrelated articles, resulting in the identifica-
tion of 4, 5 and 2 journal articles, respectively. The third phase of this stage involved cross-checking for
any duplicates between the three lists. In the end, five articles were retained. Table 2 outlines the journal
article selection process in Stage 2.

Table 2. Journal article selection process in Stage 2 (S2) via Web of Science

Number of Journal Articles

Phases Activities Keywords Used
Found
ChatGPT language education 117
Phase 1 (S2) Search ChatGPT language learning 113
ChatGPT language teaching 26
ChatGPT language education 4
Phase 2 (S2) Identification ChatGPT language learning 5
ChatGPT language teaching 2
Phase 3 (S2) Cross-checking N/A 5
Total 5
Note. N/A = not applicable

5

The Integration of ChatGPT in Language Education

As illustrated in Table 3, the first phase in Stage 3 of the process of identifying journal articles in-
volved a cross-check for duplicates between the journal articles generated during Stage 1 and Stage 2.
It was discovered that the 9 journal articles identified during Stage 1 included the 5 journal articles that
were identified during Stage 2. A forward citation search was carried out using both Scopus and Web
of Science to explore how the 9 journal articles were referenced in subsequent works. Three additional
journal articles that cited some of the initial 9 journal articles met the inclusion criteria. As a result, a
total of 12 journal articles progressed into the final investigatory phase. The details of these 12 selected
articles are summarised in Table 4 in the Appendix.

Table 3. Journal article selection process in Stage 3 (S3)

Number of Journal
Phases Activities Database
Articles Found
Phase 1 (S3) Cross-checking for duplicates Scopus and Web of Science 9
Phase 2 (S3) Forward citation search Scopus and Web of Science 3
Total 12

Data Coding and Analysis

The research data management and analysis for this study were primarily conducted using Microsoft Excel
2016 as the data storage and generation tool. To organise and structure the information in the articles,
the process commenced by coding the selected articles and then categorised the findings under relevant
themes. The themes served as a framework for interpreting the data and understanding the broader pat-
terns and insights present in the research. The categorisation process yielded four main themes: research
contexts, benefits, challenges and implications. Each of these main categories was further divided into
several sub-categories. These sub-categories provided a detailed insight into the collected data and the
iterative nature of this process allowed for a deeper and more nuanced understanding of the subject
matter. Through coding, categorisation and analysis, the aim was to identify patterns, relationships and
variations within the data.

RESULTS AND DISCUSSION

This section explores the research contexts of the identified studies, examines the benefits and challenges
of integrating ChatGPT into language education and discusses its implications.

Research Contexts

The research contexts encompassed various aspects, including research sites, participants, research meth-
ods and data collection tools. Each of these elements played a crucial role in building a comprehensive
understanding of the research environments and the processes involved in academic investigation.

6

The Integration of ChatGPT in Language Education

Research Sites

The selected studies, comprising a diverse range of research sites, reflected a global interest in this field.
In Europe, studies were carried out in Norway (Shaikh et al., 2023) and Cyprus (Alexander et al., 2023).
The project in the United States (Kostka & Toncelli, 2023) contributed to North American insights.
In the Middle East, studies in Saudi Arabia (Ahmed, 2023; Mohamed, 2023) explored the impact of
the tool. Studies in China (Guo & Wang, 2023; Xiao & Zhi, 2023; Yan, 2023) and Japan (Young &
Shishido, 2023) represented East Asian perspectives. Research on ResearchGate (Bin-Hady et al., 2023)
represented an international academic community and research context. Research on YouTube (Li et al.,
2023) underscored the utility of the platform in various language learning contexts. The study spanning
multiple countries (Liu & Ma, 2023), including China, the United States and other Anglophone countries
reflected the global applicability of ChatGPT in language learning.

Participants

The studies under investigation examined the use of ChatGPT in language education from various angles
and engaged with diverse groups of participants. Some studies focused on educators and researchers,
such as Alexander et al. (2023) who worked with a smaller group of six university English as a second
language (ESL) lecturers teaching C1 level English academic writing courses. Guo and Wang (2023)
engaged with five Chinese EFL teachers, with a focus on the importance of evaluating and implementing
ChatGPT. Mohamed (2023) involved 10 EFL faculty members researching educators’ perceptions. Bin-
Hady et al. (2023) interacted with 20 researchers on ResearchGate from various universities around the
world who had different linguistic backgrounds. They all were interested in technology-based language
learning and teaching.
Other studies examined the perspectives of language learners. Liu and Ma (2023) investigated the use
of ChatGPT in informal digital learning settings among 405 EFL learners. Meanwhile, Ahmed (2023)
included 64 first-Year university EFL students to investigate the interest in ChatGPT among language
learners. Kostka and Toncelli (2023) targeted international students in a pathways programme from
both an undergraduate public speaking course and a graduate academic listening and speaking course.
They shed light on the use of the tool in an academic context. Shaikh et al. (2023) engaged with 10 stu-
dents from various departments and offered diverse participant profiles. Xiao and Zhi (2023) included
five undergraduate students from an English-medium international university to provide insights into
the student experience. Yan (2023) investigated the behaviours and reflections of eight undergraduate
students majoring in EFL in response to their exposure to ChatGPT in writing classrooms. Young and
Shishido (2023) analysed 450 dialogue samples in their research to demonstrate ChatGPT’s potential
in generating language learning content. The final study in this context by Li et al. (2023) analysed 45
YouTube videos. It signified the influence of AI-driven content in language learning.

Research Methods

The research methods used in these studies demonstrated a blend of qualitative and quantitative ap-
proaches, reflecting the multidimensional nature of this field. On the qualitative front, Ahmed (2023)
employed a qualitative design focusing on EFL learners’ satisfaction with teacher-mediated versus
ChatGPT-assisted writing opportunities. Bin-Hady et al. (2023) employed a qualitative study based on

7

The Integration of ChatGPT in Language Education

grounded theory to explore the dimensions of ChatGPT in language learning. Using qualitative content
analysis, Mohamed (2023) delved into faculty members’ perceptions and suggested a focus on detailed
examination. Alexander et al. (2023) conducted a qualitative study to evaluate academic essays for
AI-generated content. They pointed out its exploratory nature. Similarly, Xiao and Zhi (2023) and Yan
(2023) adopted qualitative exploratory approaches to assess the impact of ChatGPT on learners in a
second language writing practicum.
Li et al. (2023) adopted the inductive content analysis method, while Kostka and Toncelli (2023)
included qualitative student quotations about the use of ChatGPT. Conversely, the studies by Guo and
Wang (2023), Shaikh et al. (2023) and Young and Shishido (2023) applied quantitative approaches. Their
studies reflected an interest in gathering numerical data to assess the potential of ChatGPT in support-
ing teacher feedback in EFL writing and generating dialogue materials for EFL learners, respectively.
Similarly, Liu and Ma (2023) utilised a quantitative cross-sectional survey design to examine users’ per-
ceptions and acceptance of ChatGPT in informal English language learning. The versatility in research
methods in this domain accommodated both the intricate exploration of participants’ experiences and
the quantitative measurement of the impact of ChatGPT in language education.

Data Collection Tools

The research data collection tools used in these journal articles reflected the diversity of approaches and
underscored the adaptability of methodologies to explore the multifaceted role of ChatGPT in language
education. Liu and Ma (2023) employed online surveys, in line with the digital nature of the use of Chat-
GPT. Mohamed (2023) conducted in-depth interviews with EFL faculty members. Although conducted
via email, the interviews allowed for extensive exploration of their perceptions. Xiao and Zhi (2023)
employed semi-structured interviews to investigate students’ experiences with ChatGPT and its role in
language learning. Ahmed (2023) relied on interviews to gather qualitative data when engaging directly
with university freshman EFL students, while Yan (2023) utilised observation and in-depth interviews
to assess the impact of ChatGPT in a second language writing practicum, with a focus on experiential
data. Similarly, Kostka and Toncelli (2023) utilised student quotations and incorporated them in their
study, emphasising participant engagement and perspectives in pathways programmes.
In contrast, Alexander et al. (2023) combined various methods such as essay sample preparation, AI
detectors and the analysis of texts by ESL lecturers to examine AI-generated content in academic essays.
Guo and Wang (2023) used a combination of ChatGPT, EFL teachers’ feedback on students’ writing and
questionnaires answered by EFL teachers to evaluate the potential of ChatGPT in supporting teacher
feedback. Shaikh et al. (2023) also adopted questionnaires to collect data, while data for Bin-Hady et al.
(2023) was collected through discussions. Li et al. (2023) uniquely collected primary data from videos
on YouTube and supplemented their findings with secondary data from the associated comments on
the videos. Young and Shishido (2023) adopted established readability assessment tools such as Flesch
Reading Ease, McAlpine EFLAW and Dale-Chall to evaluate the effectiveness of ChatGPT in generat-
ing dialogue materials for EFL students.

Impacts of the Integration of ChatGPT in Language Education

The selected journal articles reflected a keen interest in integrating ChatGPT into language education.
They underscored ChatGPT’s applications and potential in teaching and learning languages. The explora-

8

The Integration of ChatGPT in Language Education

tion of both learners’ and academics’ experiences with ChatGPT addressed its benefits and challenges,
highlighting its role in the ongoing evolution of language education.

Benefits of Using ChatGPT

Several major themes emerged regarding the benefits of using ChatGPT. The first theme highlighted
ChatGPT’s effectiveness in enhancing learning. The use of ChatGPT was also linked to learners’ attitudes
towards ChatGPT and their engagement levels. In addition, ChatGPT served a dual role as both a source
of valuable feedback and a personal tutor, assisting with various language-related tasks. Furthermore,
ChatGPT was recognised as a valuable tool in supporting teachers’ efforts in education.

Language Learning
The contributions of various authors underscored the substantial role of ChatGPT in facilitating lan-
guage learning across various dimensions. Shaikh et al. (2023) emphasised how ChatGPT expanded
vocabulary, improved grammatical and syntactical structures, and enhanced written and conversational
skills. Similarly, Bin-Hady et al. (2023) discovered that ChatGPT offered five subcategories of language
skill development, including enhancing EFL conversation practice, reading and writing skills, grammar
mastery, vocabulary and pronunciation. Yan (2023) underscored the significance of ChatGPT in assist-
ing L2 writing when students interacted with the system.
Also with a focus on writing, Xiao and Zhi (2023) reported on improved textual quality and language
competence with the assistance of ChatGPT. Moreover, they asserted that ChatGPT aided language
proficiency when students employed critical thinking skills to modify prompts, trained the model and
selectively accepted outputs. Young and Shishido (2023) suggested that the dialogues created by Chat-
GPT were well-suited for students at level A2 (elementary level) of the Common European Framework
of Reference (CEFR) for Languages and B1 (intermediate level) for learning new words. They provided
comprehensible content and stimulated vocabulary acquisition. Mohamed (2023) highlighted the advan-
tages of ChatGPT in EFL learning, such as real-time feedback, personalised instruction, a vast knowledge
base, natural language processing, human-like responses and cost-effectiveness.

Student Attitude
The integration of ChatGPT in language learning and its impact on student attitude was a key focus in the
examined studies. Two studies highlighted the significance of student attitude in influencing the adop-
tion and acceptance of ChatGPT for language learning. Liu and Ma (2023) found that learners with a
positive view of ChatGPT’s usefulness were more likely to intend to use it, a tendency that was strongly
linked to their actual English learning outside the classroom. In addition, their research indicated that
even EFL learners who initially found ChatGPT challenging could gradually develop a positive attitude
and interest in the technology as they recognised its benefits.
In a similar vein, Xiao and Zhi (2023) reported that students in their study displayed a positive at-
titude towards using ChatGPT, overwhelmingly supporting its adoption in universities instead of its
prohibition. Students’ acknowledgement of ChatGPT’s significant benefits seemed to mitigate concerns
about its potential drawbacks, reflecting a favourable view of its integration. Shaikh et al. (2023) further
emphasised the effortless and friendly interface of the tool, which greatly enhanced user experience. The

9

The Integration of ChatGPT in Language Education

high satisfaction ratings and positive student feedback regarding the acceptance of ChatGPT underscored
its promising and practical value for language learners.

Engagement
The findings of multiple authors demonstrated the positive impact of ChatGPT on student academic
engagement. Kostka and Toncelli (2023) observed an increase in student engagement with both course
materials and their interactions with peers after integrating ChatGPT into classes. This heightened
engagement led to a more enthusiastic approach to learning content and a deeper interest in critically
analysing the output generated by ChatGPT. Similarly, Liu and Ma (2023) found a general consensus
among participants regarding the usefulness of ChatGPT in various English learning activities. Particularly
noteworthy was ChatGPT’s role as a creative tool that effectively enhanced engagement in independent
learning activities outside the classroom.
The positive engagement fostered by ChatGPT effectively impacted learning, enhancing student
autonomy, boosting independent learning and encouraging critical evaluation of AI-generated informa-
tion. Xiao and Zhi (2023) highlighted that an engaging learning process not only enhanced language
skills but also promoted student autonomy. Learners actively engaged in self-revision, based on the
suggestions provided by the system. In this sense, their findings echoed those of Liu and Ma (2023),
who also noted the promotion of more active and independent language learning experiences through
independent learning activities. Also according to Xiao and Zhi (2023), the involvement of students in
modifying prompts, training the system and critically evaluating the output showed a remarkable capac-
ity for critical thinking. Students developed a critical stance towards the role of ChatGPT in English
language learning, consistently critiquing its limitations in various learning aspects. They emphasised
the importance of evaluating the usability of the information generated.

Feedback
Recognised as a tool for scaffolding learning, ChatGPT emphasised its capabilities in offering students
feedback, as highlighted by Bin-Hady et al. (2023). In line with this, Shaikh et al. (2023) argued that
ChatGPT acted as a support tool for practising a foreign language. Furthermore, ChatGPT served as a
personalised learning partner or personal tutor, delivering easily accessible and adaptive feedback (Xiao
& Zhi, 2023). It had the capacity to review writing and speaking assignments, offer corrections for
grammar, vocabulary and pronunciation errors and suggest improvements, including alternative word
choices, sentence structures and pronunciation techniques (Ahmed, 2023).
However, some distinctions between ChatGPT and teacher feedback in their approach to evaluating
student writing were noted. ChatGPT typically provided feedback more quickly and in larger quantities,
whereas teachers needed more time to evaluate student essays and provide feedback. In addition, the
nature of the feedback differed. ChatGPT offered more directive feedback, whereas teachers typically
employed informative and query-based feedback, especially when assessing content and language as-
pects of student essays. Moreover, ChatGPT tended to provide more praise when evaluating the content
of student essays and offered more summaries regarding the organisational aspect. This demonstrated
unique characteristics compared to traditional teacher feedback (Guo & Wang, 2023).

10

The Integration of ChatGPT in Language Education

Personal Tutor
ChatGPT effectively fulfilled the role of a personal tutor. This innovative tool provided learners with a
dynamic platform for engaging in various linguistic exercises, including asking questions, discussing di-
verse topics, and simulating real-life dialogues. Such interactive features proved instrumental in enhancing
motivation among learners, particularly in the context of foreign language learning, as noted by Shaikh
et al. (2023). Further emphasising ChatGPT’s role as a personal tutor, Xiao and Zhi (2023) conducted
research demonstrating how participants extensively used ChatGPT for various educational tasks. One
significant use case was text revision, in which learners sought ChatGPT’s assistance for structural and
content suggestions in their essays. In addition, ChatGPT proved helpful in providing examples and
ideas to strengthen the arguments in written work. This capability became especially beneficial in larger
classroom settings, where the number of students might limit individual attention from teachers. As noted
by Xiao and Zhi (2023), the assistance offered by ChatGPT extended beyond mere language practice; it
encompassed a more comprehensive approach to language skill development. By offering personalised
feedback and suggestions, ChatGPT enhanced learners’ understanding of language nuances and improved
their ability to construct coherent and sophisticated texts. This personalisation was particularly crucial
in language learning, where the needs and learning paces of students could vary significantly.

Teachers’ Aid
The question of whether ChatGPT could entirely replace human language teachers led to a consensus that
it cannot fully serve as a substitute. This consensus primarily arose from the understanding that certain
aspects of human interaction, such as humour, wit and empathy, could not be replicated or programmed
into AI technology (Li et al., 2023). However, ChatGPT exhibited characteristics of a knowledgeable
native speaker and proved useful in extended conversations, avoiding language fatigue (Li et al., 2023).
It demonstrated the ability to understand essay content, offer relevant revision suggestions, use praise
for student achievements and employ flexible language in feedback (Guo & Wang, 2023). Academics
viewed ChatGPT as a collaborator and a valuable source of learning, leading them to use it for generat-
ing feedback on student writing. As a result, there was a prevailing view that a combination of AI and
human interaction represented a promising approach for enhancing language learning experiences (Li
et al., 2023).
ChatGPT demonstrated the capacity to effectively assist educators in automating mechanical tasks,
such as assigning grades and evaluating assignments based on criteria like grammar accuracy, vocabulary
usage and syntax correctness, thereby saving time and effort (Ahmed, 2023). Furthermore, ChatGPT
played an integrative role alongside teachers in contributing to language learning (Bin-Hady et al., 2023).
Research highlighted the potential of ChatGPT to enhance the efficiency of EFL teachers by comple-
menting traditional teaching methods, thereby improving student language proficiency and success
(Mohamed, 2023). In addition, Xiao and Zhi (2023) emphasised the importance of teachers embracing
this AI tool and providing appropriate guidance to students. They underlined the need for educators to
adapt and effectively integrate ChatGPT in the teaching process.

Challenges Related to the Use of ChatGPT

Despite the multifaceted benefits of ChatGPT in language education, several challenges were presented.
These included inaccessibility, inaccuracy of information, inappropriate feedback and responses, and

11

The Integration of ChatGPT in Language Education

inappropriate language levels produced by ChatGPT. Learners’ ethical and privacy concerns and the
potential replacement of humans also posed significant challenges.
In their study, Guo and Wang (2023) emphasised the negative impact of inaccessibility, highlighting
how it prevented teachers in certain countries or regions from using ChatGPT as an educational tool.
This gap in accessibility limited the widespread availability of this powerful resource to educators and
deprived students of its potential benefits. Furthermore, Mohamed (2023) pointed out that AI-powered
language learning tools might not suit those without access to necessary technology. Despite its advanced
capabilities, ChatGPT was still susceptible to errors or deviations from correct language use. In their
research, Li et al. (2023) observed that these inaccuracies posed challenges in crafting accurate and ef-
fective prompts. Similarly, Mohamed (2023) expressed concerns about ChatGPT’s precision, particularly
with idiomatic expressions, cultural references and other nuanced aspects of human language.
The tendency of ChatGPT to produce inappropriate feedback was a concern for educators. For instance,
Guo and Wang (2023) observed that ChatGPT occasionally deviated from the expected feedback focus,
providing off-task feedback. In contrast, EFL teachers in the same study consistently provided on-task
feedback, highlighting a significant discrepancy between ChatGPT and human instructors. Furthermore,
teachers expressed concerns about aligning ChatGPT’s evaluation criteria with their own. The lack of
in-depth knowledge about the class and individual students further compounded this issue. Echoing this
concern, Mohamed (2023) emphasised the limitations of ChatGPT, including generating inappropriate
responses and facing challenges in adequately addressing critical language components.
The suitability of the materials generated by ChatGPT for language learners at all levels was a
complex issue. Li et al. (2023) pointed to a contradiction in this regard. They implied that ChatGPT
may not cater to the diverse proficiency levels of language learners. As Young and Shishido (2023)
suggested, the dialogues produced were well-suited for students with CEFR A2 proficiency, enabling
them to comprehend most of the words used. However, creating content for students at higher CEFR
levels had its limitations. While dialogues intended for CEFR B1 students benefited those at the A2
level by exposing them to new vocabulary, the need for more advanced content, tailored specifically for
higher-level learners, remained. Consequently, ChatGPT’s potential to provide valuable resources and
its alignment with the varied needs and abilities of learners across different proficiency levels may not
be consistently effective.
The adoption of ChatGPT raised several ethical and privacy concerns. Mohamed (2023) emphasised
the urgency to address these issues. The primary ethical concerns centred around the risk of perpetu-
ating language biases and stereotypes. In addition, there were substantial privacy and data protection
concerns, especially in safeguarding student data during interactions with the technology. The research
also highlighted apprehensions about ChatGPT potentially replacing human roles. According to Kostka
and Toncelli (2023), some students recognised the need for human intervention when using ChatGPT,
acknowledging that, while beneficial, technology cannot fully replace human guidance and expertise.
Yan (2023) further revealed the concerns about the unrestricted use of ChatGPT in L2 writing. Partici-
pants in the study demonstrated more concern than satisfaction when it came to the fully automated
workflow of ChatGPT. Undergraduate EFL learners, particularly those with limited exposure to the latest
technologies, were uneasy about the potential displacement of human educators in L2 writing pedagogy.

12

The Integration of ChatGPT in Language Education

Bridging Findings and Literature

The findings have effectively demonstrated the connection between empirical evidence on ChatGPT’s
role in language education and existing academic discourse. This connection is particularly evident in
the authentic learning contexts enabled by integrating ChatGPT, a conclusion supported by literature
from Baskara and Mukarto (2023), Cai (2023), Hong (2023) and Kohnke et al. (2023). This integration
is evident in the learning content created by ChatGPT and its dual roles as both a feedback provider and
a personal tutor. A profound impact of ChatGPT on language learning is its ability to enhance various
aspects of the learning process, such as improving conversational skills, reading, writing, grammar and
pronunciation. Designed for diverse groups of participants, ChatGPT offers personalised instruction,
thereby enriching the learning experience, although its effectiveness may currently vary across different
proficiency levels. Its capability to provide language learning content tailored to different learners and
skills mirrors real-world scenarios. This particular aspect is emphasised in the research by Baskara and
Mukarto (2023) and Cai (2023). Moreover, in line with the findings of Baskara and Mukarto (2023),
Cai (2023) and Hong (2023), ChatGPT’s provision of personalised and adaptive feedback is highlighted
as a unique characteristic that sets it apart from traditional teacher feedback in language education.
As a personal tutor, ChatGPT facilitates language learning by engaging in questions, discussions and
simulated dialogues that resemble human-like responses. This approach aligns with the assertions of
Kohnke et al. (2023), Baskara and Mukarto (2023) and Hong (2023), who praise ChatGPT’s interactive
and personalised teaching capabilities, as well as those of Cai (2023), who emphasises its adaptability
to each learner’s unique requirements.
Another significant aspect of the findings is ChatGPT’s role in empowering students to actively
engage in their learning process. Several impactful areas have been identified. The findings indicate
that ChatGPT, serving as a personal tutor, plays a crucial role in enhancing learner motivation, making
learning materials more appealing and interactive. Its personalised interactions with learners ensure
that they remain engaged and motivated, as emphasised by Cai (2023). ChatGPT’s ability to function
as a personalised tool also allows learners to engage with the AI’s output and explore topics more inde-
pendently. Students with favourable perceptions of ChatGPT’s effectiveness are more inclined to use it,
leading to a significant increase in their independent learning outside the classroom environment. This
level of engagement is crucial for developing self-directed learners who can navigate and assimilate
information without direct supervision from teachers. This resonates with the literature’s focus on learner-
driven control and engagement (Cai, 2023). These findings not only validate the existing literature but
also add depth by detailing specific instances of increased student enthusiasm and active participation
in learning activities.
The integration of ChatGPT in language education requires careful consideration of educators’ input,
a factor that is prominently emphasised in the findings. On one hand, the findings indicate that, while
ChatGPT cannot replace human language teachers, its role as a knowledgeable assistant is significantly
valuable. Academics regard ChatGPT as a collaborator that, when combined with educators’ involve-
ment, enhances the teaching and learning process. Serving as an effective support tool, it aids in extended
conversations and tasks such as grading and assignment evaluation. This synergy points to a promising
future for AI-augmented language education. The roles of ChatGPT, in line with its characterisation
as teachers’ aid (Cai, 2023; Hong, 2023), contribute to reducing their workloads. On the other hand,
there are notable concerns, such as the potential of ChatGPT replacing human roles in teaching. These
apprehensions, as echoed by Baskara and Mukarto (2023), reflect broader scepticism about the role of

13

The Integration of ChatGPT in Language Education

AI in education. Therefore, it is crucial to strike a balance between technological advancements and the
essential role of human oversight and interaction within the educational process.
Echoing the study of Kohnke et al. (2023), the findings emphasise the challenge of ensuring accurate
responses and alignment with educational standards. They also highlight the challenges educators face,
such as ChatGPT’s occasional delivery of inappropriate feedback and its difficulty in understanding
students’ specific needs. These issues correspond to identified limitations of ChatGPT, such as its ten-
dency to produce factually incorrect or irrelevant outputs, as noted by Cai (2023) and Kukulska-Hulme
et al. (2023). Furthermore, the integration raises ethical considerations, particularly concerning adapt-
ability and data privacy. This reflects concerns about cultural and social biases in the source database
and algorithms, as discussed by Cai (2023), Kohnke et al. (2023) and Kukulska-Hulme et al. (2023).
Notable differences between the two sources include the emphasis in the literature on ChatGPT’s
role in creating a comfortable and safe learning environment. This aspect, highlighted by Cai (2023),
enhances learner confidence and encourages participation, yet it is not specifically addressed in the
findings of this research. While this study aligns with the existing body of knowledge, it also expands
upon it. It offers new insights, such as the challenges in accessing AI tools like ChatGPT in less ad-
vantaged regions and the generally positive attitude of students towards ChatGPT in facilitating the
learning process. Students appreciate ChatGPT’s ease of use and effectiveness in language learning,
leading to increased acceptance and high satisfaction scores. They also favour integrating ChatGPT into
educational settings, recognising its significant benefits. In addition, the findings reveal that students
generally view ChatGPT positively in the context of language learning, appreciating its practicality and
accessibility, and recognising its potential to facilitate more effective and engaging learning processes.
Moreover, the findings suggest that ChatGPT encourages critical thinking in students, prompting them
to modify prompts, train the system, and selectively accept information. This helps students to evaluate
the usability of generated information and develop a critical stance towards the role of AI in language
learning, an aspect not exclusively highlighted in the existing literature.

IMPLICATIONS

The significant outcomes of this project also lie in the implications that it carries. These implications
are not just about technological advancements but also include pedagogical and ethical considerations
that can shape a more effective and responsible approach to language teaching and learning.

Technological Implications

As the landscape of language education progresses, the necessity for AI technologies like ChatGPT to
undergo regular updates and monitoring becomes increasingly apparent. More than just enhancing the
learning experience, these efforts are crucial for aligning educational journeys with the rapid pace of
technological advancements. A key aspect of this evolution involves integrating AI tools like ChatGPT
into educational platforms. This necessitates a design that is not only compatible with existing digital
tools and learning management systems but also user-friendly and intuitive. This ensures their relevance
and effectiveness in an evolving educational environment. Central to this process is the continuous pro-
fessional development and support extended to educators. It is essential that educators are trained not
only in the technical aspects of AI tools but also in effectively integrating these tools into their teaching

14

The Integration of ChatGPT in Language Education

practices. An example of this is the revision of assessment policies and the development of suitable
rubrics and criteria, as suggested by Alexander et al. (2023).
Moreover, educators should explore strategies that facilitate the integration of AI tools into language
education, adopting effective pedagogical frameworks. In this context, Xiao and Zhi (2023) highlight the
benefits of integrating tools like ChatGPT in language classrooms. They propose strategies that enable
students to use these tools legitimately and productively. Complementing this, Tseng and Warschauer
(2023) present a comprehensive five-part pedagogical framework (understand, access, prompt, corrobo-
rate and incorporate), specifically designed to support second language learners. Such frameworks are
instrumental in helping both educators and students to understand how to effectively collaborate with AI
technologies. This prepares them for a future increasingly intertwined with technological advancements,
both within the educational sphere and beyond.

Pedagogical Implications

As AI technologies continue to advance, their impact on language education is set to grow, transforming
the ways in which languages are taught and learnt. Among the pedagogical implications, a significant
aspect is the role of ChatGPT as teachers’ aid. This involves the substantial role of AI in augmenting
educators’ capabilities, as demonstrated by this project. By handling routine tasks, AI technologies en-
able educators to focus on more personalised, adaptive and authentic aspects of teaching. This includes
monitoring AI’s interactions with students and the feedback it provides. Ensuring that AI serves as a
reliable and effective tool is essential for students engaging with it in language learning, and it also en-
riches the overall teaching experience. Educators are thus encouraged to deliberately integrate AI-driven
tools into their teaching practices.
Moreover, AI technologies like ChatGPT act as personalised tutors, offering valuable feedback to
students. This capability plays a crucial role in student learning, particularly in fostering independent
learning opportunities outside of the classroom where teachers are not present. This underscores the
need to adapt language education methods to integrate such pedagogical advancements. On another
level, this development calls for educators to re-evaluate the significance of students’ contributions to
their learning processes. Leveraging the supportive role of AI technologies, educators should encour-
age students to engage in collaborative and reflective interactions with AI. This approach may involve
incorporating students’ input into the learning process. In addition, educational institutions should initi-
ate open dialogues with students, educating them about the responsible use of AI tools and informing
them about their limitations, biases, inaccuracies, and the ethical considerations involved. As Mills et al.
(2023) suggest, engaging students in such a collaborative manner fosters emergent, student-centred and
student-guided methods of exploring AI, contributing to broader societal discussions about its future role.

Ethical Implications

One crucial ethical implication is addressing bias in AI algorithms. Therefore, educators are responsible
for preventing the reinforcement of prejudices through these AI models. This ensures that the language
and content generated by AI tools, particularly for teaching purposes, are as unbiased as possible, reflect-
ing the utmost efforts of educators. Equally important is safeguarding students’ privacy. Considering
the need for ethical use of student data, it is imperative that educators establish and strictly adhere to

15

The Integration of ChatGPT in Language Education

rigorous protocols and policies. This step is crucial in ensuring the protection of student privacy and in
guaranteeing responsible and ethical handling of their data.
In addition, educators must ensure the appropriate and judicious use of AI to avoid the risk of be-
coming overly reliant on it for educational purposes and potentially diminishing the value of human
input and interaction in the learning process. Therefore, it is essential for educators to strike a balance
between leveraging AI for its advantages and preserving the irreplaceable human elements of teaching
languages. Moreover, AI has the potential to bridge accessibility gaps in language education. Educators
need to ensure that all students, particularly those in resource-limited areas, have equitable access to the
necessary technology for using AI tools. Implementing such practices not only enriches learning envi-
ronments but also helps to create a more diverse and technologically inclusive educational landscape.

CONCLUSION

This chapter has comprehensively reviewed research from various geographies and online platforms,
uncovering a significant global interest in integrating ChatGPT in language education. The inclusion of
diverse participant groups, such as educators, researchers, and learners, has offered deep insights into
the complex implications of ChatGPT in this field. The use of both qualitative and quantitative research
methods has highlighted the multifaceted nature of this dynamic educational technology. In addition,
the chapter has emphasised the considerable benefits, challenges and broader implications of ChatGPT
within the educational context.
However, this chapter is not without its limitations. The relatively small sample size of 12 selected
articles may limit the generalisability of the findings. In addition, the inclusion criteria, which required
articles to be in English, could have introduced language bias and possibly excluded valuable non-
English language research. Moreover, relying primarily on the Scopus and Web of Science databases for
article identification might have overlooked relevant articles from other databases, potentially leading
to selection bias. Although forward citation search was conducted to identify additional articles, the
chosen timeframe for article inclusion, ending in September 2023, may have excluded newer research
pertinent to the topic.
Despite these limitations, the chapter provides valuable insights into AI-driven projects in various
educational settings, as exemplified by ChatGPT. It highlights the technology’s impact from the perspec-
tives of both students and educators. The chapter’s significance lies in its thorough exploration of AI’s
role in language education, demonstrating its potential to shape the future of this field. This analysis
equips educators, researchers and policymakers with insights to guide their strategies for effectively
integrating AI in language education. It advocates for leveraging the benefits of AI tools like ChatGPT
while thoughtfully addressing the challenges and ethical considerations inherent in their use. As lan-
guage education continues to evolve, understanding and adapting to AI technologies will be crucial in
enhancing learning experiences and outcomes.

REFERENCES

Ahmed, M. A. (2023). ChatGPT and the EFL classroom: Supplement or substitute in Saudi Arabia’s
eastern region. Information Sciences Letters, 12(7), 2727–2734. doi:10.18576/isl/120704

16

The Integration of ChatGPT in Language Education

Alexander, K., Savvidou, C., & Alexander, C. (2023). Who wrote this essay? Detecting AI-generated
writing in second language education in higher education. Teaching English with Technology, 23(2),
25–43. doi:10.56297/BUKA4060/XHLD5365
Auer, M. E., Pester, A., & May, D. (Eds.). (2022). Learning with Technologies and Technologies in
Learning: Experience, Trends and Challenges in Higher Education (Vol. 456). Springer International
Publishing. https://link.springer.com/10.1007/978-3-031-04286-7
Bai̇doo-Anu, D., & Ansah, L. O. (2023). Education in the era of generative artificial intelligence (AI):
Understanding the potential benefits of ChatGPT in promoting teaching and learning. Journal of AI,
7(1), 52–62. doi:10.61969/jai.1337500
Baskara, R., & Mukarto. (2023). Exploring the implications of ChatGPT for language learning in higher
education. Indonesian Journal of English Language Teaching and Applied Linguistics, 7(2), 343–358.
https://eric.ed.gov/?id=EJ1391490
Bin-Hady, W. R. A., Al-Kadi, A., Hazaea, A., & Ali, J. K. M. (2023). Exploring the dimensions of Chat-
GPT in English language learning: A global perspective. Library Hi Tech. Advance online publication.
doi:10.1108/LHT-05-2023-0200
Cai, W. (2023, February 24). ChatGPT can be powerful tool for language learning: The innovation offers
multiple opportunities for language teaching and learning. University Affairs. https://www.universityaf-
fairs.ca/career-advice/career-advice-article/chatgpt-can-be-powerful-tool-for-language-learning/
Crompton, H., & Burke, D. (2023). Artificial intelligence in higher education: The state of the field.
International Journal of Educational Technology in Higher Education, 20(1), 22. doi:10.1186/s41239-
023-00392-8
Golonka, E. M., Bowles, A. R., Frank, V. M., Richardson, D. L., & Freynik, S. (2014). Technologies
for foreign language learning: A review of technology types and their effectiveness. Computer Assisted
Language Learning, 27(1), 70–105. doi:10.1080/09588221.2012.700315
Guo, K., & Wang, D. (2023). To resist it or to embrace it? Examining ChatGPT’s potential to support
teacher feedback in EFL writing. Education and Information Technologies. Advance online publication.
doi:10.1007/s10639-023-12146-0
Hong, W. C. H. (2023). The impact of ChatGPT on foreign language teaching and learning: Opportunities
in education and research. Journal of Educational Technology and Innovation, 5(1). https://jeti.thewsu.
org/index.php/cieti/article/view/103
Huang, X., Zou, D., Cheng, G., Chen, X., & Xie, H. (2023). Trends, research issues and applications
of artificial intelligence in language education. Journal of Educational Technology & Society, 26(1),
112–131. https://www.jstor.org/stable/48707971
Kasneci, E., Sessler, K., Küchemann, S., Bannert, M., Dementieva, D., Fischer, F., Gasser, U., Groh, G.,
Günnemann, S., Hüllermeier, E., Krusche, S., Kutyniok, G., Michaeli, T., Nerdel, C., Pfeffer, J., Poquet,
O., Sailer, M., Schmidt, A., Seidel, T., ... Kasneci, G. (2023). ChatGPT for good? On opportunities and
challenges of large language models for education. Learning and Individual Differences, 103, 102274.
doi:10.1016/j.lindif.2023.102274

17

The Integration of ChatGPT in Language Education

Kohnke, L., Moorhouse, B. L., & Zou, D. (2023). ChatGPT for language teaching and learning. RELC
Journal, 54(2), 537–550. doi:10.1177/00336882231162868
Kostka, I., & Toncelli, R. (2023). Exploring applications of ChatGPT to English language teach-
ing: Opportunities, challenges, and recommendations. TESL-EJ, 27(3). Advance online publication.
doi:10.55593/ej.27107int
Kukulska-Hulme, A., Bossu, C., Charitonos, K., Coughlan, T., Deacon, A., Deane, N., Ferguson, R.,
Herodotou, C., Huang, C.-W., Mayisela, T., Rets, I., Sargent, J., Scanlon, E., Small, J., Walji, S., Weller,
M., & Whitelock, D. (2023). Innovating Pedagogy 2023: Open University Innovation Report 11. The
Open University.
Li, B., Bonk, C. J., & Kou, X. (2023). Exploring the multilingual applications of ChatGPT: Uncovering
language learning affordances in YouTuber videos. International Journal of Computer-Assisted Lan-
guage Learning and Teaching, 13(1), 1–22. Advance online publication. doi:10.4018/IJCALLT.326135
Liu, G., & Ma, C. (2023). Measuring EFL learners’ use of ChatGPT in informal digital learning of
English based on the technology acceptance model. Innovation in Language Learning and Teaching,
0(0), 1–14. doi:10.1080/17501229.2023.2240316
Mills, A., Bali, M., & Eaton, L. (2023). How do we respond to generative AI in education? Open educa-
tional practices give us a framework for an ongoing process. Journal of Applied Learning and Teaching,
6(1), 16–30. doi:10.37074/jalt.2023.6.1.34
Moeller, A., & Catalano, T. (2015). Foreign language teaching and learning. In J. D. Wright (Ed.), In-
ternational Encyclopedia of the Social & Behavioral Sciences (2nd ed., Vol. 9, pp. 327–332). Elsevier.
doi:10.1016/B978-0-08-097086-8.92082-8
Mohamed, A. M. (2023). Exploring the potential of an AI-based Chatbot (ChatGPT) in enhancing English
as a foreign language (EFL) teaching: Perceptions of EFL faculty members. Education and Information
Technologies. Advance online publication. doi:10.1007/s10639-023-11917-z
Rebolledo Font De La Vall, R., & González Araya, F. (2023). Exploring the benefits and challenges of
AI-language learning tools. International Journal of Social Sciences and Humanities Invention, 10(01),
7569–7576. doi:10.18535/ijsshi/v10i01.02
Roumeliotis, K. I., & Tselikas, N. D. (2023). ChatGPT and open-AI models: A preliminary review.
Future Internet, 15(6), 192. doi:10.3390/fi15060192
Shadiev, R., & Yang, M. (2020). Review of studies on technology-enhanced language learning and
teaching. Sustainability (Basel), 12(2), 524. doi:10.3390/su12020524
Shaikh, S., Yayilgan, S. Y., Klimova, B., & Pikhart, M. (2023). Assessing the usability of ChatGPT for
formal English language learning. European Journal of Investigation in Health, Psychology and Educa-
tion, 13(9), 1937–1960. doi:10.3390/ejihpe13090140 PMID:37754479
Tseng, W., & Warschauer, M. (2023). AI-writing tools in education: If you can’t beat them, join them.
Journal of China Computer-Assisted Language Learning, 3(2), 258–262. Advance online publication.
doi:10.1515/jccall-2023-0008

18

The Integration of ChatGPT in Language Education

Xiao, Y., & Zhi, Y. (2023). An exploratory study of EFL learners’ use of ChatGPT for language learning
tasks: Experience and perceptions. Languages (Basel, Switzerland), 8(3), 212. Advance online publica-
tion. doi:10.3390/languages8030212
Yan, D. (2023). Impact of ChatGPT on learners in a L2 writing practicum: An exploratory investiga-
tion. Education and Information Technologies, 28(11), 13943–13967. Advance online publication.
doi:10.1007/s10639-023-11742-4
Young, J. C., & Shishido, M. (2023). Investigating OpenAI’s ChatGPT potentials in generating chatbot’s
dialogue for English as a foreign language learning. International Journal of Advanced Computer Sci-
ence and Applications, 14(6), 65–72. doi:10.14569/IJACSA.2023.0140607
Ziegler, N., & González-Lloret, M. (2022). The Routledge Handbook of Second Language Acquisition
and Technology (1st ed.). Routledge. doi:10.4324/9781351117586

KEY TERMS AND DEFINITIONS

AI: Or Artificial Intelligence, is a system that simulates human intelligence and can perform tasks
traditionally carried out by humans.
AI Technologies: Refer to systems that utilise principles and techniques of AI to carry out various
tasks.
ChatGPT: Is a prominent AI language model developed by OpenAI. The remarkable ability of
ChatGPT to handle complex tasks has received significant attention in the field of language education.
Language Education: Aims to foster effective communication and meaningful interaction in differ-
ent linguistic and cultural contexts. It provides learners with skills to overcome linguistic barriers and
collaborate across diverse geographical boundaries.
Language Learning: Is a process through which learners immerse themselves in a new language,
developing proficiency in its linguistic components, language learning skills and cultural awareness.
This comprehensive development contributes to their ability to effectively use the language for com-
munication and understanding in real-world contexts.
Language Teaching: Is a process through which teachers aim to enhance learners’ linguistic profi-
ciency, develop their language learning skills, foster their cultural awareness and enable learners to use
the language effectively for communication and understanding in real-world contexts.
Learner Attitude: Refers to the emotions, thoughts and actions of learners towards their learning
process.
Learner Engagement: Is characterised by the extent of involvement and enthusiasm displayed by
learners as they participate in their learning process, impacting their learning outcomes.

19
20
Table 4. Summary of the selected journal articles

Publication Number of Research Data Collection

Authors Title of Publication Participants Research Site
APPENDIX
Year Participants Design Tools
ChatGPT and the EFL
classroom: Supplement or First-year university Qualitative
1 Ahmed 2023 64 Saudi Arabia Interviews
substitute in Saudi Arabia’s EFL students design
eastern region
Essay sample
Who wrote this essay?
ESL lecturers preparation;
Alexander Detecting AI-generated writing Exploratory
2 2023 6 (C1 level English Cyprus AI detector analysis
et al. in second language education qualitative study
academic writing) of essays; ESL
in higher education
lecturer text analysis
ResearchGate
Exploring the dimensions of researchers in Grounded
Bin-Hady Discussion data
3 2023 ChatGPT in English language 20 technology-based ResearchGate theory-based
et al. collection
learning: A global perspective language learning qualitative study
and teaching
ChatGPT feedback;
To resist it or to embrace
EFL teacher
Guo and it? Examining ChatGPT’s Chinese EFL Exploratory
4 2023 5 China feedback;
Wang potential to support teacher teachers study
EFL teacher
feedback in EFL writing
questionnaires
Exploring applications
International
of ChatGPT to English Qualitative
Kostka and students in
5 2023 language teaching: n/a USA student Student quotations
Toncelli a pathways
Opportunities, challenges, and quotations
programme
recommendations
Exploring the multilingual
YouTube videos
applications of ChatGPT:
YouTube video Inductive (primary data) and
6 Li et al. 2023 Uncovering language learning 45 YouTube
content content analysis comments (secondary
affordances in YouTuber
data)
videos
Measuring EFL learners’ use China, the
of ChatGPT in informal digital United Quantitative
7 Liu and Ma 2023 learning of English based on 405 EFL learners States, Other cross-sectional Online survey
the technology acceptance Anglophone survey
model countries

continues on following page

The Integration of ChatGPT in Language Education
Table 4. Continued

Publication Number of Research Data Collection

Authors Title of Publication Participants Research Site
Year Participants Design Tools
Exploring the potential of an
AI-based Chatbot (ChatGPT)
in enhancing English as EFL faculty Qualitative
8 Mohamed 2023 10 Saudi Arabia Email interviews
a foreign language (EFL) members content analysis
teaching: Perceptions of EFL
faculty members
Assessing the usability of Students from Quantitative
9 Shaikh et al. 2023 ChatGPT for formal English 10 various departments Norway exploratory Questionnaires
language learning of a university study
The Integration of ChatGPT in Language Education

Undergraduate
An exploratory study of EFL
students Qualitative
learners’ use of ChatGPT Semi-structured
10 Xiao and Zhi 2023 5 (English-medium China exploratory
for language learning tasks: interviews
international study
Experience and perceptions
university)
Impact of ChatGPT on learners Qualitative
Undergraduate EFL Observations;
11 Yan 2023 in a L2 writing practicum: An 8 China exploratory
majors In-depth interviews
exploratory investigation approach
Investigating OpenAI’s
Flesch reading ease
ChatGPT potentials in
Young and ChatGPT-generated Quantitative analysis; McAlpine
12 2023 generating Chatbot’s dialogue 450 Japan
Shishido dialogues study EFLAW analysis;
for English as a foreign
Dale-Chall analysis
language learning

21
22

Chapter 2
Enhancing Language
Teaching Materials Through
Artificial Intelligence:
Opportunities and Challenges

Surjit Singha
https://orcid.org/0000-0002-5730-8677
Kristu Jayanti College (Autonomous), India

Ranjit Singha
https://orcid.org/0000-0002-3541-8752
Christ University, India

Elizabeth Jasmine
Indian Institute of Psychology and Research, India

ABSTRACT
Incorporating artificial intelligence (AI) into language education signifies a paradigm shift that promotes
originality and inclusiveness. The partnership between AI developers and educators effectively tackles
obstacles and establishes a foundation for continuous progress. Anticipating the future, the progression
of AI holds the potential to deliver intricate customization, customizing educational encounters to suit
the unique requirements of each individual. Responsible incorporation of AI into teaching methodologies
transforms them into a collaborative model that empowers educators to engage in individualized interac-
tions. Ethics remain of the utmost importance, encompassing bias mitigation and privacy. In essence,
the integration of AI into language education signifies an impending era in which the combined powers
of technology and human proficiency foster the development of capable individuals who are prepared
to navigate an interconnected, digitally globalized society.

DOI: 10.4018/979-8-3693-0872-1.ch002

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

Enhancing Language Teaching Materials Through Artificial Intelligence

INTRODUCTION

AI revolutionizes language education, offering interactive content, chatbots, and intelligent tutors for
personalized and adaptive learning experiences, transforming traditional approaches. (Li & Yu, 2021).
Implementing artificial intelligence (AI) in language learning platforms has profoundly impacted user
experiences and learning outcomes, representing a paradigm shift in education. Prominent media, in-
cluding Duolingo, Rosetta Stone, Babbel, Lingodeer, ChatGPT Language Tutor, and Memrise, have
effectively utilized artificial intelligence (AI) to deliver customized lessons, modify instructional ma-
terials, and augment user involvement. These technological advancements deliver immediate feedback,
accommodate unique learning preferences, and provide unprecedented personalization. AI transforms
language assessments, offering adaptive learning, real-time analytics, and automated evaluations for
precise insights. Collaboration ensures ethical and effective AI integration (Akgün & Greenhow, 2021).
Advancing technology allows educators to integrate AI for dynamic, individualized language learning,
fostering inclusivity, innovation, and educational evolution. This chapter examines the convergence of
artificial intelligence (AI) and language teaching materials, investigating novel approaches to utilizing
AI to enhance and supplement the materials employed in language classrooms.
AI transforms language education by offering adaptive, personalized resources and customizing
material for varied linguistic proficiencies, preferences, and cultural backgrounds. (Towle & Halm,
2006). AI-driven language education employs interactive platforms, tutoring systems, and chatbots for
real-time assessment, offering immediate feedback and tailored assistance to foster interactive education
with adaptive pathways, tailoring lessons based on individual progress, ensuring inclusivity, and enhanc-
ing cultural relevance (Roche et al., 2022). By employing this tool, the cultural sensitivity of language
education materials is elevated. The purpose of this chapter is to present a thorough examination of the
potential benefits AI can bring to improve language teaching materials. AI in language education spans
interactive platforms and intelligent tutors. Ethical considerations and teacher preparedness are vital for
successful integration (Meng et al., 2022). Understanding AI in language education involves exploring
fundamental theories and contextual frameworks to develop effective instructional materials.

LITERATURE REVIEW

The concept of cognitive load theory, initially introduced by John Sweller, centres on the degree of
cognitive exertion required during the learning process (Sweller, 2012). It is proposed that the design of
instructional materials should regulate cognitive burden to maximize learning outcomes efficiently. AI
can assist in customizing language teaching materials for individual students by regulating and modifying
the difficulty level following their cognitive abilities. This customization is consistent with the tenets of
Cognitive Load Theory, given that artificial intelligence can analyze real-time data on student perfor-
mance, identify problem areas, and adapt learning materials dynamically (Gandhi et al., 2023; Zhao et
al., 2022). Furthermore, artificial intelligence (AI) can utilize tactics such as chunking information into
more manageable segments, thereby reducing the cognitive burden on learners. Artificial intelligence
can augment comprehension and retention by deconstructing and presenting intricate linguistic concepts
sequentially. It is consistent with cognitive load theory principles, which advocate reducing unnecessary
cognitive load and enhancing relevant cognitive load. As a result, language learners can concentrate on
comprehending and utilizing newly acquired skills. Adaptive learning pathways may also be incorporated

23

Enhancing Language Teaching Materials Through Artificial Intelligence

into AI-powered language instructional materials, following the Cognitive Load Theory’s suggestion that
personalized instruction is optimal (Sweller et al., 2022; Zhao et al., 2022). By dynamically adapting
these pathways following the learners’ progress, it is possible to maintain a challenging yet optimally
designed curriculum that promotes effective learning. The capacity for adaptation mitigates cognitive
excess and guarantees that learners can effectively process and assimilate language concepts. Funda-
mentally, incorporating artificial intelligence (AI) into language instructional resources exemplifies a
beneficial implementation of cognitive load theory. Anger management, adaptive learning experiences,
and the personalization of content are a few of the functionalities of artificial intelligence that educators
can utilize to improve the efficacy and efficiency of language instruction (Sweller et al., 2022; Paas &
Van Merriënboer, 2020). By adhering to the principles of Cognitive Load Theory, this language learning
environment becomes more learner-centric and optimized from a cognitive standpoint.
Building upon the research of Jean Piaget and Lev Vygotsky, constructivism places significant
emphasis on the active engagement of learners as they construct their understanding of knowledge.
The social process of learning is characterized by collaboration and interaction. Language-teaching
materials propelled by AI have the potential to foster collaborative and interactive learning environ-
ments. The constructivist approach is compatible with chatbots, virtual language exchange platforms,
and AI-driven discussion forums, enabling students to participate in language learning actively. Within
the constructivist paradigm, learners are perceived as engaged contributors who construct knowledge
utilizing practical experiences and interpersonal engagements. Some theories say that AI tools, including
chatbots, facilitate learners’ active application of language skills through the simulation of real-world
conversations. Assisting learners in dialogues while providing immediate corrections and feedback,
these interactive conversational agents support the constructivist principle of learning through reflection
and feedback. An additional implementation of AI in language education is virtual language exchange
platforms, which link students with native speakers or peers from around the globe (Behrens, 2021;
Kaufman, 2004). Implementing virtual language exchange platforms facilitates this engaging and coop-
erative linguistic setting. These platforms serve as spaces where students actively partake in authentic
dialogues, cultural interchanges, and collaborative language exercises. The constructivist principle is
upheld, emphasizing that the most efficient learning occurs within social and meaningful environments.
In addition, discussion forums powered by artificial intelligence can strengthen collaborative learning
by providing a venue for students to exchange thoughts, pose inquiries, and work together on projects
about language. AI can facilitate these forums to guarantee that discussions follow language learning
objectives and encourage constructive interactions among learners (Cohen & Téllez, 1994; Bruffee,
1984). By actively participating in discussions, learners can exchange their unique viewpoints and col-
laboratively develop an understanding of language usage, grammar, and cultural subtleties. Language
instructional materials powered by artificial intelligence facilitate a constructivist approach to language
education. AI aligns with the constructivist philosophy by providing collaborative and interactive learn-
ing experiences via discussion forums, chatbots, and virtual language exchange platforms (Kaufman,
2004). For example, a language-learning application powered by artificial intelligence could incorporate
chatbots that engage learners in simulated conversations, offering immediate feedback and corrections.
A virtual language exchange platform could connect students with native speakers or peers globally,
enabling authentic dialogues and cultural exchanges. Through these AI-driven tools, students actively
participate in constructing their understanding of language, aligning with the constructivist approach to
education. This philosophy underscores the significance of active participation, social interaction, and
collective knowledge construction as critical components of the language learning journey. Incorporat-

24

Enhancing Language Teaching Materials Through Artificial Intelligence

ing artificial intelligence (AI) into language education improves its efficacy by providing learners with
dynamic and interactive learning experiences.
Adaptive Learning Theory (Towle & Halm, 2006) is predicated on the customization of instruction
to the specific requirements of each learner. Utilizing technology facilitates individualized learning
experiences by adapting the material, speed, and evaluations to the learner’s progress. By analyzing
learner data, AI technologies can dynamically adapt language instructional materials. The ability to ad-
just ensures that educational materials align with students’ individual learning patterns, preferences, and
proficiency levels, promoting a more efficient and tailored educational experience. The impact of AI’s
adaptive learning capabilities in language education is especially significant. By continuously analyzing
learner interactions, AI algorithms can detect patterns, strengths, and areas that require refinement. By
leveraging data, this methodology permits the adaptation of language instructional resources to cater
to the unique requirements of each learner. For example, suppose a student excels at specific language
abilities while encountering difficulties with others. In that case, artificial intelligence can adapt the level
of difficulty and emphasis of lessons in real time to deliver specific assistance where it is required most.
Moreover, the adaptability of AI surpasses mere content customization and encompasses personalized
cadence as well. Language learners advance individually, guaranteeing adequate time to comprehend
concepts and solidify their comprehension before proceeding.
Adaptive pacing accommodates a wide range of learning rates, including those who progress quickly
and those who benefit more from a deliberate and comprehensive approach. Providing targeted and
immediate feedback is an additional crucial element of AI-powered adaptive learning. AI can give in-
stantaneous feedback on language usage, pronunciation, and comprehension based on real-time analysis
of learner responses. Implementing this immediate feedback loop is crucial in expeditiously rectifying
errors, reinforcing proper usage, and augmenting overall language proficiency. The incorporation of AI
into language education perfectly matches the tenets of Adaptive Learning Theory (Jiang, 2022; Seo et
al., 2021). Using artificial intelligence (AI) to analyze learner data and dynamically adapt instructional
materials enhances language education’s responsiveness, personalization, and efficacy (Seo et al., 2021).
By implementing this adaptive methodology, students are guaranteed personalized assistance, the abil-
ity to advance at their rates, and the advantage of prompt evaluation, all of which contribute to a more
captivating and fruitful language-learning encounter.
A subfield of artificial intelligence (AI), Natural Language Processing (NLP), examines the relation-
ship between computers and human language (Kaddari et al., 2020). It entails the creation of models and
algorithms that empower machines to comprehend, interpret, and produce text that resembles that of
humans. NLP is paramount in developing intelligent tutors, chatbots, and language assessment tools for
language instructional materials. These applications facilitate language acquisition through immediate
feedback, the simulation of authentic language usage, and the delivery of customized language practice. An
essential impact of natural language processing (NLP) on language education has been the development
of intelligent language instructors (Tafazoli et al., 2019). By utilizing NLP algorithms, these instructors
analyze students’ responses to determine their level of language proficiency and subsequently customize
instruction. These competent instructors create a dynamic and engaging learning environment by simulat-
ing interactive conversations and replicating real-life language interactions closely. Using NLP-powered
instructors facilitates immediate correction for students and reinforces adherence to correct language
usage. NLP-powered chatbots are an additional asset that can be added to language-teaching materials.
By engaging learners in text or voice conversations, these chatbots simulate the learning environment and
facilitate the practice of language skills. NLP empowers chatbots to comprehend input in natural language,

25

Enhancing Language Teaching Materials Through Artificial Intelligence

provide contextually relevant responses, and adjust the level of complexity of conversations following
the learner’s proficiency (Jeon & Lee, 2023; Belda-Medina & Calvo-Ferrer, 2022). By giving hands-on
and immersive experiences, this conversational and interactive method enhances language acquisition.
In addition, NLP makes a substantial contribution to language assessment instruments. Utilizing NLP
algorithms, automated language assessment systems are capable of real-time evaluation of learners’
language proficiency. The evaluations encompass various topics, such as pronunciation, vocabulary, and
grammar. Using NLP-based assessments enables learners to monitor their progress, pinpoint areas that
require refinement, and obtain focused guidance to enhance their skills through immediate feedback.
NLP is critically important in creating language instruction materials powered by AI. NLP enhances lan-
guage education by utilizing intelligent instructors, chatbots, and assessment tools, all of which facilitate
dynamic, interactive, and personalized learning experiences. The ongoing progression of technology
presents an opportunity to enhance language learning experiences by incorporating natural language
processing (NLP) into instructional materials (Baha et al., 2023; Kurni et al., 2023). This integration
could result in more effective, engaging, and individualized language learning journeys for students.
Lev Vygotsky’s sociocultural theory significantly emphasizes the influence of cultural context and
social interactions on forming cognitive processes (Eun, 2010). The learning process is socially medi-
ated; AI can facilitate sociocultural interactions in language learning by enabling collaborative initiatives,
language exchange platforms, and virtual language communities. These technological advancements
transcend the confines of the traditional classroom setting, fostering connections between students and
culturally and linguistically diverse environments. AI-enabled virtual language communities offer a
platform for language learners to participate in collaborative language activities. These communities
can replicate authentic language usage by integrating chatbots, virtual tutors, and peer interactions.
Students can cultivate a sense of community and engage in collective learning experiences by honing
their language abilities in a social setting. AI-powered language exchange platforms facilitate connec-
tions between language learners, language enthusiasts and native speakers worldwide. These platforms
pair language learners according to their shared interests, proficiency levels, and language objectives.
Through active participation in language exchanges, students not only enhance their linguistic profi-
ciency but also acquire a deeper understanding of diverse cultures, dialects, and modes of communica-
tion. AI-supported collaborative projects enable students to join efforts to complete language-related
assignments. AI can support group endeavours by offering necessary resources, constructive criticism,
and coordination instruments. Collaborative initiatives furnish learners with prospects to collectively
resolve challenges, exchange insights, and investigate linguistic variety (Zou et al., 2023; Machwate et
al., 2021). An example of a community facilitating collaborative language projects with AI support is
“Tandem.” Tandem is a language exchange app that connects users with language learners worldwide
for virtual language exchange. In this community, learners can collaborate on language-related assign-
ments, engage in conversation, and provide feedback to each other, enhancing their linguistic skills and
cultural understanding. The platform utilizes AI to suggest conversation topics, match language exchange
partners, and provide language resources, contributing to a collaborative and enriching language learn-
ing experience.
Moreover, language learning platforms propelled by AI can expose students to authentic materials,
traditions, and customs by integrating cultural elements into lessons. Through a greater comprehension
of the cultural milieu in which the language is utilized, this integration enhances the educational expe-
rience. AI promotes collaborative and culturally diverse learning environments in language education,
contributing to sociocultural theory (Li & Yu, 2021). By facilitating sociocultural exchanges facilitated

26

Enhancing Language Teaching Materials Through Artificial Intelligence

by AI, language learners can engage with a worldwide community and gain first-hand knowledge of vari-
ous linguistic and cultural milieus. Incorporating artificial intelligence (AI) into sociocultural language
learning can augment the depth and genuineness of language instruction as technology progresses. AI
language platforms integrate authentic materials, traditions, and customs, enhancing cultural under-
standing. Learners experience a personalized, culturally diverse education using multimedia content
and adaptive algorithms aligning with sociocultural theory.
Concerning algorithmic bias, privacy, and data security, implementing AI in education raises ethical
issues. It is imperative to comprehend the ethical ramifications to guarantee the responsible and equi-
table implementation of artificial intelligence in language instructional resources. In language educa-
tion, developers and educators must be conscious of and address ethical concerns associated with AI
applications. It encompasses measures to safeguard data privacy, reduce biases in artificial intelligence
models, and promote transparency regarding the implementation of AI technologies. Data privacy is
of the utmost importance in language education powered by AI. Because these systems amass and
analyze enormous quantities of learner data, it is critical to implement stringent safeguards to secure
sensitive information (Nguyen et al., 2022; Akgün & Greenhow, 2021). To protect learners’ privacy, it
is imperative to implement explicit policies and procedures that guarantee data is utilized exclusively
for educational intentions and remains invulnerable to unauthorized access or exploitation. Addressing
biases in AI models constitutes an additional pivotal element of ethical AI integration. It is incumbent on
developers to consistently assess and rectify any biases that might unintentionally manifest in language
teaching materials, algorithms, or datasets. It is critical to understand cultural, linguistic, and gender
biases to guarantee that AI technologies foster inclusiveness rather than perpetuate prejudice or discrimi-
nation. Integrity is crucial for establishing confidence in AI applications (Holmes et al., 2021; Akgün
& Greenhow, 2021). Singha and Singha (2023) suggest safeguarding sensitive data and user privacy in
organizations through encryption, access controls, threat detection mechanisms, and privacy protection
measures. Developers and educators must communicate transparently regarding how AI is incorporated
into language learning materials, including the algorithms employed, data categories gathered, and the
integration process. Transparent communication assures accountability in utilizing these technologies
and aids stakeholders, learners, and educators in comprehending the function of AI in the learning
process. Educators and developers can strategically incorporate AI into language teaching materials by
considering these ethical principles. It would ensure that technology remains in line with established
educational principles and ultimately improve the quality of the language learning experience (Klímová
et al., 2023; Akgün & Greenhow, 2021). By employing this methodology, the advantages of AI in lan-
guage instruction are optimized, while possible hazards and ethical considerations are reduced. In the
ongoing evolution of AI in education, it is critical to establish and uphold a robust ethical framework to
foster an environment that is secure, responsible, and inclusive.

CURRENT LANDSCAPE OF AI IN LANGUAGE TEACHING

This wide range of AI-driven instructional tools not only exemplifies the cutting-edge technologies
that are reshaping the field of language education but also underscores the dynamic and comprehensive
learning opportunities accessible to students. Automated language instructors, furnished with sophis-
ticated machine learning and natural language processing (NLP) algorithms, are a prime illustration of
AI-powered education’s individualized and flexible characteristics (Eguchi, 2021; Chaudhry & Kazim,

27

Enhancing Language Teaching Materials Through Artificial Intelligence

2021). For example, the conversational practice on Duolingo and Microsoft Xiaoice can be custom-
ized to suit the proficiency levels of individual users, thereby establishing a dynamic and captivating
atmosphere for language acquisition. Incorporating AI into language learning applications like Babbel
surpasses a simple examination of user interactions. The learning paths are proactively customized
according to individual performance and preferences, guaranteeing a customized and productive edu-
cational experience. Platforms like Tandem utilize artificial intelligence to connect learners with native
speakers, facilitating collaborative and interactive language practice in the real world (App Store, 2015).
Knewton’s demonstration of the adaptability of content and curriculum platforms guarantees that edu-
cational materials are consistently modified to cater to each learner’s unique requirements, providing a
flexible and personalized learning experience (El-Sabagh, 2021). By adjusting content in response to
user performance, gamified language learning applications, such as Memrise, demonstrate how artificial
intelligence can augment motivation and engagement, rendering language acquisition interactive and
pleasurable. Rosetta Stone’s multimodal language learning platforms exemplify artificial intelligence’s
(AI) adaptability in handling diverse input formats, furnishing students with an all-encompassing and
immersive language acquisition encounter. The investigation into these AI-driven instructional tools
highlights their capacity for profound change and the learner-centred and interactive characteristics
that characterize contemporary language instruction (Tan, 2023; Yeşilyurt, 2023). As these technolo-
gies progress, individuals pursuing language acquisition can anticipate an ever-expanding selection of
practical, interactive, and personalized resources that accommodate their specific learning inclinations.
It will create a dynamic and captivating educational experience.
Integrating AI applications in language education represents a paradigm shift in pedagogy, establish-
ing an interdependent ecosystem that enhances learning. Integrating diverse AI-powered tools creates
a unified and ever-changing educational setting, facilitating a more individualized and efficient learn-
ing experience. Apps for personalized learning, intelligent language tutors, and adaptive chatbots are
examples of how AI integrates seamlessly with conventional teaching methods. Language instructors
enhance learners’ progress by implementing targeted feedback and personalized instruction via machine
learning algorithms and natural language processing (Zhu, 2020). Practical communication skills are
enhanced through chatbots such as Microsoft’s Xiaoice, which facilitate immersive conversations and
provide learners with simulated real-world language practice. Language learning applications showcase
how AI analysis of user interactions and progress monitoring customizes learning trajectories according
to personal preferences—providing a more captivating and individualized language learning encounter—
with Babbel serving as an illustrative case. As exemplified by ETS’s SpeechRater, automatic language
assessment systems demonstrate the efficacy that artificial intelligence (AI) imparts to education by
providing immediate evaluations of spoken competence. The combined influence of these artificial
intelligence technologies in language education is readily apparent, establishing a pathway towards a
revolutionary, student-focused, and interrelated process of acquiring a language (Hou, 2020; Zhu, 2020).
With the ongoing development of these technologies, students can expect an educational voyage that is
progressively more immersive and dynamic. Throughout this process, artificial intelligence (AI) will
seamlessly integrate into the language learning framework, enhancing each aspect of the journey.

28

Enhancing Language Teaching Materials Through Artificial Intelligence

PERSONALIZED LEARNING: REDEFINING LANGUAGE ACQUISITION

Powered by Artificial Intelligence (AI), adaptive learning pathways have ushered in a paradigm shift in
language education, fundamentally reshaping traditional instructional approaches. This innovative ap-
plication of artificial intelligence entails customizing the educational experience to precisely align with
every learner’s requirements, speed, and inclinations. AI algorithms, which frequently integrate Natural
Language Processing (NLP) and machine learning, form the basis of this innovation. These algorithms
consistently evaluate and analyze the progress of every learner. Dynamic personalization facilitates the
instantaneous modification of lesson sequences, content, and difficulty levels, following the learner’s
learning style and level of proficiency. By utilizing real-time assessment and promptly modifying the
learning pathway, this approach guarantees that areas of improvement are attended to, deficiencies are
rectified, and students’ progress to more complex concepts when suitable.
AI-driven adaptive learning pathways provide individualized scheduling that surpasses the constraints
of conventional education models, thereby accommodating learners with varying rates of progress. The
ability to adapt enables individuals to make progress at a personalized pace, granting them the flexibility
to explore ideas in greater depth or rapidly advance. The system’s proficiency in discerning particular
language abilities that require enhancement guarantees focused skill development, concentrating on each
individual’s strengths and limitations. As individuals improve their linguistic skills, AI-powered trajectories
consistently adjust to guarantee that the educational process remains pertinent and thought-provoking,
fostering enduring interest and development. In brief, artificial intelligence-driven adaptive learning
pathways signify a fundamental change in language acquisition by providing a customized, adaptable,
and data-informed learning experience that accommodates individual students’ distinct requirements
and inclinations (Karoui et al., 2022). By employing this revolutionary methodology, acquiring language
skills is optimized, and AI is also positioned as a fundamental element in moulding the trajectory of
education in the coming years.
A paradigm shift in language education is exemplified by the use of Artificial Intelligence (AI) to
facilitate personalized content delivery and learner engagement. AI’s significant impact on transforming
how content is delivered, and learners engage with it represents a fundamental change toward a more
individualized and effective educational environment. Through analyzing user interactions and learning
preferences, language learning platforms powered by artificial intelligence have been at the forefront of
providing content tailored to each individual’s proficiency level. This individualized methodology also
encompasses adaptive learning materials, in which AI algorithms consistently evaluate the aptitudes
and deficiencies of learners, dynamically modifying the level of difficulty of the material in real-time to
guarantee an ideal equilibrium between problem and involvement. AI-driven content delivery enables an
inherent level of personalization that surpasses simple customization and significantly enhances learner
engagement. By integrating gamification components, interactive activities, and practical situations,
acquiring language skills is transformed into something both pleasurable and highly applicable.
Artificial intelligence’s prompt and specific feedback functionalities foster a nurturing educational
setting, enabling students to promptly remedy errors and solidify accurate language applications.
Incorporating AI into interactive learning platforms enhances the language-learning experience by in-
corporating chatbots and virtual language exchanges, among other features. AI customizes content and
entire learning paths by offering recommendations for specific modules and activities that align with
the individual’s objectives and advancement (Karoui et al., 2022). Fundamentally, this innovative and
learner-focused methodology for language instruction, facilitated by artificial intelligence, represents

29

Enhancing Language Teaching Materials Through Artificial Intelligence

a substantial deviation from conventional frameworks. It guarantees students encounter individualized

material and participate actively in a gratifying and customized educational experience.

INNOVATIVE ASSESSMENT METHODS: AI’S ROLE

The implementation of AI-powered real-time performance analytics in language education brings

about a significant transformation through the provision of instantaneous insights, flexible teaching
methodologies, and a data-centric approach that ultimately improves the efficacy and learner-centric
nature of language learning experiences (Salas‐Pilco et al., 2022; Khan et al., 2021). With the continu-
ous progression of technology, the incorporation of real-time analytics holds significant potential as a
determining factor in the trajectory of language education itself. Integrating automated assessment and
feedback systems powered by Artificial Intelligence (AI) capabilities represents a paradigm shift in lan-
guage education. By implementing sophisticated natural language processing (NLP) algorithms, these
systems have significantly transformed the evaluation procedure by furnishing learners with prompt,
focused feedback. The utmost importance is placed on the effectiveness and promptness of automated
assessment, as AI algorithms rapidly scrutinize written assignments and oral responses, assessing aspects
such as pronunciation, vocabulary utilization, and grammar. Educators can provide timely feedback by
automating the assessment process, promoting an ongoing learning cycle. Automated grading guarantees
a consistent and unbiased evaluation by consistently implementing pre-established criteria and reducing
the influence of subjective biases in the assessment process. The feedback produced by these systems
is tailored to individual needs, enabling learners to obtain precise evaluations of their performance that
direct them towards their most substantial areas and those that necessitate enhancement. In addition,
the flexibility of automated grading systems facilitates the development of adaptive learning environ-
ments by customizing subsequent assignments per each student’s unique abilities and deficiencies, thus
maximizing their educational experience.
Grading systems propelled by AI are invaluable in educational environments with many students
due to their scalability. Finally, educators are equipped with valuable information regarding overall
class performance trends and individual student progress through the data-driven insights produced by
these systems (Xi, 2010). It empowers them to customize instructional strategies following empirical
evidence. Automated evaluation and feedback systems powered by artificial intelligence are of utmost
importance in improving the effectiveness and responsiveness of language education assessments through
the facilitation of consistency, personalization, and efficiency.
A frontier of revolution in language education is being traversed with the assistance of Artificial In-
telligence (AI) in real-time performance evaluation and analytics. This innovative methodology entails
the ongoing surveillance and evaluation of students’ engagement with language resources, delivering
immediate and dynamic feedback. AI algorithms efficiently evaluate written and spoken responses,
continuously monitoring learners’ pronunciation, vocabulary comprehension, and grammar usage. It
provides educators with instantaneous insights into the proficiency levels of their students. In addition
to conventional evaluation methods, real-time performance analytics provide continuous assessments of
student engagement, enabling instructors to modify their instructional approaches following changing
demands. The ongoing assessment of adaptability guarantees that the learning process remains pre-
cisely calibrated to confront obstacles promptly (Roll & Wylie, 2016). In addition, real-time analytics
empowers instructors to deliver immediate and customized feedback, cultivating a nurturing educational

30

Enhancing Language Teaching Materials Through Artificial Intelligence

setting where students actively pursue language proficiency. The abundance of data produced by these
analytics facilitates improved decision-making based on data, allowing educators to discern recurring
obstacles, customize instructional approaches, and efficiently distribute resources. Constant tracking of
the progress of individual students enables educators to gain a more comprehensive comprehension of
their learning trajectories, providing them with invaluable information to tailor assistance accordingly.

ETHICAL CONSIDERATIONS AND CHALLENGES

Amidst the emergence of AI-mediated learning environments, the imperative to uphold the utmost ethical
standards in education becomes more apparent: the need to safeguard academic integrity and combat
plagiarism. Incorporating Artificial Intelligence (AI) into educational platforms offers both a prospect
and a hurdle in fostering an equitable and truthful academic environment. One advantage is the possibil-
ity of real-time detection via sophisticated plagiarism tools that employ advanced algorithms. It enables
prompt identification of instances of academic dishonesty and facilitates immediate intervention. Student
consciousness is considerably increased through integrating integrity-focused educational modules into
AI-mediated platforms; these modules inform users of the significance of generating original content
and the repercussions associated with plagiarism. AI’s distinctive capability to deliver immediate feed-
back strengthens adherence to ethical writing standards, thereby establishing a proactive stance towards
upholding academic integrity.
AI plays a role in providing personalized guidance to students, aiding them in comprehending appro-
priate paraphrasing techniques and citation standards. In addition to preventing plagiarism, this promotes
academic integrity by providing students with the necessary understanding to conduct themselves ethi-
cally as scholars. Nevertheless, obstacles continue to endure, specifically in light of the rise of advanced
plagiarism methods that exploit developing AI capabilities. It emphasizes the sustained importance of
privacy and ethical considerations in learning environments mediated by AI. To adequately confront these
challenges, education and awareness continue to be crucial. Under its ability to provide reminders and
contextualized information, AI has the potential to significantly contribute to the ongoing reinforcement
of students regarding the critical nature of academic integrity. Mitigation strategies include implement-
ing thorough institutional policies, routine audits of artificial intelligence (AI) tools to verify their ef-
fectiveness and impartiality, and fostering a culture of integrity by acknowledging and commemorating
innovative contributions. To ensure academic integrity in AI-mediated learning, adopt a comprehensive
and multifaceted strategy incorporating technological advancements, educational programs, and solid
institutional structures (Foltúnek et al., 2023). Integrating these components establishes an environment
that promotes ethical behaviour and actively safeguards it. It fosters a culture that emphasizes and adheres
to the tenets of academic integrity.
The imperative to guarantee AI-generated materials are devoid of bias is paramount in educational
content creation and distribution. The growing incorporation of Artificial Intelligence (AI) into educational
platforms requires an increased recognition of the possible inadvertent biases that may enter datasets
and algorithms. The onus is on those who conscientiously conceive and curate educational resources,
which include evaluations, tasks, and instructional material. To establish an AI-driven educational en-
vironment devoid of bias, it is imperative that both developers and educators proactively participate in
the detection and rectification of preferences that may arise from cultural stereotypes or historical data.
Adopting this proactive stance is crucial for guaranteeing that the artificial intelligence algorithms uti-

31

Enhancing Language Teaching Materials Through Artificial Intelligence

lized in educational technology are not only technologically sophisticated but also intrinsically equitable,
inclusive, and reflective of a wide range of viewpoints. It is critical to prioritize integrating diversity
and inclusivity principles into AI-driven educational materials to cultivate honest learning experiences.
Singha & Singha (2023a) argue that sustaining artificial intelligence (AI) and machine learning (ML)
necessitates both human diversity and mindfulness.
The dedication to reducing bias goes beyond the preliminary design stage. Consistent audits and
continuous surveillance of AI-generated content are fundamental elements of a holistic approach to
identifying and rectifying potential biases that may develop gradually. Utilizing this dynamic and itera-
tive procedure, educational content is consistently synchronized with the ever-changing benchmarks
of equity and inclusiveness. To develop AI-driven educational materials that are devoid of bias, it is
imperative to balance technological proficiency and an unwavering dedication to inclusiveness (Akter et
al., 2021; Loder et al., 2019). Through proactive measures to mitigate biases during all stages of develop-
ment, implementation, and upkeep, the academic community can cultivate an environment conducive
to learning in which AI-powered resources function as impartial, fair, and enlightening instruments that
enhance the educational experience in its entirety and breadth.

SUCCESSFUL CASES OF AI INTEGRATION IN LANGUAGE EDUCATION

Language learning platforms incorporating artificial intelligence (AI) symbolize a substantial advance-
ment in educational technology by presenting novel methods for acquiring a second language. Numerous
prominent platforms exemplify the effective incorporation of artificial intelligence, thereby showcasing
the capacity for individualized, adaptable, and captivating language instruction. As an industry-leading
AI-enhanced language learning platform, Duolingo is distinguished. By utilizing AI-driven algorithms
and a gamified interface, Duolingo customizes lessons to suit the unique proficiency levels of its users.
Chatbots on the platform provide interactive conversational practice and alter the difficulty level based
on the user’s performance, resulting in effective language acquisition.
AI is utilized by Rosetta Stone, a renowned provider of immersive language learning experiences,
to improve user engagement and outcomes. The platform offers immediate feedback on pronunciation
through AI-powered speech recognition. Rosetta Stone ensures effective and individualized language
instruction by modifying content following student development.
By utilizing AI, Babbel optimizes users’ language learning paths. The platform analyses user in-
teractions and customizes courses to suit users’ requirements and preferences. Babbel’s AI-powered
methodology prioritizes pragmatic language proficiencies, delivering an individualized and adaptable
educational encounter that strongly connects with students.
As an illustration of the incorporation of AI into language education, Lingodeer provides individu-
alized learning trajectories. The platform modifies the content by customizing the learning experience
according to an individual’s assets and weaknesses. Lingodeer implements AI-powered interactive
exercises and lexical drills to augment user engagement and language proficiency.
ChatGPT Language Tutor and other AI-powered language tutoring applications offer users conver-
sational and interactive language practice. By simulating real-life dialogues with natural language pro-
cessing (NLP) algorithms, these platforms provide language learners with an immersive and interactive
experience.

32

Enhancing Language Teaching Materials Through Artificial Intelligence

AI is integrated into the language learning platform Memrise to increase user engagement. The
platform generates an engaging and interactive learning environment by incorporating gamification ele-
ments and adjusting content in response to user performance. The methodology employed by Memrise
exemplifies how AI can render language instruction both productive and enjoyable. These illustrations
showcase the wide-ranging implementations of artificial intelligence in language learning, encompassing
interactive conversational practice and personalized content delivery. By utilizing artificial intelligence,
these platforms provide students with a personalized and dynamic method for acquiring proficiency in
foreign languages, ultimately enhancing the efficacy and appeal of language learning.
The utilization of AI in personalized learning paths guarantees that students are provided with mate-
rial customized to their specific requirements and levels of expertise. Implementing AI algorithms, such
as those found in the chatbots of Duolingo or the speech recognition system of Rosetta Stone, enables
instantaneous corrections and enhancements in language usage and pronunciation. Implementing dynamic
adaptation leads to improved learning outcomes, as it ensures that learners receive focused assistance
exactly where they require it, thereby expediting the development of their language proficiency.
The integration of artificial intelligence has fundamentally transformed how language learners interact.
Duolingo and Memrise exemplify that gamified interfaces introduce interactivity and enjoyment into the
learning process. AI-powered personalization implemented in platforms such as Lingodeer and Babbel
fosters a user-centric atmosphere by ensuring that teachings correspond to individual progress and pref-
erences. By replicating authentic language exchanges, the incorporation of natural language processing
into ChatGPT Language Tutor facilitates conversational practice that is both realistic and responsive.
These platforms’ ability to accommodate their users’ strengths and limitations cultivates a feeling of
achievement and encouragement. Incorporating AI into interactive exercises, vocabulary lessons, and
content adaptation makes language learning more dynamic and engaging. Consequently, individuals are
more inclined to maintain their motivation and dedication towards pursuing language acquisition, foster-
ing favourable user experiences. AI integration in language learning platforms has initiated a paradigm
shift towards individualized and captivating instruction. The influence on educational achievements is
demonstrated in the expedited growth of linguistic competence, while user engagement is enhanced via
interactive interfaces, personalized material, and prompt corrections. These developments collectively
improve the quality and appeal of language education, demonstrating the revolutionary capacity of ar-
tificial intelligence to shape the future learning trajectory.

FUTURE HORIZONS: AI’S EVOLUTION IN LANGUAGE EDUCATION

The evolution of Artificial Intelligence (AI) is poised to revolutionize language education, ushering in
a new era of personalized, adaptable, and multimodal learning experiences. The rapid advancements in
AI promise not only to transform instructional resources but also to reshape the educational landscape.
Language education is poised to undergo a significant paradigm shift shortly, propelled by the swift
progressions in Artificial Intelligence (AI). These advancements have the potential to not only revolu-
tionize instructional resources but also transform the overall educational environment (Roll & Wylie,
2016). The forthcoming improvement in artificial intelligence holds the potential to introduce a novel
epoch characterized by learning pathways that are exceptionally personalized and adaptable. Sophis-
ticated algorithms, equipped with a profound comprehension of personal learning styles, preferences,
and proficiency levels, are poised to bring about a paradigm shift in instructional materials by precisely

33

Enhancing Language Teaching Materials Through Artificial Intelligence

customizing them to suit the distinct requirements of every learner. It is anticipated that the impact of AI
will not be limited to simple customization but will also encompass content production autonomously.
It implies that instructional resources will adapt dynamically and immediately in response to student
progress and performance, guaranteeing that students remain consistently engaged and suitably stimulated
throughout their academic trajectory. An imminent development is incorporating multimodal learning
resources, including augmented reality applications, virtual reality experiences, and interactive videos.
It indicates a transition towards a more all-encompassing and captivating educational encounter, which
caters to the varied inclinations of students and promotes a more profound comprehension of the content
(De Oliveira et al., 2019). With the ongoing progress in Natural Language Processing (NLP), individu-
als learning the language can expect significant improvements in the precision of language evaluations,
instantaneous feedback systems, and conversational language resources that imitate human interactions
almost precisely. In addition, forthcoming developments can incorporate gamification and interactive
components into educational resources, bolstering motivation and maintaining long-term engagement.
The expected progressions in artificial intelligence (AI) possess the capacity to enhance and fundamen-
tally transform the language education field (Jiang, 2022). By utilizing teaching resources that are highly
personalized, adaptable, and multimodal, students can anticipate a future in which education is more
effective, immersive, and dynamic. The aforementioned transformative capacity establishes the foun-
dation for an educational encounter that is not solely technologically sophisticated but also profoundly
tailored to every learner’s specific requirements and inclinations.
The investigation into teaching resources generated by artificial intelligence signals the beginning
of a paradigm shift in language education, as AI is poised to reshape how educational materials are pro-
duced and distributed. One fundamental aspect of this paradigm shift resides in the capacity of artificial
intelligence to customize the development of educational materials independently to suit the distinct
characteristics of every learner. By harnessing sophisticated algorithms, artificial intelligence (AI) evalu-
ates learners’ strengths, weaknesses, and preferences to generate tailored materials that effectively target
their requirements. Doing so guarantees that educational materials are pertinent and their difficulty is
maximized, promoting a more streamlined and individualized learning experience. One crucial element
concerning the potential of teaching resources generated by AI is their ability to alter in real time in
response to dynamic learner interactions. As students interact with the resources, artificial intelligence
algorithms evaluate their progress and modify the material to correspond with their reading speed and
level of understanding. The capacity to adapt ensures that instructional materials remain sensitive to
changing learning requirements, resulting in a personalized and productive educational experience (Hol-
mes, 2019). By integrating diverse modalities, including interactive videos, virtual reality scenarios, and
augmented reality applications, artificial intelligence demonstrates its capacity to generate multimodal
learning experiences. AI extends the learning experience by incorporating multimedia components,
increasing engagement and immersion, accommodating a wide range of learning preferences, and sub-
stantially influencing comprehension.
The potential for language education to be substantially scaled up is heightened by the efficacy of
AI resource generation. By eliminating the need for educators to allocate time and resources towards
material development, automated content creation allows them to focus on more strategic facets of in-
struction. This enhanced efficacy enables a broader and more readily available dissemination of superior
educational content produced by artificial intelligence. An essential element that significantly contrib-
utes to the transformative capacity of teaching resources generated by AI is the ongoing enhancement
achieved via machine learning algorithms. Over time, content generation processes are refined as AI

34

Enhancing Language Teaching Materials Through Artificial Intelligence

systems learn and adapt in response to learner feedback and material interaction. By implementing this
iterative development process, instructional materials are continuously updated to align with students’
evolving needs and preferences, augmenting language education’s overall efficacy. Investigating instruc-
tional materials produced by artificial intelligence (AI) portends a forthcoming era in which technology
dominates the creation of adaptive, individualized, and multimodal learning encounters. The potential
for a paradigm shift in language education exists due to AI’s increasing efficiency in generating and
improving instructional materials. It could offer students a more individualized, captivating, and produc-
tive journey towards language proficiency.
The forthcoming developments in AI hold the potential to customize dynamically and autonomously
produce instructional materials, leading to a paradigm shift in language education. With personalized,
adaptive, and multimodal learning experiences on the horizon, students can anticipate a more effective,
immersive, and tailored educational journey towards language proficiency. The transformative capacity
of AI-generated teaching resources signals a shift towards a technologically sophisticated and highly
individualized approach to language education.

COLLABORATION AND MITIGATION OF AI’S DRAWBACKS

Effective collaboration between educators and AI developers is crucial for realizing the complete potential
of AI in education while efficiently addressing its limitations. Such cooperation is not only beneficial
but essential. A symbiotic relationship is established through this collaborative synergy; educators con-
tribute their profound pedagogical knowledge, comprehension of student requirements, and insights into
efficacious teaching approaches. AI developers have the technical proficiency to seamlessly integrate
AI systems into educational settings. Educators’ contributions to this collaborative partnership are of
immense value as they influence the development of AI-powered tools. Educators guarantee that the
technology is advanced and grounded in effective pedagogy by ensuring that these tools align with edu-
cational goals and curricular objectives. Implementing this co-design process is critical to developing
AI applications that integrate seamlessly into the educational experience, improving overall academic
performance (Kim, 2023; Kasepalu et al., 2022). AI developers contribute their technical proficiency,
guaranteeing that the deployed AI systems adhere to the utmost operation, security, and effectiveness
criteria. Their function is of the utmost importance in connecting educational theory with technologi-
cal application, thereby enabling the development of AI tools that are efficient and flexible enough to
accommodate the ever-changing educational environment. Consistent and transparent lines of com-
munication between developers and educators are critical for fostering a dynamic feedback loop. The
ongoing exchange of knowledge and experiences facilitates the iterative enhancement of AI applications
in response to user feedback and classroom requirements. Utilizing collective improvement, AI-powered
instruments can be customized to tackle particular obstacles, improve usability, and more effectively
cater to the varied needs of the academic community. The foundation of an effective incorporation of
AI in education is the fruitful partnership between educators and AI developers (Kim et al., 2022). By
utilizing this collaborative model, the advantages of AI are optimized, and potential disadvantages are
proactively recognized and resolved. As a result, a profoundly transformative educational environment
is created, as it maximizes artificial intelligence’s (AI) capabilities to enhance students’ and instructors’
learning and teaching processes.

35

Enhancing Language Teaching Materials Through Artificial Intelligence

To adequately address the limitations of AI in language education, it is critical to adopt a proactive

and all-encompassing strategy. It requires aggressive implementation of strategies to mitigate potential
ethical, privacy, and bias concerns to prevent their escalation into significant issues. Transparency
becomes a fundamental aspect of this undertaking, requiring unambiguous and candid communication
regarding the operational complexities of AI systems, the data they employ, and the algorithms that
govern their operation. Educators and AI developers contribute significantly to establishing comprehen-
sive guidelines and ethical frameworks governing the ethical application of AI in educational settings
through their collaborative efforts (Akgün & Greenhow, 2021; Holmes et al., 2021). Moreover, because
education is an ever-changing and dynamic domain, educators must engage in continuous professional
development about AI-related subjects. This practice guarantees that individuals teaching languages
remain abreast of the most recent developments, possible obstacles, and ethical implications of artificial
intelligence in the field. With this understanding, educators can actively participate in the responsible
implementation of AI technologies, promoting a culture that values ethical and well-informed usage.
Systematic evaluations and routine audits constitute a pivotal component of the proactive mitigation
approach. Through the systematic assessment of AI applications, educators and developers can detect
and address any potential biases or ethical issues that may develop gradually. The aforementioned itera-
tive procedure substantially contributes to the overall reliability of AI applications in language educa-
tion, assuring stakeholders regarding the honest and impartial implementation of these technologies. A
solid groundwork for the responsible incorporation of AI in language education is established upon the
collaboration between educators and AI developers, supplemented by proactive measures to mitigate
concerns (Gartner & Krašna, 2023; Nguyen et al., 2022). By adopting this cooperative and foresee
methodology, we guarantee that AI technologies augment the educational process and are dedicated to
mitigating possible disadvantages. In essence, this cultivates an educational setting that is equitable and
efficient, wherein the revolutionary capabilities of artificial intelligence are judiciously utilized for the
advantage of both students and instructors.

DISCUSSION

The discourse thoroughly analyzes the significant ramifications of incorporating Artificial Intelligence
(AI) into language instruction, emphasizing the mutually beneficial association between human profi-
ciency and technological advancement. A compelling future vision arises wherein artificial intelligence
(AI) surpasses its present capabilities and develops the ability to comprehend and address the intricate
requirements of individual learners. Ongoing enhancements to AI algorithms hold the potential for
ever more intricate customization, dynamically adjusting to a wide range of learning styles and prefer-
ences to optimize the process of language acquisition in a manner that is distinct for every student. The
transformative capacity of artificial intelligence (AI) encompasses a fundamental change in pedagogical
approaches, wherein AI-generated materials supplement educators rather than replace them. This col-
laborative framework enables educators to allocate additional time for personalized engagements, guid-
ance, and the cultivation of critical thinking abilities. Ethical considerations are emphasized, focusing on
addressing biases, safeguarding privacy, and maintaining academic integrity. The discourse emphasizes
the need for AI developers and educators to establish comprehensive ethical frameworks to navigate the
intricacies associated with the responsible incorporation of AI in language education.

36

Enhancing Language Teaching Materials Through Artificial Intelligence

The future depicted in the envisioned era of AI-integrated language education is characterized by
its inclusiveness and dynamism, as it anticipates a seamless collaboration between human expertise
and technology. The potential benefits of this collaborative interaction extend beyond the development
of skilled language learners; it also cultivates self-assured and flexible individuals prepared to flour-
ish in an increasingly interconnected digital and global society. Collaboration between educators and
AI developers is crucial for ongoing progress, as it resolves present obstacles and promotes sustained
innovation in language education. The pivotal role of the dynamic and evolving relationship between
human expertise and AI in this transformative endeavour is to guarantee that AI enriches the educational
experience while maintaining the utmost ethical principles. The conclusion and subsequent discussion
collectively construct an all-encompassing account of a future in which language education is trans-
formed into a dynamic, inclusive, and ethically guided domain through the fusion of human ingenuity
and technological understanding.
A proactive and all-encompassing strategy is necessary to mitigate the adverse effects of AI in
language education. It entails recognizing and proactively addressing potential ethical, privacy, and
bias issues. Ensuring stakeholders are well-informed regarding AI system operations, data usage, and
algorithms is considered crucial, and this is facilitated by transparent communication. Educators and AI
developers lead collaborative initiatives to establish ethical frameworks and guidelines, which demon-
strate a steadfast dedication to the responsible utilization of AI in educational environments. Aware of
the ever-changing nature of education, educators must engage in continuous professional development
concerning AI-related subjects. It guarantees that educators are adequately prepared to navigate the
ever-changing environment, actively participating in the responsible implementation of AI technologies.
Systematic evaluations and audits of AI systems regularly function as preventative actions, scrutinizing
applications to detect and address potential biases or ethical issues. This iterative procedure contributes
substantially to developing confidence in AI applications for language education. A solid groundwork
for the responsible incorporation of AI in language education is established upon the collaboration
between educators and AI developers, supplemented by proactive measures to mitigate concerns. By
adopting this cooperative and foreseeing methodology, we guarantee that AI technologies augment the
educational process and are dedicated to mitigating possible disadvantages. In essence, this cultivates
an educational setting that is equitable and efficient, wherein the revolutionary capabilities of artificial
intelligence are judiciously utilized for the advantage of both students and instructors.

CONCLUSION

Integrating artificial intelligence (AI) into language education marks a transformative moment in aca-
demia, heralding an era where technological prowess and human insight synergize. This paradigm shift
promises a future where personalized, adaptive learning environments optimize language acquisition.
As this collaborative journey progresses, ethical considerations such as correcting biases and protecting
privacy are critical. Educators can enhance their roles by responsibly integrating AI, fostering critical
thinking and personalized engagements. This fundamental intersection of AI and human expertise culti-
vates literate individuals and nurtures self-assured, versatile beings poised to thrive in an interconnected,
digitally globalized society.

37

Enhancing Language Teaching Materials Through Artificial Intelligence

REFERENCES

Akgün, S., & Greenhow, C. (2021). Artificial intelligence in education: Addressing ethical challenges
in K-12 settings. AI and Ethics, 2(3), 431–440. doi:10.1007/s43681-021-00096-7 PMID:34790956
Akter, S., McCarthy, G., Sajib, S., Michael, K., Dwivedi, Y. K., D’Ambra, J., & Shen, K. N. (2021).
Algorithmic bias in data-driven innovation in the age of AI. International Journal of Information Man-
agement, 60, 102387. doi:10.1016/j.ijinfomgt.2021.102387
App Store. (2015). Tandem: Language exchange. https://apps.apple.com/us/app/tandem-language-
exchange/id959001619
Baha, T. A., Hajji, M. E., Es-Saady, Y., & Fadili, H. (2023). The impact of educational chatbot on student
learning experience. Education and Information Technologies. Advance online publication. doi:10.1007/
s10639-023-12166-w
Behrens, H. (2021). Constructivist approaches to first language acquisition. Journal of Child Language,
48(5), 959–983. doi:10.1017/S0305000921000556 PMID:34382923
Belda-Medina, J., & Calvo-Ferrer, J. R. (2022). Using chatbots as AI conversational partners in language
learning. Applied Sciences (Basel, Switzerland), 12(17), 8427. doi:10.3390/app12178427
Bruffee, K. A. (1984). Collaborative learning and the “Conversation of Mankind.”. College English,
46(7), 635. doi:10.2307/376924
Chaudhry, M., & Kazim, E. (2021). Artificial intelligence in education (AIEd): A high-level academic
and industry note 2021. AI and Ethics, 2(1), 157–165. doi:10.1007/s43681-021-00074-z PMID:34790953
Cohen, M. D., & Téllez, K. (1994). Implementing cooperative learning for language minority students.
Bilingual Research Journal, 18(1–2), 1–19. doi:10.1080/15235882.1994.10162655
De Oliveira, L. C., Jones, L., & Smith, S. L. (2019). Multimodal literacies in the english language arts
classroom for english language learners. In English language education (pp. 21–31). doi:10.1007/978-
3-030-02245-7_2
Eguchi, A. (2021). AI-powered educational robotics as a learning tool to promote artificial intelligence
and computer science education. In Advances in intelligent systems and computing (pp. 279–287).
doi:10.1007/978-3-030-82544-7_26
El-Sabagh, H. A. (2021). Adaptive e-learning environment based on learning styles and its impact on
development students’ engagement. International Journal of Educational Technology in Higher Educa-
tion, 18(1), 53. Advance online publication. doi:10.1186/s41239-021-00289-4
Eun, B. (2010). From learning to development: A sociocultural approach to instruction. Cambridge
Journal of Education, 40(4), 401–418. doi:10.1080/0305764X.2010.526593
Foltýnek, T., Bjelobaba, S., Glendinning, I., Khan, Z. R., Santos, R., Pavletic, P., & Kravjar, J. (2023).
ENAI Recommendations on the Ethical Use of Artificial Intelligence in Education. International Jour-
nal for Educational Integrity, 19(1), 12. Advance online publication. doi:10.1007/s40979-023-00133-4

38

Enhancing Language Teaching Materials Through Artificial Intelligence

Gandhi, T. K., Classen, D. C., Sinsky, C. A., Rhew, D. C., Garde, N. V., Roberts, A., & Federico, F. (2023).
How can artificial intelligence decrease cognitive and work burden for front line practitioners? JAMIA
Open, 6(3), ooad079. Advance online publication. doi:10.1093/jamiaopen/ooad079 PMID:37655124
Gartner, S., & Krašna, M. (2023). Artificial intelligence in education - Ethical framework. In 12th Mediter-
ranean Conference on Embedded Computing (MECO) (pp. 1-7). 10.1109/MECO58584.2023.10155012
Holmes, W., Porayska-Pomsta, K., Holstein, K., Sutherland, E., Baker, T. T., Shum, S. B., Santos, O.
C., Rodrigo, M. M. T., Cukurova, M., Bittencourt, I. I., & Koedinger, K. R. (2021). Ethics of AI in
education: Towards a community-wide framework. International Journal of Artificial Intelligence in
Education, 32(3), 504–526. doi:10.1007/s40593-021-00239-1
Hou, Y. (2020). Foreign language education in the era of artificial intelligence. In Advances in Intelligent
Systems and Computing (pp. 937–944). doi:10.1007/978-981-15-2568-1_128
Jeon, J. H., & Lee, S. (2023). Large language models in education: A focus on the complementary
relationship between human teachers and ChatGPT. Education and Information Technologies, 28(12),
15873–15892. doi:10.1007/s10639-023-11834-1
Jiang, R. (2022). How does artificial intelligence empower EFL teaching and learning nowadays? A
review on artificial intelligence in the EFL context. Frontiers in Psychology, 13, 1049401. Advance
online publication. doi:10.3389/fpsyg.2022.1049401 PMID:36467167
Kaddari, Z., Mellah, Y., Berrich, J., Belkasmi, M. G., & Bouchentouf, T. (2020). Natural language pro-
cessing: Challenges and future directions. In Lecture Notes in Networks and Systems (pp. 236–246).
doi:10.1007/978-3-030-53970-2_22
Karoui, A., Alvarez, L., Geoffre, T., Guin, N., Lefèvre, M., Lachand, V., & Ramalho, M. (2022). Towards
an automated adaptive learning web platform through personalization of language learning pathways. In
Lecture Notes in Computer Science (pp. 448–454). doi:10.1007/978-3-031-16290-9_35
Kasepalu, R., Prieto, L. P., Ley, T., & Chejara, P. (2022). Teacher artificial intelligence-supported peda-
gogical actions in collaborative learning coregulation: A wizard-of-oz study. Frontiers in Education, 7,
736194. Advance online publication. doi:10.3389/feduc.2022.736194
Kaufman, D. (2004). Constructivist issues in language learning and teaching. Annual Review of Applied
Linguistics, 24. Advance online publication. doi:10.1017/S0267190504000121
Khan, I., Ahmad, A. R., Jabeur, N., & Mahdi, M. N. (2021). An artificial intelligence approach to monitor
student performance and devise preventive measures. Smart Learning Environments, 8(1), 17. Advance
online publication. doi:10.1186/s40561-021-00161-y
Kim, J. (2023). Leading teachers’ perspective on teacher-AI collaboration in education. Education and
Information Technologies. Advance online publication. doi:10.1007/s10639-023-12109-5
Klímová, B., Pikhart, M., & Kacetl, J. (2023). Ethical issues of the use of AI-driven mobile apps
for education. Frontiers in Public Health, 10, 1118116. Advance online publication. doi:10.3389/
fpubh.2022.1118116 PMID:36711343

39

Enhancing Language Teaching Materials Through Artificial Intelligence

Kurni, M., Mohammed, M. S., & Srinivasa, K. G. (2023). Natural language processing for education.
In Springer eBooks (pp. 45–54). doi:10.1007/978-3-031-32653-0_3
Li, P., & Yu, L. (2021). Digital Language Learning (DLL): Insights from behavior, cognition, and
the brain. Bilingualism: Language and Cognition, 25(3), 361–378. doi:10.1017/S1366728921000353
PMID:35669733
Loder, C., Minadeo, L., Jiménez, L. E. C., Luna, Z., Ross, L. J., Rosenbloom, N., Stalburg, C. M., &
Harris, L. H. (2019). Bridging the expertise of advocates and academics to identify reproductive justice
learning outcomes. Teaching and Learning in Medicine, 32(1), 11–22. doi:10.1080/10401334.2019.16
31168 PMID:31293184
Machwate, S., Bendaoud, R., Henze, J., Berrada, K., & Burgos, D. (2021). Virtual exchange to develop
cultural, language, and digital competencies. Sustainability (Basel), 13(11), 5926. doi:10.3390/su13115926
Meng, N., Dhimolea, T. K., & Ali, Z. (2022). AI-enhanced education: Teaching and learning reimagined.
In Educational Communications and Technology (pp. 107–124). Issues and Innovations. doi:10.1007/978-
3-030-84729-6_7
Nguyen, A., Ngo, H. N., Hong, Y., Dang, B., & Nguyen, B. T. (2022). Ethical principles for artificial
intelligence in education. Education and Information Technologies, 28(4), 4221–4241. doi:10.1007/
s10639-022-11316-w PMID:36254344
Paas, F., & Van Merriënboer, J. J. G. (2020). Cognitive-load theory: Methods to manage working memory
load in the learning of complex tasks. Current Directions in Psychological Science, 29(4), 394–398.
doi:10.1177/0963721420922183
Roche, C., Wall, P. J., & Lewis, D. (2022). Ethics and diversity in artificial intelligence policies, strate-
gies and initiatives. AI and Ethics, 3(4), 1095–1115. doi:10.1007/s43681-022-00218-9 PMID:36246014
Roll, I., & Wylie, R. (2016). Evolution and revolution in artificial intelligence in education. International
Journal of Artificial Intelligence in Education, 26(2), 582–599. doi:10.1007/s40593-016-0110-3
Salas‐Pilco, S. Z., Xiao, K., & Hu, X. (2022). Artificial intelligence and learning analytics in teacher
education: A systematic review. Education Sciences, 12(8), 569. doi:10.3390/educsci12080569
Seo, K., Tang, J., Roll, I., Fels, S., & Yoon, D. (2021). The impact of artificial intelligence on learner–
instructor interaction in online learning. International Journal of Educational Technology in Higher
Education, 18(1), 54. Advance online publication. doi:10.1186/s41239-021-00292-9 PMID:34778540
Singha, R., & Singha, S. (2023a). Economic sustainability, mindfulness, and diversity in the age of ar-
tificial intelligence and machine learning. In P. Raj, P. B. Soundarabai, & P. Augustine (Eds.), Machine
Intelligence: Computer Vision and Natural Language Processing (pp. 273–285). Taylor & Francis Group.
doi:10.1201/9781003424550-15
Singha, S., & Singha, R. (2023). Protecting data and privacy: Cloud-based solutions for intelligent trans-
portation applications. Scalable Computing: Practice and Experience, 24(3), 257–276. doi:10.12694/
scpe.v24i3.2381

40

Enhancing Language Teaching Materials Through Artificial Intelligence

Sweller, J. (2012). Cognitive load theory. In Springer eBooks (pp. 601–605). doi:10.1007/978-1-4419-
1428-6_446
Tafazoli, D., María, E. G., & Abril, C. H. (2019). Intelligent language tutoring system. International
Journal of Information and Communication Technology Education, 15(3), 60–74. doi:10.4018/IJI-
CTE.2019070105
Tan, S. (2023). Harnessing artificial intelligence for innovation in education. In Learning Intelligence (pp.
335–363). Innovative and Digital Transformative Learning Strategies. doi:10.1007/978-981-19-9201-8_8
Towle, B., & Halm, M. J. (2006). Designing adaptive learning environments with learning design. In
Springer eBooks (pp. 215–226). doi:10.1007/3-540-27360-3_12
Xi, X. (2010). Automated scoring and feedback systems: Where are we and where are we heading?
Language Testing, 27(3), 291–300. doi:10.1177/0265532210364643
Yeşilyurt, Y. E. (2023). AI-enabled assessment and feedback mechanisms for language learning. In Ad-
vances in Educational Technologies and Instructional Design book series (pp. 25–43). doi:10.4018/978-
1-6684-9893-4.ch002
Zhao, J., Wu, M., Zhou, L., Wang, X., & Jia, J. (2022). Cognitive psychology-based artificial intel-
ligence review. Frontiers in Neuroscience, 16, 1024316. Advance online publication. doi:10.3389/
fnins.2022.1024316 PMID:36278021
Zhu, Y. (2020). The application of artificial intelligence in foreign language teaching. 2020 International
Conference on Artificial Intelligence and Education (ICAIE). 10.1109/ICAIE50891.2020.00024
Zou, B., Guan, X., Shao, Y., & Chen, P. (2023). Supporting speaking practice by social network-based
interaction in artificial intelligence (ai)-assisted language learning. Sustainability (Basel), 15(4), 2872.
doi:10.3390/su15042872

KEY TERMS AND DEFINITIONS

Adaptive Assessment: Evaluation methods that dynamically adapt in response to the performance
of individual learners, utilizing artificial intelligence to deliver immediate feedback and streamline
language assessment procedures.
AI (Artificial Intelligence): An intelligent behaviour simulation technological system that enhances
personalized learning experiences and adaptive assessment in language education.
Challenges: The integration of AI into language education is accompanied by various hindrances
and obstacles, including but not limited to ethical concerns, biases, and privacy considerations, all of
which necessitate a cautious approach when navigating.
Integration: Learning outcomes can be improved by integrating artificial intelligence (AI) into
language education, which entails a smooth synergy between conventional pedagogical approaches and
technological systems.
Language Acquisition: Language learning necessitates the development of linguistic proficiency
and cultural awareness, which are frequently improved by AI-integrated instructional materials.

41

Enhancing Language Teaching Materials Through Artificial Intelligence

Language Teaching Materials: Educational materials specifically developed to support the progress
of language learners, including textbooks, multimedia materials, and interactive tools that aid in the
acquisition of the target language.
Personalized Learning: Optimizing language acquisition outcomes by customizing educational
experiences to suit the needs, preferences, and proficiency levels of individual learners, frequently with
the assistance of AI.

42
43

Chapter 3
The Reality of Artificiality:
The Impact of Artificial Intelligence
on Language and Culture Course
Assessments and Rubrics

Teresa Lobalsamo
https://orcid.org/0009-0008-6807-4862
University of Toronto Mississauga, Canada

Dellannia Segreti
https://orcid.org/0009-0007-7320-9808
University of Toronto Mississauga, Canada

Mohammad J. Jamali
University of Toronto, Canada

Sylvia Gaspari
University of Toronto, Canada

ABSTRACT
As artificial intelligence (AI) continues to increase its presence and accessibility within education, the need
to address AI’s impact on assignment design and the production of original coursework is heightened.
Within the context of an undergraduate language and culture course, this chapter thus offers reflections
on the integration of AI tools and their effect on shaping assessment methods. The authors also highlight
that there indeed remains a great need for continued research in the realm of AI and education going
forward, especially where enhanced AI-detection technologies, institutional policies, academic rigour,
and learner expressiveness are concerned.

DOI: 10.4018/979-8-3693-0872-1.ch003

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

The Reality of Artificiality

INTRODUCTION

Artificial Intelligence (AI) has been in steady development in information technology and other indus-
try sectors for several decades. However, recent developments in Generative AI and the unprecedented
accessibility of tools such as ChatGPT have heightened the need for critical discussion on AI and the
ways in which they will inevitably affect the education sector. In an effort to contribute to this evolving
discussion, this chapter reflects on the recent implementation of Generative AI on methods of assess-
ments assigned and completed for an undergraduate Italian Language and Culture course (University of
Toronto Mississauga). The course is structured around 12 thematic units; weekly to bi-weekly assess-
ments chart learning progress through formative pieces of work related to each [unit]. For students who
undertake the course to fulfill an Italian language requirement as part of their program of study, select
assignments are completed in Italian. By outlining how generative AI tools were integrated within the
context of Italian Language and Culture, we will consider how modifications made to the course’s syl-
labus, assessments, and rubrics reveal new opportunities and potential pitfalls that instructors will want
to consider--and quickly--so that course delivery, academic rigour and integrity can remain impactful in
this new reality. In sharing our preliminary reflections, we hope to offer some pathways toward navigat-
ing such technological advancements, today and in future.

CURRENT DEBATE SURROUNDING AI

Current hesitations around the use of AI in education are simply the next phase of a decades-long
discussion on the feasibility and necessity of bringing new technologies into the classroom which, in
recent years, has also engaged topics such as text messaging (Carrington, 2005) and machine translation
(Urlaub & Dessein, 2022).
With regards to the language classroom, Urlaub and Dessein (2022) diffuse the perceived disruption
caused by machine translation, such as Google Translate, to the acquisition of language-learning outcomes
by drawing an intriguing comparison with pocket calculators in Mathematics classrooms, which became
a widespread practice in schools only once the S.A.T. permitted their use in 1994. Initial debates in the
1970s hinged upon whether the availability of pocket calculators in the mathematics classroom would lead
to a loss of basic arithmetic skills among students. Urlaub and Dessein (2022) point to a shift in instructor
perception of the pocket calculator, as it went from being considered an impediment to a learning tool
that could optimize learning outcomes. Analogously, they argue that a targeted and thoughtful approach
toward machine translation in the language classroom could enhance learning outcomes. The prevailing
concern is that the frequent use of machine translation could prevent students from accumulating the
skills necessary to produce written communication in the target language without the support of aids
(51). Urlaub and Dessein (2022) admit that there is a real danger that tools such as Google Translate
can contribute to a reductionistic perception of language and language learning. They underscore that
if language proficiency is “treated as a tool, it reduces human beings to speakers exchanging messages
in crude manners that are agnostic of the sociocultural embeddedness of message and speaker” (p. 57).
Naturally, this concern has implications for oral and written communication across academic disciplines.
However, the possibility that communication in a foreign language could be reduced to mere “transla-
tion” particularly stands out in the language classroom. In order to combat this outcome, Urlaub and
Dessein (2022) argue that we must understand language proficiency as a nuanced and context-sensitive

44

The Reality of Artificiality

form of communication that reflects and represents the individual within society. Moreover, machine
translations’ inability to harness cultural nuance (through, for example, idiomatic expressions)1 in fact
limits the depths to which it is beneficial in achieving language competence.
Rather than fleeing from this danger, Urlaub and Dessein (2022) recommend introducing tools such
as Google Translate into the classroom in a thoughtful and goal-oriented way. They cite several studies
from the past two decades in which students have been observed to “develop higher levels of linguistic
awareness through the use of online translators by using the technology to elicit feedback on both their
written and spoken language” (p. 51). The authors also suggest that prohibiting Google Translate in
the classroom will not impede the “proliferation of increasingly sophisticated online translators in the
‘real world’ and the impact of this technology on human communicative behaviour in general and our
students’ and society’s perceptions of the purpose of language education” (p. 53). They propose that
language instructors instead consider the gradual integration of machine translators into the classroom
by designing tasks that (1) require students to recognize instances where the use of online translation
tools can enhance the learning process; (2) train students to use these machine translators as study aids
rather than a default “go-to” resource for completing assignments (Urlaub & Dessein, 2022, p. 54).
There remains another major hurdle to overcome with regards to intentionally using Large Language
Model-based tools such as Google Translate in the classroom: the difficulty in implementing a systemic
approach to their integration at all educational levels (Urlaub & Dessein, 2022). Urlaub and Dessein
(2022) highlight the importance of sharing a consensus around how tools such as chatbots can and should
be used at all teaching, learning, and assessment levels; otherwise, without an overarching model for
their integration, such tools will not be maximized beyond their dictionary-like uses.
While the pocket calculator and Google Translate present unique challenges to overcome for educa-
tors, the most challenging of any new technology yet is undoubtedly the introduction of LLM-based
chatbots. Chatbots like ChatGPT, Bard, and Ernie are conversational artificial intelligence models de-
signed to generate text that resembles natural, human-like writing based on prompts they receive from
the user. As their utilization has increased, these tools have exponentially augmented the importance of
refining our teaching, learning, and assessment practices. In an opinion piece published in June 2023,
Hao Yu, a Professor in the Faculty of Education at the Shaanxi Normal University (Xi’an, Shaanxi,
China), debates the pros and cons of banning ChatGPT from academia, whether it is a useful approach,
and whether it is even possible to eliminate it at this stage. Based on recent surveys, Hao Yu finds that a
growing number of students in American colleges are using ChatGPT for a variety of purposes, such as
to complete homework tasks (89% of students in American colleges), write papers (53%), exams (48%),
and generate essay outlines (22%) (McGee, 2023). Major concerns surround student use of LLMs in the
completion of exams and other academic tasks meant to function as objective evaluations of students’
understanding of the material taught in class (Yu, 2023). Similarly, students may depend on AI in lieu
of engaging in critical thinking on assignments, negatively impacting their ability to actively explore,
verify, and summarize sources (Yu, 2023). Further concerns are expressed regarding the knowledge
provided by these tools, as it is viewed by many educators as superficial and mechanized, “which cannot
help students deeply understand the surrounding world and operate effectively in it” (Yu, 2023, p. 7). In
addition, the use of ChatGPT has also raised ethical and legal questions. Many educators view its use in
examinations and written assignments as academic plagiarism. Since the very function of these LLMs is
based on data from sources available on the Internet, their usage in an academic setting prompts further
inquiry into the nature of intellectual theft and artistic and academic integrity (Kitamura, 2023). These

45

The Reality of Artificiality

concerns lead scholars and educators to the same question: How should we view the use of AI in the
classroom? Many scholars tread a fine line between acceptance of and weariness towards this technology.
Maureen Walsh brings an optimistic perspective to the potential benefit of using tools such as Chat-
GPT in the classroom. She describes how the definition of literacy has changed from merely reading and
writing to now encompassing a broad range of skills that students hone by using technology regularly
outside of school (Walsh, 2017). For Walsh (2017), the changing definition of literacy goes together with
many students developing a higher level of digital literacy outside the classroom. Technology has changed
the nature of communication, directly impacting the definition of “literacy,” especially as it pertains to
the classroom. Nowadays, students require a repertoire of “print and digital literacy practices for their
future workplace and life” (Walsh, 2017, p. 21). Traditional writing assignments (on paper) have given
way to multi-modal approaches - students can still incorporate traditional skills such as style, vocabulary,
and sentence structure, but this is now paired with the added potential offered by digital media (Walsh,
2017). Literacy as a multimodal skill also requires that students be given multiple literacies to be able
to work with different forms of media and curriculum content; as Walsh emphasizes, digital technology
can be used as an inclusive tool in developing literacy (Walsh, 2017).
It has also been argued that the decision by institutions and instructors to ignore or dismiss AI inad-
vertently creates space for its unwarranted use, which could be a detriment to student learning. On the
topic of AI regulation for classroom assignments, Aikens and Kuo (2023) and Fulford (2023) both point
to the fact that, like it or not, AI has arrived, and educators need to find a way to cope with it because
the technology is here to stay. Aikens and Kuo interviewed a small sample of 30 students at an unnamed
private university who used LLMs such as ChatGPT in their academic work. Their research revealed that
an ever-growing number of students are “turning to AI as a first resort for almost everything.” Students
believe that AI provides them with better tools than traditional learning for their postgraduate careers,
and they tend to value AI-aware class environments that permit the use of these tools more than those
that do not. Especially in mathematical and statistical fields, students “praised the democratizing effect
of on-call and accurate code checking as a “game-changer,” with ChatGPT being a nimbler learning
resource than static course materials or discussion boards” (Aikens & Kuo, 2023, para. 8). Aikens and
Kuo conclude that while “AI by no means obviates the need for human help - which students said was
still situationally preferable - its availability seems a helpful antidote to last-minute despair, especially
during exam periods, when tutoring appointments may be scarce” (Aikens & Kuo, 2023, para. 9).
Fulford (2023) further suggests that, by not incorporating AI into their classroom or intentionally
using ChatGPT on assignment design, teachers will spend an abundance of their time trying to detect
cheating and uninvited AI usage instead of focusing on their students’ learning progress and knowledge
gains. He argues that perspectives surrounding the use of AI must necessarily shift away from assump-
tions of plagiarism. Instead, educators should focus on specific learning objectives related to reading and
writing assessments (Fulford, 2023). In his own experience, time spent determining whether students
used AI ends up taking over the grading process instead of looking at what the students are writing.
Fulford (2023) shares that he finally began to look at the ideas the students were presenting as opposed
to how much AI they were using, which, in turn, proved to be an effective detection method due to the
generally poor quality of AI writing. This shift in perception of the use of AI allowed Fulford to focus
on creativity in research and writing more than simply regurgitating ideas. Further, he is confident
that, if the technology is employed appropriately, more space will be left open for students to engage in
creative thinking. With this in mind, some scholars see the possibility for tools like ChatGPT to reduce
researchers’ workloads, allowing them to devote their time and energy to conducting new experiments

46

The Reality of Artificiality

(Fulford, 2023). However, van Dis et al. (2023) acknowledge that AI indeed faces many obstacles that
need to be addressed, namely issues of bias, provenance, and accuracy, before it can be implemented
and accepted fully in the workplace and, inevitably, in the classroom as well.
While the AI debate in the education sector and other fields is ongoing, the growing body of literature
already available provides a valuable foundation for beginning to incorporate AI into the classroom. In
the sections that follow, we will consider how the ongoing debate has supported the Humanities faculty
in navigating the abrupt introduction of AI technologies into Higher Education and guided a successful
implementation of AI into the language and culture course in focus here.

CONSIDERATIONS ON INSTITUTIONAL POLICY

Technological advancements should continue to be approached as an opportunity for education administra-

tors to reflect upon and audit instructor teaching practices and student learning behaviours to ensure that
academic integrity, learning outcomes, and institutional visions are in seamless alignment. Growth is an
essential component of education. As practices are revisited and revised to respond to societal changes
and needs, pedagogies are improved, and students’ learning experiences are enhanced.
The inclusion of clear institutional policies where AI use is concerned can provide valuable support
to students and teachers alike. Formal policies promote a standardized approach to the integration of AI
in education, which can, in turn, create opportunities for students to utilize it properly and effectively
across their university experience. Many post-secondary institutions have left the decision to allow
the use of ChatGPT in the classroom to departments and their course instructors. Institutional policies
do, however, differ from one university to another. In North America, the Higher Education sector has
spent the last 12 months pre-empting the potential impact that this technology may have on teaching
and learning, developing resources and policies on how to navigate student engagement with generative
AI, particularly concerning academic integrity at course (Indiana University, 2023; Harvard Business
School, 2023), program (University of British Columbia, 2023), or university (University of Toronto,
2023; University of Wisconsin–Madison, 2023) levels. While one (University of Toronto) gives each
instructor the autonomy to identify authorized and unauthorized aids for their specific course, it also
guides the effort by providing suggested wording for course syllabi. Similarly, the University of Hong
Kong requires students to obtain written permission from their professors to use AI in their coursework;
otherwise, its use will be considered plagiarism.2
To get ahead of the inevitable increase in student engagement with and reliance upon AI, several
institutions have indeed started to publish best practices and guidelines for instructors and students
engaging with AI in the classroom. We highlight, in particular, the University of Toronto’s resource on
“Using ChatGPT or other generative AI tools on a marked assessment,” which provides students with
detailed scenarios of and strategies around AI use and potential consequences associated with using it
outside of suggested boundaries (University of Toronto, n.d.b). McGill University Library’s guide on
AI literacy provides students with the foundational knowledge needed to understand the complexity of
AI and provides them with tangible tests (such as the ROBOT test) to evaluate the legitimacy of the
produced results (McGill Library, 2023). The University of British Columbia (UBC, n.d.) shares Genera-
tive AI Resources from various sources that aim to provide education surrounding effective AI use in a
variety of contexts. With clearly stipulated policies and supportive resources in place, and by engaging

47

The Reality of Artificiality

in open conversations around the ethical use of AI in academia, institutions foster a strong commitment
to academic responsibility and integrity while highlighting boundaries, insights, and acceptable uses.

AI’S ACKNOWLEDGEMENT AND INCORPORATION INTO AN

UNDERGRADUATE LANGUAGE AND CULTURE COURSE

In an effort to analyze the role that AI can play in the language-culture classroom, we will now examine a
12-week undergraduate course offered at the University of Toronto Mississauga. The course is unique in
the way that it brings together students from various disciplines, bridging academic backgrounds by being
taught in English and providing all members of the class, regardless of program of study, with opportunities
to engage in multimodal and experiential learning activities in order to work towards achieving a series
of learning outcomes. All learners acquire and recognize the language of Italian cultural currency either
in the classroom or through experiential learning, thereby connecting how and why the practical learning
experience applies to course content; they gain an appreciation of the Italian language and culture in
authentic environments and, overall, seek to recognize the relevance of Italian culture. More specifically,
students are well positioned to assess how history has shaped various aspects of culture - art, fashion,
cinema, cuisine, and how each of those intersects with politics, socio-economics, economics, migration,
gender, and self-expression. Learners also trace the impact of Italian immigration and the development
of diaspora in international contexts and are encouraged to discover the links between course content
and their own histories, cultures, and identities. In order to develop such outcomes and to help students
identify course-based connections for in-class discussions and as features of their assignment submis-
sions, Experiential Learning is a cornerstone of this course’s pedagogy. As such, numerous immersive
opportunities are available to students, including local and international field trips and virtual walking
tours of cultural heritage sites. For students who are part of an Italian-Language Program (Minor, Major,
or Specialist), language proficiency ranges from beginner to beginner-intermediate, having undertaken
one year of formal academic preparation in the language of study, and they may opt to use the course
to fulfill the Program’s language requirements. For Italian-program students, then, the course provides
them with opportunities to employ spoken and written Italian with ease, spontaneity, and organically in
both personal and professional contexts; they also recognize the relevance and inextricable links between
the Italian language and culture.
Since the inception of the course in 2014, assignments have been intentionally curated to prompt
students to extend their learning beyond the classroom, fostering their critical thinking skills and self-
reflection to personally connect their lived experiences with course concepts in the language - Italian or
English - best suited to their respective program. In particular, methods of assessment centre on weekly
and bi-weekly assignments which incorporate logic-, fact-, and opinion-based (personal) reflections
into multiple choice, true/false, written and/or recorded responses. Each assignment is intentionally
designed and structured in its multimodal format to reflect a variety of learning styles and to maximize
course goals, learning outcomes, and student success. Before the widespread availability of AI and its
capabilities were readily known, student engagement with lecture content and experiential learning op-
portunities was evaluated mainly through written and/or audiovisual, essay-style assignments that sought
a balance of personal anecdotes and academic reflections on scholarly and popular articles. Responses
were evaluated according to a standardized course rubric, composed in alignment with the institution’s
grading scheme, that considered the following three key areas of assessment: (1) content, (2) sources, (3)

48

The Reality of Artificiality

language, organization, style. Specifically, coursework content was assessed based on its quality and the
extent to which it addressed all aspects of the assignment question(s), whether it contained meaningful
and detailed personal and academic reflections, and whether it was connected to the course’s learning
objectives. “Sources” were evaluated based on, for example, their relevance to the topic at the core of the
paper and the judiciousness students exercised when citing from such sources. “Language, organization,
style” looked at, among other factors, the overall progression or sequence of arguments and the clarity
of the writing style employed. The rubric and its adjacent criteria were in place to support students in
approaching their work holistically and in a manner that encouraged them to draw close connections to
their learning experiences, and they [the rubric and criteria] ensured that as instructors and assistants
graded such work, we approached evaluations with the same goals in mind.
The necessary decision to incorporate AI into course assessments came ahead of the Summer
(May-June) 2023 iteration of the course when generative tools, such as ChatGPT, were quickly gaining
momentum. Based on institutional policies released at the same time (May 2023), adjustments were
made to coursework expectations and rubrics accordingly. The University presented instructors with
descriptions to include in course syllabi according to how they intended to engage with Generative AI
tools in their courses: (1) Can Use Generative AI Tools, (2) Can Use Generative AI in Certain Instances
or Specific Ways, and (3) Cannot Use Generative AI (“U of T Syllabus Language - Use of Generative AI
in Assignments,” Spring/Summer 2023). For courses in which Generative AI use would be permitted--
that is, (1) and (2)--the description acknowledged and outlined flexible parameters to promote an open
dialogue around ethical AI use and its capabilities for learning. The language-culture course, in particular,
opted to use descriptions (1) and (2), permitting students to use AI for specific, reflective written and/
or audio-visual submissions. Students were also invited to submit an optional “AI Appendix” with their
assignments outlining if and how they had used Generative AI tools in completing the assessment and
including a screenshot of the generated response, if applicable. Furthermore, the course’s experiential
learning opportunities and accompanying reflection questions lent themselves well to limiting the presence
of AI use, given that assessments emphasized personal experiences and required references from select
sources. The flexibility of multimodal submissions and the personal nature of the assignments left us
cautiously optimistic that with a few tweaks, such as adding the AI Appendix and an increased emphasis
in the rubric on students’ use of explicit sources, we might outwit and stave off any unwarranted AI uses.
AI’s adoption into the course for Summer 2023 was slow as Generative AI had only recently made
an incursion into academia. The course’s stance on AI use acknowledged its presence and welcomed it
in ways that did not impede or infiltrate students’ personal and academic reflections while also operat-
ing on an expectation of student understanding and honesty. Students were advised against using AI for
large components of their coursework submissions, and the importance of ethical AI use was stressed.
Authentic academic processes and benefits of self-generated work were shared, and students were asked
to confirm their understanding of the information and tools they were given. During the Summer course
offering, only 1 of 115 students used AI on 5 of 7 written reflections. The student’s use of AI was limited
to including 1-2 generated paragraphs on each submission, but the grading team noted that personal
contributions were either missing or minimal. Beyond online dictionaries, students specifically enrolled
in an Italian program did not rely on a generative AI tool to complete their assignments.
As generative AI tools grew in sophistication3 and their implications continued to dominate public
discourse over the summer, this group of instructors and assistants was keenly sensitive to the fact that
the course would need to re-address appropriate AI usage ahead of its Fall 2023 offering.4 The AI Ap-
pendix was made into a mandatory declaration that all students appended to each assignment, lest their

49

The Reality of Artificiality

submission be considered incomplete and their mark temporarily withheld. Taking into consideration the
data collected during the Summer 2023 term and the limited reliability of self-reported data (Mensah et
al., 2018; Yang et al., 2017), it was apparent that this declaration, whether optional or required, would
not be enough to sustain academic rigour throughout the Fall iteration of the course. It was necessary
to make further modifications to course assignments and rubrics.
The teaching team continued to refine its approach to embedding AI into coursework. While detecting
AI usage is becoming easier, it is not yet an exact science, and, importantly, there are ethical and privacy
issues concerning detection software. Our practices are, therefore, in part informed by Fulford (2023),
who argues that AI use must not be treated as plagiarism but as an opportunity for assignment reform,
which begins with explicitly drawing the line between using AI as a research and writing aid rather than
a cheating tool. Select assessments were designed to encourage learners to engage firsthand with AI
tools and assess the language of AI-generated responses by judging the accuracy of the grammatical
concepts employed, vocabulary appropriateness, and the general tone of the Italian produced. Students
were also invited to adjudicate the quality of the content generated by corroborating or debunking its
claims with information procured from primary and secondary sources (e.g., scholarly articles and
course textbooks) and personal anecdotes. Reflective assignments, in other words, necessarily under-
went a series of modifications, from asking students to draw tighter connections between their in-class
learning, accompanying readings, and course objectives to asking students to evaluate the accuracy, or
otherwise, of AI-generated responses. Entirely new assessments were also created that did not require
and/or would not be well-served by AI tools, leveraging multimodal frameworks such as live discus-
sions, improvised elevator-pitch-style presentations, and audiovisual social media posts. This approach
has the added benefit of reducing the gap between the tools available to some students by bringing a
wide variety of multimodal literacy tools to classroom learning and practice and supporting creative
reflections on student participation in experiential learning opportunities. We also harkened back, on
some assignments, to traditional multiple choice and true or false-style questions.
Within the updated rubric, parameters for evaluating content were expanded to include further con-
siderations on originality and innovation, including whether the response offered new interpretations
of primary and secondary sources. As both a deterrent for a heavy reliance on AI and a way to better
evaluate the students and not ChatGPT, the rubric considered how much and for what purposes AI was
employed. Further, the rubric stated that responses should be well-substantiated and demonstrate suf-
ficient depth and innovation with minimal to no use of AI. The rubric’s criteria for sources assessed
their quality and the extent to which referenced materials were used accurately and effectively. Evalu-
ations of language, organization, and style continued to esteem work that was presented diligently and
which showed evidence of self-editing prior to submitting a final copy of any coursework, including the
extent to which learners exercised care in elevating the language produced by AI and transforming it
into a clearer, more concise response. For Italian-program students specifically, a language analysis was
embedded into their assignment which asked them to compare the language level of the AI-generated
answer against their own preparation by identifying, for example, the verb tenses, syntactic structures,
and academic conjunctions present in the response.

50

The Reality of Artificiality

REFLECTING ON THE USE OF AI IN COURSEWORK DESIGN

In the Fall 2023 term, we noted a gradual increase in the number of students who confirmed using AI.
The first two assignments had an identical number of confirmed generative AI uses; however, starting
from Assignment 3 onward, the number significantly rose, and by Assignment 5, the number had risen by
100% (compared to Assignment 1). This growth can be attributed to the fact that course content became
more complex as the term progressed and that, perhaps, external factors, such as elevated amounts of
work in other courses, prompted learners to seek out ChatGPT as an aid more frequently than before.
In most instances, students who answered positively to the AI Appendix shared that they used such
systems to brush up on their original composition’s language (Italian or English) or to provide correct
formatting for in-text citations and reference lists. Using AI tools also proved advantageous for some
students who, for example, benefitted from it to gain feedback on their composition skills. Moreover,
given how these platforms tend to generate responses by pulling information from the vast amounts of
data accessible online, they provided strong starting points for generating ideas into which students then
investigated topics further on their own. This allowed the students to engage in fact-checking exercises,
upon which they elaborated their additional research findings. Other uses, however, did seem to bring
with them a few caveats, namely an over-reliance on the AI system, which impeded students from de-
veloping self-directed learning techniques, critical thinking, and research skills.
Among students who acknowledged at least some measure of reliance on generative AI in their assign-
ments, submissions, by and large, continued to leave out the personal reflections outlined and expected
by the assessment questions and adjacent rubrics. In extreme cases of an over-reliance on technology,
students turned to ChatGPT for assignments that sought to connect their personal lives and/or experiences
on field trips to topics in the course. The chatbot provided responses written in the first person, but again,
they contained no personal opinions. AI-generated responses also frequently exhibited an unnatural use
of the English or Italian language. In the case of Italian, specifically, the language presented complex
grammatical structures and advanced vocabulary beyond students’ beginner-intermediate preparation.
Moreover, the ability to compose complex texts with advanced words is different across all languages, as
AI machines rely on the number of tokens available to them in a given language. Similar to other LLMs,
ChatGPT is trained on a mix of data from multiple languages; however, since the vast majority of data to
which they have access is in English, generative AI tools are not, as of now, able to adequately evaluate
texts that exhibit complex language proficiency (Lai et al., 2023) in most languages outside of English.
Therefore, the community lacks a comprehensive, public, and independent evaluation of ChatGPT in
various non-English languages for diverse natural-language processing tasks to provide proper perspec-
tives for this research application. What the authors have noted to date is that due to this inefficiency
with translation and multilingual data, some students resorted to using multiple tools to translate into
English the prompt they wanted to give the AI machine and then, at most, paraphrased the response
received without sufficiently editing the entire response. Students sometimes used these tools multiple
times for one assignment to achieve their desired content. For instance, for a text that was to be written
in Italian, a student declared having (1) used Google Translate to translate their prompt from Mandarin
(native language) to English, (2) fed the English translation of the prompt to ChatGPT, (3) used Google
Translate again to translate ChatGPT’s response to Italian (target language) in an effort to arrive at a
text with minimal errors. Unsurprisingly, this machine-driven game of broken telephone resulted in the
final text exhibiting language structures beyond the expected level of proficiency and containing errors
in otherwise simple grammatical concepts.

51

The Reality of Artificiality

A second significant caveat to AI usage is the potential hindrance it may cause to developing research
skills. When students excessively rely on AI systems for information retrieval and quality control, they
may miss the opportunity to develop and practice the critical thinking skills required for research profi-
ciency. As with all university courses, students were provided with the course syllabus at the beginning
of the term, and the instructor reviewed course expectations during the first lecture, one of which was
the exclusive use of APA style for reflective essays. To aid with citation style and formatting, students
also participated in research-related workshops on navigating online resources and where to find detailed
guides for the APA citation format. While most students effectively applied their workshop learnings
and online resources for sound research and to compose proper citations, there remained a few students
who continued to struggle with standardized APA guidelines and turned to AI tools to check the quality
of their citations for them. Unfortunately, in those instances, the AI system failed to provide the correct
formatting style, underscoring the importance of fostering a comprehensive understanding of citation
formats beyond automated tools and emphasizing the necessity to cross-verify one’s work against the
exemplars and guidelines provided in course materials.
The process of manually researching, critically evaluating, and synthesizing knowledge is integral
to fostering intellectual autonomy and analytical thinking. By delegating these tasks to AI systems, stu-
dents may miss the opportunity to develop a deeper understanding of their research subjects and refine
their academic productions. We observed that students who declared having used AI tools to paraphrase
paragraphs, which they themselves composed, to improve their language and style, or to make their
paragraphs more succinct in order to meet the required word count, are overly trusting of the chatbot’s
diligence and language skills. Thus, oftentimes, passages omitted a keyword or a critical component of
the original passage written by the student and left key words or phrases untranslated in instances where
those expressions were original and specific to lecture content. The capacity to critically evaluate and
rectify discrepancies in AI-generated content requires a foundational proficiency in writing and a keen
understanding of the subject matter. Indeed, this course permits the use of AI tools to support the refine-
ment of one’s work, but a combination of efforts - both human and technologically-generated - should
be employed if a response is to be optimized. To maximize the use of AI, the integration of technology
into the writing process should be a supplementary measure, complementing rather than replacing the
core skills that students possess.
As AI tools become more diverse and polyvalent in what content they can generate, older systems will
lose users. Regardless of the number of online dictionaries available, some students, particularly those
composing a text in their non-native language, tend to seek assistance from LLM-based translators like
Google Translate. The AI Appendix exercise in this course revealed that, in some instances, students
used systems such as ChatGPT to seek the meaning of words or, at other times, ask for synonyms and
related terminology of words that they intended to use in their long answers. When it comes to language,
be it looking for a simple word or paraphrasing a passage, AI tools are faced with the shortcoming that
they cannot accurately assess the context in which words appear, as their LLMs are served by what is
available in their databases and elsewhere on the Internet. Furthermore, texts generated by these systems
do not (and cannot) anticipate the user’s language level. Therefore, it is relatively easy to detect whether
a student who does not possess advanced knowledge of the language—Italian, in our case—has used
generative AI tools in their compositions due to abrupt shifts in language complexity, the use of ad-
vanced vocabulary, or the incorporation of complex syntactic structures that deviate from the student’s
beginner-intermediate language proficiency.

52

The Reality of Artificiality

When used effectively, however, AI machines can be valuable learning tools. If a student has already
developed composition skills and knowledge of grammar, then AI tools, such as Grammarly for learners
completing their work in English, or Word Reference or Google Translate for Italian program students,
can be used as time-efficient mechanisms in place to provide feedback on grammar, awkward phrasing,
verbosity, and overall coherence in a text. In other words, again, users must be encouraged to review
AI’s suggestions and revise their writing as necessary. With the help of AI tools, the student can identify
their weaknesses, if any, and, through suggested instructions provided by the software, identify ways to
improve their writing skills for future assignments. In addition, the availability of such tools can help the
student to foster a habit of revision and editing, thereby elevating the quality of the work submitted, as
working through feedback received from AI tools mirrors the real-life iterative learning process wherein
professional writers will undergo multiple rounds of editing to refine their composition. The feedback
and editing loop can teach students that it is okay to make mistakes, helping them to develop autonomy in
their writing and self-correct their future compositions, according to the feedback received from the AI.

FUTURE CONSIDERATIONS

For the Fall 2023 iteration of the course in focus, the teaching team was able to leverage data collected
during its Summer 2023 offering to improve the implementation of AI tools. Moving forward, the teach-
ing team will continue to improve this aspect of the course and engage in important discussions on the
role of AI in education. Reflecting on the efforts made over the past two terms, the AI Appendix will be
further amended to include a space in which students can describe their thoughts on AI (in relation to,
for example, its reliability and how it affects their claim to intellectual property), assignment rubrics will
undergo additional updates that directly address and account for the use of AI tools, and select future
assessments will ask learners to address in more depth the language and content of an AI-generated
response, at times provided for them and at other times produced by their prompts. Specifically, stu-
dents will continue to analyze a response’s accuracy, corroborating and/or debunking, as needed and
as determined by the students themselves, any AI-generated information with the support of different
pedagogical materials (e.g. scholarly articles, the course textbook) and personal anecdotes. We will
also continue to create new assessments that do not require and/or would not benefit from AI use. Such
advancements in the course’s assessment methods require that the capabilities of AI be explored more
and understood better by the teaching team. Ultimately, we will reimagine assessments at their core to
more precisely centre the learner and course concepts, further calling upon students’ active engagement
in all aspects of the course.
In terms of large language models, specifically within this language-culture course, we noted that
students spent significant time using copy-and-paste functions from Google Translate to adopt the vo-
cabulary and grammatical structures necessary to continue their learning. In future studies, we intend to
work with students to parse out the differences between AI tools (e.g. ChatGPT vs. Google Translate)
to reach a common understanding of the use and impact on learning of various technologies. Follow-
ing Bonner et al. (2023), we will redesign methods of assessment in ways that call upon generative AI
to facilitate certain dimensions of language teaching and learning, such as using it to reinterpret texts,
to write using level-appropriate grammar and vocabulary, including academic conjunctions, idiomatic
expressions, etc. In sum, we will develop assessments that consider the language level of each learner
to co-construct appropriate AI usages and better support students’ language-learning journeys.

53

The Reality of Artificiality

CONCLUSION

In this self-reflective effort, we highlight the importance of constantly evolving our assessment design
practices and maintaining a good grasp, as instructors, of the capabilities and limitations of generative
AI. For all learners, coursework perhaps fell short of encouraging autonomous critical production, and,
for Italian-program students specifically, they were perhaps insufficiently structured around the language
abilities and tools with which learners have the most practice. Nonetheless, it is the ongoing work of any
instructor to try to be ahead of the technological curve as much as possible and/or address the inevitable
changes it actualizes in a timely fashion. With that, assignment design gaps will be considered and re-
worked into new assessments that will be first piloted among focus groups before their implementation
in future course iterations.
The introduction of generative AI into various contexts has impacted education systems worldwide,
and it is an important leap forward in technological advancements. AI will inevitably continue to grow
and increase its presence in various contexts, but in our course alone, we did not consider its employ-
ment to have drastically improved student performance. The skills students bring to the classroom, and
the knowledge gains they achieve on their own far surpass the production capabilities of ChatGPT.
When AI-produced responses are correctly cited, we may see the fruits of an effective collaboration
if instructors and students utilize AI as a tool to support learning in a way that does not override the
human element and contribution. In that case, AI can allow us all to promote and engage with course
concepts differently and develop new skills. To emphasize the inevitable interconnectivity of human
and machine future, we end this chapter in collaboration with ChatGPT. Prompt: “How should a chapter
on ‘The Reality of Artificiality: Artificial Intelligence in the Language-Culture Classroom’ conclude?”
Generated Response: In conclusion, the integration of artificial intelligence into the cultural classroom
is a multi-faceted journey that holds both promises and challenges. As we navigate this intersection of
technology and education, it becomes crucial to foster a balanced approach that leverages AI’s capabilities
while preserving the essential human elements of cultural competence, understanding, and interpreta-
tion. In essence, the convergence of artificial intelligence and language-cultural education offers an
opportunity for innovation, collaboration, and the cultivation of a global perspective. By navigating the
challenges thoughtfully and ethically, we can pave the way for a future where AI contributes positively
to the classroom, enhancing our understanding of diverse societies and fostering a more interconnected
world. (Paraphrased by the authors; response curated by ChatGPT, 2023a)

REFERENCES

Academic Integrity at UBC. (2023). CHATGPT Q&A. https://academicintegrity.ubc.ca/chatgpt-faq/

Aikins, R., & Kuo, A. (2023). What Students Said About the Spring of ChatGPT. Inside Higher Ed. https://
www.insidehighered.com/opinion/views/2023/09/07/what-students-said-about-spring-chatgpt-opinion?fb
clid=IwAR0vUM4HY5ideFrvGVABp2sz8MZGuzEss4EH-YiXtaUZZ1_UsZA0xKar8kk_aem_AaflEki-
AJcqt065wZj0M4DpuY4xmlkyGMnz6JBFWzOh8ZjZMuKvLmriGOa6Cr1rHDho&mibextid=Zxz2cZ
Azzo, A. (2023). Teaching Artificial Intelligence Literacy: ‘AI Is for Everyone.’ Artificial Intelligence
at Northwestern. https://ai.northwestern.edu/news-events/articles/2023/teaching-artificial-intelligence-
literacy-ai-is-for-everyone.html

54

The Reality of Artificiality

Bonner, E., Lege, R., & Frazier, E. (2023). Large Language Model-Based Artificial Intelligence in
the Language Classroom: Practical Ideas for Teaching. Teaching English with Technology, 2023(1).
doi:10.56297/BKAM1691/WIEO1749
Carrington, V. (2005). Txting: The end of civilization (again)? Cambridge Journal of Education, 35(2),
161–175. doi:10.1080/03057640500146799
Dreibelbis, E. (2023). Google Translate vs. ChatGPT: Which One Is the Best Language Translator? PC-
Mag UK. https://uk.pcmag.com/ai/147242/google-translate-vs-chatgpt-which-one-is-the-best-language-
translator#:~:text=AI Will Level Up Web Translation&text=But as we saw with,Translate’s capabilities
across the board.
Font de la Vall, R., González Araya, F. (2022). Exploring the Benefits and Challenges of AI-Language
Learning Tools. The International Journal of Social Sciences and Humanities Invention. doi:10.18535/
ijsshi/v10i01.02
Fulford, M. (2023). In the AI age, it’s time to change how we teach and grade writing: If we continue to
treat the use of AI as plagiarism, we’re doomed to fail. Here’s what we should be doing instead. Chalkbeat
Colorado. https://co.chalkbeat.org/2023/8/4/23820783/ai-chat-gpt-teaching-writing-grading?fbclid=Iw
AR2IuQa23f0M6dxmfay5nB_DlQgrJfMfPmm9hMbrWYVMW3WKAaruL3XrNKE
Harvard Business School. (2023). 2.1 Academic Standards of Conduct. Harvard Business School MBA.
https://www.hbs.edu/mba/handbook/standards-of-conduct/academic/Pages/chatgpt-and-ai.aspx
Indiana University Knowledge Base. (2023). Acceptable uses of generative AI services at IU. https://
kb.iu.edu/d/biit
Kitamura, F. C. (2023). ChatGPT Is Shaping the future of medical writing but still requires human judg-
ment. Radiology, 230171(2). Advance online publication. doi:10.1148/radiol.230171 PMID:36728749
Lai, V. D., Ngo, N. T., Veyseh, A. P. B., Man, H., Dernoncourt, F., Bui, T., & Nguyen, T. H. (2023).
ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multi-
lingual Learning. /arxiv.2304.05613 doi:10.18653/v1/2023.findings-emnlp.878
Lee, H., Ahn, H., Nguyen, T. G., Choi, S. M., & Kim, D. J. (2017). Comparing the Self-Report and Mea-
sured Smartphone Usage of College Students: A Pilot Study. Psychiatry Investigation, 14(2), 198–204.
doi:10.4306/pi.2017.14.2.198 PMID:28326119
Liang, W., Yuksekgonul, M., Mao, Y., Wu, E., & Zou, J. (2023). GPT detectors are biased against non-
native English writers. A Cell Press Journal, 4(7). doi:10.1016/j.patter.2023.100779
Lin, Z., Zhang, D., Tao, Q., Shi, D., Haffari, G., Wu, Q., He, M., & Ge, Z. (2023). Medical visual ques-
tion answering: A survey. Artificial Intelligence in Medicine, 143, 102611. Advance online publication.
doi:10.1016/j.artmed.2023.102611 PMID:37673579
McGee, R. W. (2023). Is Chat Gpt biased against conservatives? An empirical study. SSRN Electron.
J. doi:10.2139/ssrn.4359405
McGill Library. (2023). AI Literacy Guide. https://libraryguides.mcgill.ca/ai/literacy

55

The Reality of Artificiality

Mensah, C., Azila-Gbettor, E. M., & Asimah, V. (2018). Self-Reported Examination Cheating of Alumni
and Enrolled Students: Evidence from Ghana. Journal of Academic Ethics, 89-102. doi:10.1007/s10805-
017-9286-x
Mohan, D. D., Jawade, B., Setlur, S., & Govindaraju, V. (2023) Chapter 4 - Deep metric learning for
computer vision: A brief overview. Handbook of Statistics, 48, 59–79. doi:10.1016/bs.host.2023.01.003
OpenA. I. (2023a). ChatGPT. https://chat.openai.com/c/02af3cf9-1598-4fa1-882b-f543a27b21cc
Open, A. I. (2023b). ChatGPT - Release Notes. OpenAI. https://help.openai.com/en/articles/6825453-
chatgpt-release-notes
Schiff, D. (2021) Out of the laboratory and into the classroom: the future of artificial intelligence in
education. AI & Soc, 331–348. doi:10.1007/s00146-020-01033-8
Southern, M. G. (2023, February 8). Google Launches Ai-Powered Contextual Translations. Search
Engine Journal. https://www.searchenginejournal.com/google-launches-ai-powered-contextual-
translations/478863/#close
UBC. (n.d.). Generative AI Resources. The University of British Columbia: Generative AI. https://genai.
ubc.ca/resources/
UNESCO. (2023). UNESCO survey: Less than 10% of schools and universities have formal guidance
on AI. UNESCO. https://www.unesco.org/en/articles/unesco-survey-less-10-schools-and-universities-
have-formal-guidance-ai
University of Toronto. (n.d.a). ChatGPT and Generative AI in the Classroom. Office of the Vice-Provost,
Innovations in Undergraduate Education. https://www.viceprovostundergrad.utoronto.ca/strategic-
priorities/digital-learning/special-initiative-artificial-intelligence/
University of Toronto. (n.d.b). Using ChatGPT or Other Generative AI Tools on a Marked Assessment.
https://www.academicintegrity.utoronto.ca/perils-and-pitfalls/using-chatgpt-or-other-ai-tool-on-a-
marked-assessment/
Urlaub, P., & Dessein, E. (2022). From Disrupted Classrooms to Human-Machine Collaboration? The
Pocket Calculator, Google Translate, and the Future of Language Education. Journal of Linguistics and
Language Teaching, 14(1). Advance online publication. doi:10.5070/L214151790
UW–Madison Information Technology. (2023, August 24). Generative AI @ uw–madison: Use & poli-
cies. https://it.wisc.edu/generative-ai-uw-madison-use-policies/
van Dis, E. A., Bollen, J., Zuidema, W., van Rooij, R., & Bockting, C. L. (2023). ChatGPT: five priori-
ties for research. Nature, 614, 224–226. doi: m10.1038/d41586-023-00288-7
Walsh, M. (2017). Multiliteracies, Multimodality, New Literacies and…. What Do These Mean for
Literacy Education? Inclusive Principles and Practices in Literacy Education, 11, 19–33. doi:10.1108/
S1479-363620170000011002
Yu, H. (2023). Reflection on whether Chat GPT should be banned by academia from the perspective
of education and teaching. Frontiers in Psychology, 14, 1181712. doi:10.3389/fpsyg.2023.1181712
PMID:37325766

56

The Reality of Artificiality

KEY TERMS AND DEFINITIONS

Cultural Competence: Increasing individuals’ cross-cultural awareness and appreciation. Achieving

cultural competence is seen as inextricably linked to language proficiency.
Digital Literacy: Honing the skills needed to effectively navigate today’s technology-drive world.
Experiential Learning: Hands-on learning and reflection through direct contact with the subject
matter.
Generative AI: Artificial Intelligence technologies that generate responses based on inputted prompts.
Italian Cultural Studies: Examining various aspects of Italian culture (art, fashion, cinema, cuisine,
etc.) within historical context.
LLMs: Large Language Models (LLMs) are sophisticated AI systems trained on vast amounts of
textual data, allowing them to learn complex linguistic patterns. The versatility of LLMS makes them
useful tools that could be applied to language processing tasks such as translation, answering questions,
and providing summaries. Within the umbrella of Generative AI tools available to the public, ChatGPT,
developed by OpenAI, falls under the category of an LLM-based chatbot. Other LLM-based chatbots
include Bard, developed by Google, and Ernie, developed by Baidu. While Google Translate is an LLM,
it is not an LLM-based chatbot.
Multimodal: Coursework or activities which are enhanced through a variety of formats (e.g. audio-
visual assignments, in-person and virtual delivery of lecture content).
Reflective Assignments: We define reflective assignments as a blend of students’ considerations
on the ways in which their in-class and lived experiences intersect with their academic research and
analyses of scholarly sources.

ENDNOTES
1
See also Font de la Vall and González Araya (2022) on generative AI’s limited abilities in creative
expression and in producing natural-sounding language or replicating “cultural and contextual
nuances of language, such as idioms, colloquialisms” (Font de la Vall, R., González Araya, 2022,
p. 7573).
2
Despite the progress that has been made in devising policies at an increasing number of institu-
tions, according to a recent (2023) UNESCO global survey of over 450 schools and universities,
“approximately 13% of the universities reported having institutional policies and/or some formal
guidance concerning the use of generative AI applications guidance, while only 7% of schools did”
(UNESCO survey, 2023).
3
ChatGPT first launched on November 30, 2022 and 27 subsequent updates, with 26 of them oc-
curring from January 2023 to November 2023 (Open AI, 2023b).
4
See Appendix (T. Lobalsamo_Supplemental Teaching Notes) for a sample Style Guide, AI Ap-
pendix/Declaration, Rubric, Essay-Style Reflection Question.

57
The Reality of Artificiality

APPENDIX

Teaching Notes

58
The Reality of Artificiality

59
Section 2
Perspectives:
What People Say About AI
61

Chapter 4
Enriching the Teaching-
Learning Experience by Using
AI Tools in the L2 Classroom
Dimaris Barrios-Beltran
Mount Holyoke College, USA

ABSTRACT
Artificial intelligence (AI) has emerged as a transformative force in second language (L2) education,
reshaping teaching and learning methodologies. This chapter explores AI’s impact on L2 educators
and learners through insights from questionnaires and a follow-up conversation. Initial apprehension
towards AI is counterbalanced by curiosity about its potential to enhance educational practices. The
chapter provides practical guidance, showcasing how AI tools can be aligned with key language learn-
ing skills and offering structured examples of activities to enhance these skills. It highlights AI’s role in
providing immediate feedback, simplifying complex concepts, and creating inclusive classrooms tailored
to individual learning styles and needs. The discussion also addresses educators’ recognition of AI’s
potential and underscores the need for clear guidelines and training in ethical AI implementation. As
AI technology evolves, it promises a more personalized, dynamic educational journey, enriching the L2
learning process.

INTRODUCTION

The integration of Artificial Intelligence (AI) in educational settings is a burgeoning discourse, particu-
larly in the United States, where educators express a mix of doubt, insecurity, and skepticism about this
emerging technology. Concerns range from viewing AI as a potential threat to student cognition to an
under-recognition of its nuanced intelligence applications. Some institutions are banning AI use due to
concerns over facilitating plagiarism, while others emphasize responsible usage but struggle to define
and clarify its ethical boundaries (Singer, 2023). Conversely, higher education institutions in Asia and
Europe are increasingly adopting AI, not only in remote learning platforms (Adipat et al., 2022) but also

DOI: 10.4018/979-8-3693-0872-1.ch004

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

Enriching the Teaching-Learning Experience by Using AI Tools

in administrative systems (Sellar & Gulson, 2019), fostering innovative pedagogies like flipped learning
and universal design teaching.
Recent studies, focusing on the need for regulatory frameworks and examining AI’s impact on learn-
ing outcomes and classroom integration (Zheng et al., 2021), have yet to fully uncover AI’s potential
in education. Specifically, in second language (L2) classrooms, there are many doubts about how this
technology can truly enhance learners’ linguistic skills without doing the work for them. Questions
arise about the extent to which these tools might minimize effort but jeopardize learning, or conversely,
support the language learning process. Furthermore, most studies focus on perceptions of current AI
tool users, such as those using ChatGPT and Grammarly, leaving the actual improvement in their per-
formance largely unassessed.
Additionally, many technology experts are still learning about the capabilities of these new tools
and are tasked with guiding educators on their usage. This leads to the central challenge: exploring how
to ethically incorporate these tools in the classroom, ensuring they fulfill their intended purposes. A
pivotal question emerges: How can educators be best prepared, through targeted training or orientation,
to navigate a future increasingly intertwined with AI? This chapter contributes to the ongoing dialogue
about AI in higher education by presenting an in-depth analysis of second language (L2) educators’ and
learners’ perceptions, with a focus on face-to-face learning environments. It examines their readiness
to adopt AI tools for diverse linguistic needs, specifically in areas such as time management and plan-
ning, memorization, interpersonal communication, presentation, and creative and critical thinking – all
crucial for mastering a second language. Furthermore, the chapter offers practical insights, aligning spe-
cific AI tools with these key language skills and providing structured activity examples. This approach
demonstrates how AI can be effectively integrated into classroom activities and pedagogical practices,
enhancing the language learning experience.

LITERATURE REVIEW

Previous research on AI in language education spans a diverse range of areas, from ethical considerations
to the facilitation and personalization of learning experiences. This body of work converges on a key
consensus: the integration of AI necessitates a deep ethical awareness and a nuanced understanding of
its implications for learners. Highlighting this, studies emphasize fostering critical thinking in learners,
enabling them to navigate the ethical dimensions inherent in the use of AI in education.
This integration of AI use into the curriculum assumes a role of preponderant significance, not only
in fostering a futuristic pedagogical outlook but also in nurturing the professional mindset of potential
developers and consumers of this emerging technology (Borenstein & Howard, 2021). Emphasis on AI
ethical use in education is exemplified in Sabuncuoglu (2020) which demonstrates how incorporating
AI into curricula can enhance not just subject knowledge, like mathematics and science, but also stu-
dents’ understanding of AI’s ethical implications. Building on this, a novel area of exploration is AI’s
application in classroom teaching analysis. Roschelle et al. (2020) and Sun et al. (2023) illustrate how
AI can meticulously scrutinize classroom dynamics, behavior patterns, and knowledge representation.
This multidimensional assessment serves to refine classroom management and enhance teaching and
learning practices. By recognizing and deciphering behavioral trends, educators can optimize their
teaching methodologies, aligning with data-informed pedagogical movements and equipping them to
tailor learning experiences.

62

Enriching the Teaching-Learning Experience by Using AI Tools

In line with these ethical considerations, Roe et al. (2023) emphasizes the need for clear guidelines
and transparent rules regarding the use of technology in the classroom. Their analysis extends to the
advantages and disadvantages of three common tools: Machine Translation services (MTs), Digital
Writing Assistants (DWAs), and Academic Plagiarism Trackers (APTs). Unlike tools like ChatGPT that
generate original content, these technologies provide support in translation, grammar, vocabulary, sen-
tence structure, and plagiarism detection. However, Roe et al. (2023) also highlights a critical concern:
students often lack clarity on what constitutes a violation of academic honor codes versus proper AI
use in academia. This finding underscores the necessity for educational institutions to develop explicit
guidelines to help students navigate the ethical use of AI tools in their academic pursuits.
Further research efforts have been directed towards leveraging AI for various educational purposes,
such as student tutoring, writing assistance, immersive virtual reality settings, chatbot dialogues, and
adaptive learning experiences (Samea Qoura & Moustafa Elmansi, 2023; Zawacki-Richter et al., 2019).
AI’s most compelling attribute in this domain is its ability to craft personalized learning experiences by
adapting teaching materials to students’ proficiency levels and reconfiguring learning paths. Extending
its capabilities, AI now includes immediate feedback provision, translation assistance, error identification,
and support in pronunciation and grammatical reflections (Dodigovic, 2009; Miller, 2019; Samea Qoura
& Moustafa Elmansi, 2023), highlighting its role as a versatile tool in enhancing language proficiency.
The impact of AI on writing skills, in particular, has attracted considerable interest. Gayed et al.
(2022) examined the use of predictive text tools, focusing on a study with Japanese students learning
English. Their AI-assisted app improved syntactic complexity but not lexical diversity or production rates.
In contrast, Abdul Rahman et al. (2022) observed substantial improvement in writing scores through
Grammarly use, indicating its effectiveness in detecting grammatical errors. Nonetheless, they recognize
that such technology alone cannot replace the critical role of instructors in guiding high-quality writing.
Although a significant majority of second language acquisition studies predominantly focus on Eng-
lish, there is a noticeable dearth of research on other languages. Among the limited studies in this under-
researched area, the work of Li et al. (2023) is particularly notable. Assessing the impact of ChatGPT
in Chinese L2 classrooms, their research targeted low-income Hispanic students in New York City. The
study revealed improvements in writing skills and increased empowerment among students, highlight-
ing AI’s potential to equalize educational opportunities. However, it also underscored the importance of
ethical integration strategies, emphasizing the role of AI as a supportive tool rather than a replacement
in the learning process.
Delving into instructor perspectives, Marzuki et al. (2023) analyzed how AI tools are perceived in
Indonesian classrooms. While recognizing AI’s benefits in improving writing skills, concerns arose about
students using complex vocabulary without full comprehension, potentially affecting their creativity and
critical thinking. This underscores the necessity for balanced and informed use of AI in teaching practices.
Kohnke (2023) and similar studies (Wahyuni, 2022; Fryer et al., 2019) illustrate the growing ac-
ceptance of AI among learners for its role in facilitating independent learning and providing accessible,
enjoyable experiences. Additionally, these technologies are being employed to support inclusive and
equitable practices, particularly for individuals facing language, mental, emotional, or physical chal-
lenges (Mohato, 2023). AI serves as a transformative tool within classrooms, offering opportunities for
students with disabilities to remain integrated in standard courses.
Despite the predominantly positive reception of AI in language learning, challenges regarding in-
teraction authenticity, dehumanization, privacy issues, and technological barriers persist. Furthermore,
it is important to note that most studies focus on the opinions or perceptions of learners and educators

63

Enriching the Teaching-Learning Experience by Using AI Tools

who are already engaging with these technologies, predominantly in online learning environments. The
actual impact of AI on linguistic skills remains unclear, as much of the existing data do not evaluate
tangible performance outcomes. Additionally, not every educator feels confident incorporating AI into
their teaching practices and student evaluations. Alharbi (2023) advocates for increasing familiarity with
these technologies among educators and students. This involves enhancing digital literacy and developing
a deeper understanding of how AI can support and enhance the teaching-learning process.
Therefore, this chapter aims to delve into technology usage in the second language classroom, exam-
ining perceptions of AI integration and pinpointing specific educational needs that technology can ad-
dress. It also seeks to bridge the gap in existing literature by providing explicit examples of AI-enhanced
activities and tasks. This approach is intended to equip educators and learners to navigate and thrive in
the changing terrain of learning and digital advancements.

THE PERCEPTION OF AI IN THE L2 CLASSROOM

The integration of artificial intelligence into educational settings, particularly in today’s digital era,
represents a complex and evolving area of inquiry. In education, the harnessing of a diverse array of
technological tools – from computers, tablets, and smartphones to projectors, VR headsets, and smart
whiteboards – has created dynamic learning experiences. This technological shift has transformed
classroom interactions, dynamics, and access to information, marking a new era in teaching and learn-
ing methodologies. AI, with its distinct capabilities, adds a new dimension to this transformation. Its
integration into educational tools and platforms signifies a paradigm shift, prompting a reassessment of
its role in equipping students to navigate and contribute to a world that is continually evolving in terms
of communication, learning, and information acquisition.
The incorporation of AI in the second language classroom, however, has been met with diverse per-
spectives. While AI offers unique interactive capabilities that differ from conventional tech tools, there
are concerns about its potential impact on language proficiency. This is especially pertinent in second
language acquisition, where the focus is on developing the ability to express thoughts and ideas in the
target language. In the United States, there exists a notable degree of reluctance among educators and
administrators regarding the implementation of AI in the curriculum and its impact on students’ learning
experiences. These apprehensions are more pronounced in L2 learning due to the emphasis on preparing
students for real-world interactions in the target language. Key questions emerge: To what extent can AI
assistance improve students’ linguistic skills? Can AI act as an interactive tool that not only assists but
also promotes reflection on the learning process and language-related errors? Despite these concerns,
various studies have acknowledged AI’s potential in offering personalized learning experiences, provid-
ing immediate feedback, and exposing learners to a diverse range of linguistic content, at least from the
perspective of current users of these technologies.
Before delving into these complexities, it is vital to understand the current perceptions and potential
misconceptions surrounding the use of AI and technology in the L2 classroom, particularly in higher
education in the United States. Familiarity with AI’s capabilities and limitations could significantly
shape this discourse.
To contribute to this ongoing discussion, this study surveyed L2 educators and L2 learners at a higher
education institution in the United States, focusing on the following research questions:

64

Enriching the Teaching-Learning Experience by Using AI Tools

RQ1. Do educators and learners integrate technology into their daily lives?
RQ2. Do they consider technology an essential aspect of the L2 learning process?
RQ3. Are they familiar with the application of AI in the L2 classroom?
RQ4. Do they believe AI should be integrated into the L2 classroom?

METHODOLOGY

This study adopted a mixed-methods approach to comprehensively explore the perceptions of AI in sec-
ond language education. The data collection process involved administering a structured questionnaire
to both educators and learners, which comprised both open and closed questions. The closed questions
were designed to gather quantitative data, while the open questions aimed to elicit more in-depth quali-
tative responses. In addition to the questionnaire, follow-up open-ended conversations with educators
were conducted to delve deeper into the preliminary findings and discuss potential strategies for AI
implementation in the second language classroom.
For the analysis, the quantitative data derived from the closed questions were processed using inde-
pendent samples t-tests and descriptive statistics. This approach facilitated the examination of patterns
and differences in the responses. The qualitative data, sourced from the open-ended questions in the
questionnaire and the post-study conversations with educators, were analyzed through a thematic ap-
proach. This method aligned with the research questions and enabled a nuanced exploration of the themes
and insights emerging from participants’ responses.

Context and Participants

This study was conducted at Mount Holyoke College (MHC), a private liberal arts institution known
for its diverse language program and emphasis on global citizenship. The study involved a total of fifty
participants (N=50), comprising twelve educators (N=12) teaching second language courses and thirty-
eight students (N=38) enrolled in these courses.
MHC offers an extensive range of language courses, including Arabic, Chinese, French, German,
Hebrew, Italian, Japanese, Korean, Russian, and Spanish. These courses range from introductory levels
to advanced literature and research-focused studies. Language learning is a curricular requirement at
MHC, underscoring the institution’s commitment to fostering multicultural understanding and global
engagement. The most populous language departments at MHC are Spanish, Latino/a, and Latin Ameri-
can Studies, and French. However, a significant number of students also enroll in other language classes.
Additionally, the college participates in the Five College interchange program with Amherst College,
Hampshire College, Smith College, and the University of Massachusetts Amherst, allowing students to
take courses across these institutions. For this study, only students enrolled in language courses at MHC
were considered for participation.
Regarding the demographic composition of the participants, the majority identified as White (52%),
followed by Hispanic/Latino (28%). More detailed demographic information is presented in Table 1.
The educator group in this study included twelve individuals: 8 females, 3 males, and 1 person who
preferred not to disclose their gender. A significant majority of these educators, 83.3%, had over 21
years of experience in teaching second language courses. There was a notable preference for in-person

65

Enriching the Teaching-Learning Experience by Using AI Tools

instruction among them, with 91.7% favoring this mode of teaching. In terms of languages taught, Span-
ish was the most common (41.7%), followed by French and Italian (each at 16.7%).
The learner group comprised thirty-eight students with diverse gender identities: 25 females, 7 iden-
tifying as non-binary/non-conforming, 2 as transgender, and 4 who chose not to disclose their gender.
The majority of these students were in the early stages of their college education, with first-year students
making up 39.5% and sophomores 34.2%. Like the educators, these learners showed a strong preference
for in-person courses (97.4%). Spanish was the most commonly studied language (76.3%), followed by
Italian (10.5%) and French (5.3%).

Table 1. Ethnicity of participants by profession

Ethnicity
POC, Do Not
Black or
Hispanic or Prefer Not to Identify With
Profession Asian African White Total
Latino Say Any Race or
American
Ethnicity
Educator 1 0 4 6 1 0 12
Learner 2 2 10 20 3 1 38
Total 3 2 14 26 4 1 50

Materials and Procedures

The study’s participants were drawn from the academic community of Mount Holyoke College. Recruit-
ment began with initial contact via email, facilitated by the Academic Department Coordinators of the
language departments who had access to the email lists of both L2 educators and learners. Comprehensive
information about the research, including its objectives, participant involvement, and data confidentiality,
was provided to potential participants. Emphasis was placed on the voluntary nature of participation,
with informed consent required from all participants.
Data collection was primarily conducted using a structured questionnaire distributed through Google
Forms. This questionnaire consisted of 22 questions, designed to explore participants’ daily interactions
with technology and their perceptions of its relevance in educational settings. Questions also probed
familiarity with AI tools and attitudes towards integrating these tools in second language education.
The primary format of the questionnaire was a 5-point Likert scale, ranging from 1 (strongly agree) to
5 (strongly disagree), allowing participants to express their level of agreement with various statements
(see Example 1 below). In addition to the Likert scale items, the questionnaire featured multiple-choice
and open-ended questions to capture a wider range of responses.
Example 1. Likert Scale Question Format in the Questionnaire
Statement #12: I understand what artificial intelligence (AI) tools/platforms are.

1 - Strongly agree
2 - Agree
3 - Neither agree nor disagree
4 - Disagree

66

Enriching the Teaching-Learning Experience by Using AI Tools

5 - Strongly disagree

A demographic section with six questions was included in the questionnaire to collect essential par-
ticipant information. This section asked about ethnicity, gender identity, teaching experience (for educa-
tors) or academic year (for learners), language of instruction or study, and preferred mode of instruction.
The questionnaire aimed to assess attitudes towards technology, capture current usage patterns, evaluate
familiarity with AI tools, and determine openness to incorporating AI into language learning experiences.
Following the analysis and interpretation of the data collected from the questionnaire, language edu-
cators at MHC were invited to engage in a follow-up conversation. This gathering served as a platform
to present the general results of the study, allowing participants to ask questions, share their experi-
ences, and discuss various activities that could enhance the teaching-learning process. Approximately
15 educators attended this session. Among them were some who had completed the questionnaire, as
well as others who joined the conversation to gain deeper insights into the implications of AI in higher
education, specifically in the context of in-person teaching.
This interactive session provided an opportunity for educators to reflect on the study’s findings and
explore practical ways of integrating AI tools in their teaching methodologies. It also allowed for an
exchange of ideas and perspectives, enriching the study’s overall understanding of AI’s role in language
education.

Results and Discussion

The findings of this study offer valuable insights into the role of technology in language education and
the potential benefits of integrating AI tools. The discussion is structured thematically, aligned with the
research questions, to facilitate a clear understanding and interpretation of the results.

Role of Technology in the Daily Lives of Educators and Learners (RQ1)

To address RQ1, responses to three specific statements in the questionnaire were analyzed. As indi-
cated in Table 2, the data predominantly underscore the integral role of technology in the daily lives of
participants and its influence on their teaching and learning experiences. The majority of participants
(98%) affirmed the significance of technology in their lives, with no statistical difference between
educators and learners, t(48) = -.902, p > 0.05. Furthermore, 72% recognized technology’s potential
to enhance the teaching-learning experience, with no significant difference between the groups in this
regard, t(30.267) = 1.587, p > 0.05.
However, perspectives varied regarding technology’s role in easing tasks. While 44% of participants
agreed that technology makes everything easier, a notable 46% remained neutral. This pattern of neutrality
was consistent across both groups, t(48) = .179, p > 0.05, indicating no significant statistical difference.
This lack of a strong consensus suggests a varied perception of technology’s practical utility. One possible
interpretation is that participants’ digital literacy levels may influence their recognition of technology’s
ease-of-use. Those more familiar with technology may more readily acknowledge its facilitative role in
completing regular tasks, while those with less experience might not perceive the same level of ease.
Given the lack of statistical significance observed across all analyses, the remainder of the quantita-
tive data discussion will primarily focus on descriptive statistics rather than inferential ones.

67

Enriching the Teaching-Learning Experience by Using AI Tools

Table 2. Importance of technology in the daily lives of participants

Strongly
Profession Agree Neutral Disagree Strongly Disagree
Agree
Statement #1: Technology is an important aspect of my life.
Educator 5 7 0 0 0
Learner 23 14 1 0 0
Total 28 21 1 0 0
Statement #2: Technology makes everything easier.
Educator 0 6 5 1 0
Learner 3 13 18 3 1
Total 3 19 23 4 1
Statement #3: Technology improves the teaching-learning experience.
Educator 1 10 1 0 0
Learner 4 21 12 1 0
Total 5 31 13 1 0

Essential Use of Technology for Teaching and Learning (RQ2)

This part of the study explored whether educators and learners view technology as indispensable in
teaching and learning contexts. Analysis mainly focused on two statements, as detailed in Table 3.
When considering whether teaching and learning are possible without technology, the responses varied.
A majority of learners (66%) disagreed with the notion that learning is impossible without technology,
suggesting a recognition of the value of non-technological learning methods. In contrast, half of the
educators felt that teaching is not feasible without technology, possibly reflecting their reliance on tech-
nological tools such as audio and video resources, computer and projector use, and online platforms for
homework assignments.

Table 3. Essential use of technology for teaching and learning

Strongly
Profession Agree Neutral Disagree Strongly Disagree
Agree
Statement #4: Teaching is not possible without technology (educators).
Learning is not possible without technology (learners).
Educator 1 5 3 1 2
Learner 0 1 4 20 13
Total 1 5 7 21 15
Statement #5: Students cannot learn a second language without technology.
Educator 2 4 1 2 3
Learner 0 7 6 15 10
Total 2 11 7 17 13

68

Enriching the Teaching-Learning Experience by Using AI Tools

Further, when asked about the necessity of technology in learning a second language, 63.1% of learn-
ers disagreed with its indispensability, compared to 41.7% of educators. This difference might indicate
a divergence in perspectives based on roles. Historical evidence suggests substantial contributions to
society in eras before advanced technology, supporting the learners’ views. However, the responses may
also be influenced by students’ perceptions of expected or appropriate answers in an academic setting,
though no specific evidence was found to support this hypothesis.
Additional statements in the questionnaire addressed the role of technology in the L2 classroom. A
notable 76% of participants reported using digital online platforms in their language classes, yet only
30% did not see the benefits of such platforms for completing homework assignments. Interestingly,
64% of both educators and learners expressed a preference for hard copy textbooks over digital versions.
This preference, spanning generations, challenges the assumption that younger ‘digital natives’ would
favor digital materials. The coexistence of this preference with an acknowledgment of digital platforms’
advantages illustrates a balanced approach to learning resources.
Regarding the usage of cellphones, tablets, and laptops/computers, all educators noted their students’
use of these devices for in-class activities or note-taking. This observation aligns with the majority of
learners’ responses, though eight disagreed. At MHC, the use of technological devices in the classroom
is common, with students permitted to use them for note-taking and class activities. The preference for
notebooks among some students reflects individual differences in learning styles.
In addition to exploring the perceived essentiality of technology in teaching and learning, the study also
assessed participants’ familiarity with various educational platforms, such as Edmodo, Moodle, Google
Classroom, and Blackboard. A striking 94% of participants demonstrated a high degree of comfort and
confidence in using these platforms for educational purposes. This widespread proficiency underscores
the integral role these digital tools play in the current educational landscape at MHC.
The participants’ familiarity and ease with these platforms further reinforce the findings that, despite
some reservations about the indispensability of technology for learning, there is a significant acceptance
and utilization of digital tools in educational settings. This comfort level with educational platforms
is indicative of a broader trend towards integrating technology into the teaching and learning process,
aligning with the institution’s commitment to leveraging digital advancements in education.

Familiarity With AI Tools in the L2 Classroom (RQ3)

To assess participants’ familiarity with AI tools and their implementation in the second language classroom,
responses to three specific statements were analyzed, as shown in Table 4. Additionally, participants were
asked multiple-choice and open-ended questions about popular AI tools. The data indicate that a majority
of participants (76%) are confident in their understanding of what AI tools/platforms are. However, their
responses regarding the actual application of AI in the L2 classroom showed considerable variation. Only
four educators reported integrating AI into their teaching, and eleven learners indicated using AI to aid
their language learning, suggesting that a significant 70% of participants have not actively experienced
AI in the classroom setting. Furthermore, when it comes to using AI tools for completing assignments,
only seven learners (18%) and two educators (16%) acknowledged its utilization.
The responses were even more varied when participants were asked about AI’s effectiveness in en-
hancing language comprehension. The majority showed neutrality (34%) or disagreement (40%), with
only 26% agreeing that AI helps students better understand the language they are learning.

69

Enriching the Teaching-Learning Experience by Using AI Tools

In exploring specific AI tools, participants chose from a list that included Brainly, ChatGPT, ChatPDF,
Grammarly, Scite.ai, Quillbot, and others, indicating their familiarity and usage. The most recognized
tools among both educators and learners were ChatGPT and Grammarly. However, a striking 83% of
educators reported not using any of these tools in their L2 classrooms. This contrasts with learners,
where 44.7% reported using Grammarly and 28.9% using ChatGPT. This discrepancy suggests that while
educators are aware of AI tools, their actual usage in teaching is limited. On the other hand, learners,
despite a lower self-reported use of AI for assignments, have been using these tools more frequently
than indicated, with many acknowledging the use of at least two AI tools.

Table 4. Participant’s familiarity with the use of AI in the L2 classroom

Strongly
Profession Agree Neutral Disagree Strongly Disagree
Agree
Statement #12: I understand what artificial intelligence (AI) tools/platforms are.
Educator 5 5 2 0 0
Learner 12 16 7 3 0
Total 17 21 9 3 0
Statement #13: I have used AI tools in my second language classroom (educators).
I have used AI tools to clarify doubts about the L2 language I am learning (learners).
Educator 1 3 2 4 2
Learner 5 6 3 10 14
Total 6 9 5 14 16
Statement #14: My students have used AI tools to complete assignments for my class (educators).
I have used AI tools to complete assignments in my L2 language class (learners)
Educator 2 0 5 3 2
Learner 4 3 3 11 17
Total 6 3 8 14 19
Statement #15: AI helps students better understand the language they are learning.
Educator 0 4 7 0 1
Learner 4 5 10 7 12
Total 4 9 17 7 13

The Need for AI to Be Integrated in the L2 Classroom (RQ4)

This subsection examines participants’ perspectives on the necessity of integrating AI in second lan-
guage education. The analysis was based on responses to three statements (illustrated in Table 5) and
a multiple-choice question regarding various descriptions of AI tools. This approach was designed to
assess if perceptions differed when considering the potential of AI tools to enhance linguistic skills and
performance.

70

Enriching the Teaching-Learning Experience by Using AI Tools

Table 5. The need for using AI in the L2 classroom

Strongly
Profession Agree Neutral Disagree Strongly Disagree
Agree
Statement #16: Students should be trained on how to use AI tools for academic purposes.
Educator 4 6 2 0 0
Learner 7 9 10 6 6
Total 11 15 12 6 6
Statement #17: Instructors should use AI tools in the second language classroom.
Educator 2 3 4 1 2
Learner 0 8 11 13 6
Total 2 11 15 14 8
Statement #18: Instructors should allow students who are learning a second language to use AI tools.
Educator 1 6 2 2 1
Learner 2 6 11 10 9
Total 3 12 13 12 10

Regarding the need for AI tool training for academic purposes, over half of the participants (52%)
expressed some agreement. Specifically, 10 educators and 17 learners viewed such training positively,
while a smaller number remained neutral. This result suggests a general consensus on the importance
of educating both educators and learners about AI tools.
Curiously, 41.7% of educators and 28.9% of learners agreed that AI should be integrated into the L2
classroom. This indicates a disparity in perceptions, with educators showing a slightly higher inclination
toward AI integration, possibly due to their recognition of the evolving technological landscape. However,
learners displayed a more hesitant stance, potentially reflecting concerns about the diminishing role of
the educator in a tech-driven learning environment.
The need for AI integration becomes more evident when considering attitudes towards allowing AI
tool usage for language learning. A majority of educators (58%) agreed with this, compared to only
21% of learners. This difference may stem from concerns about AI’s ethical implications or its potential
impact on the learning experience. Educators might perceive training as a means to instruct students in
the ethical use of AI, while learners may fear a reduced human interaction in their language education.
To further probe into misconceptions and interest in AI tools, participants were asked to select from
descriptions of various AI functionalities without knowing their commercial names. The top choices
for educators included tools for memorization, live speech transcription, grammar checking, learning
progress tracking, and literature mapping. These preferences align with functionalities of tools like Anki,
Otter.ai, Grammarly, Knowji, and Research Rabbit. Learners showed similar interests, with their top
choices encompassing tools for memorization, grammar checking, live speech transcription, intelligent
tutoring, and generating human-like responses. This mirrors functionalities of Anki, Grammarly, Otter.
ai, Scite.ai, and ChatGPT.
The findings from the questionnaire underscore the significant role of technology in both educators’
and learners’ lives. Educators generally acknowledge the importance of technology in second language
teaching, while learners do not view it as indispensable for learning. There’s a notable awareness of
AI among participants, but its actual implementation in the classroom is limited. Educators, more than

71

Enriching the Teaching-Learning Experience by Using AI Tools

learners, recognize the need for training in the ethical use of AI tools. Despite some initial apprehension,
learners showed interest in AI tools that could support their language learning through personalized
experiences and assist in completing assignments.
These insights affirm the integral role of technology and the emerging interest in AI within second
language classrooms. While debates continue over the necessity of technology in language learning,
there’s a shared curiosity about how AI might enhance language proficiency.

Follow-Up Conversation with Educators

The follow-up conversation with educators sought to deepen the understanding of AI implementation in
L2 education. Focusing on fundamental skills necessary for language learning success, the discussion
explored AI tools that could aid their development. Educators, showing a strong interest in AI func-
tionalities from the questionnaire, engaged in an in-depth dialogue about specific learning skills crucial
for linguistic proficiency. They considered how various AI tools might support or enhance these skills,
aiming to reconcile the potential of AI with its practical application in the classroom. This conversation
also served as a forum for educators to voice their concerns and explore practical integration strategies
for AI in their teaching.
The discussion began by acknowledging the diversity in pedagogical approaches, assessment tools, and
classroom activities, underscoring the individuality of each learner’s language learning journey. Educators
noted that students often face unique challenges, leading to varied error patterns. Recent research, such
as Zablotsky et al. (2019), highlights a rise in learning disabilities among students, presenting additional
challenges in language education. Howard (2023) further emphasizes the need to recognize and value
the linguistic diversity these students bring to the classroom.
A major motif became apparent around the need for personalized instruction. Educators expressed
difficulties in creating individualized learning experiences due to time and resource constraints. Current
accommodations in classrooms are often reactive rather than proactive, focusing on immediate solutions
like extending deadlines rather than anticipating and addressing potential learning barriers. There was
consensus on the need for more comprehensive, universally designed teaching frameworks that adapt
flexibly to diverse learning needs.
The conversation then shifted to identifying key skills essential for L2 success: time management and
strategic planning, memorization, interpersonal communication, presentation skills, creative thinking,
and critical and reflective thinking. While recognizing the importance of these skills, educators expressed
uncertainty about integrating AI tools without undermining the value of human interaction and instructor
guidance. To bridge this gap, examples of AI tools corresponding to each skill were presented, helping
educators visualize how AI could complement traditional teaching methods (see Table 6 for details).
The discussion about essential language learning skills and the potential support of AI tools was
enlightening, especially when contextualized with example activities. Some educators realized that they
were already using AI in their classrooms, unaware that certain tools and methods they employed were
AI-based. This realization led to a deeper exploration into the broader perception of AI among educators.
It became apparent that many primarily associated AI with ChatGPT, not recognizing the full spectrum
of AI technologies already integrated into educational platforms, emails, and other applications. Their
main concern was ChatGPT’s potential use in completing assignments, which posed a risk of academic
dishonesty.

Table 6. AI tools and their corresponding support for key language learning skills

Language
Skill Description AI Tools for Skill Enhancement Example Activity #1 Using AI Example Activity #2 Using AI
Learning Skill

Creating a Schedule: Students consult the Solving Scheduling Conflicts: Students

Click Up, Clockwise, and Motion can analyze syllabus, academic calendar, class schedule, analyze the schedule of a real or fictional
Effective time management is essential
calendars to highlight tasks and assignments assignment list, and personal events. Using character using AI tools. They identify priority
Time Management for punctual assignment completion,
requiring immediate or prompt attention. They AI tools, they then create a weekly or tasks, potential conflicts, assess AI tool
and Planning enhanced focus, and improved
also recommend optimal time slots for completing monthly schedule to effectively manage recommendations, and devise creative solutions
learning.
specific tasks. their time and ensure timely completion of to enhance overall time management and
assignments. scheduling.

Generative Flashcard tools such as Limbiks

and Quizlet can create flashcards from diverse Generating Flashcards: In group
Memorization is a key skill essential Error Identification Task: Educators utilize
sources like study guides, online textbooks, collaborations, students use AI tools to
for everyday tasks, complex work, and AI tools to develop flashcard sets containing
and multimedia content. These tools feature create flashcard sets for reviewing specific
academic requirements. It entails the intentional errors. Students work in groups to
Memorization organizational capabilities, enabling users to topics. These sets are shared with the class,
ability to retain and store information, spot and correct these inaccuracies, thereby
create folders, study sets, and personalized study facilitating peer-to-peer learning and aiding
thus demanding considerable capacity deepening their understanding of proper
plans. Additionally, they provide various options in the memorization of relevant vocabulary,
from the brain’s memory storage. language usage.
for testing and reinforcing learning of challenging grammar, and other content.
material.

Interpersonal Communication involves Oral Interview Practice: Students utilize

Interpersonal Written Communication: Students
exchanging information, thoughts, AI tools like Small Talk and ChatGPT serve AI tutors to practice oral interviews outside
use ChatGPT for written dialogues on specific
ideas, feelings, and emotions among as linguistic tutors by creating a simulated, the classroom. These tools dynamically
Interpersonal topics, providing detailed prompts to guide the
individuals. This exchange can occur pressure-free conversational environment, ideal adjust to the conversation’s focus and topics,
Communication conversation. Additionally, they can conduct
face-to-face or through written and for practicing language skills without fear of generating relevant questions, responding to
interviews with the AI, instructing it to emulate
digital channels such as phone calls, judgment. inquiries, and offering hints and constructive
a historical figure or personality.
chat applications, emails, and letters. feedback.

Presentation skills involve delivering

AI tools, including chatbots like ChatGPT and
Enriching the Teaching-Learning Experience by Using AI Tools

a one-way message to an audience, Brainstorming Presentation Ideas: Students Structuring Presentation Ideas: Students use
Jasper, and voice bots like Small Talk, assist in
which may consist of readers, listeners, utilize ChatGPT to brainstorm and generate AI tools to obtain examples and guidance on
various presentation-related tasks. Additionally,
Presentation or viewers. These skills are crucial in potential topics for their presentations, effectively structuring their presentations,
tools such as Sendsteps, SlidesAI, and Haiku
formal contexts where the aim is to tapping into the AI’s ability to suggest diverse ensuring coherent organization and adequate
Deck can automate the creation of visually
inform or persuade, and presentations and relevant ideas. support for their ideas.
appealing slides, enhancing visual storytelling.
are often well-rehearsed.

Develop a Short Story or Dialogue: Students

Pictionary-Like Game: In this activity,
Creative Thinking is characterized by Chatbots such as ChatGPT and Jasper aid students craft a story or dialogue related to a specific
students are given a word or phrase and
flexibility, originality, and realism. in brainstorming sessions and creating engaging topic or vocabulary. Following brainstorming,
must describe it effectively using AI tools to
Creative Thinking This skill enables individuals to content. For visual creativity, AI-driven tools like character development, and dialogue creation,
generate a corresponding image. This task
generate innovative ideas and devise DALL-E, Canvas, and Adobe Firefly add a visual they utilize AI comic generator tools to either
enhances descriptive language skills and
novel solutions to complex problems. dimension, enriching creative language usage. use predefined templates or create original
fosters creative expression.
comics, incorporating their written dialogues.

Critical and Reflective Thinking

Structuring a Research Paper: Students
empowers students to analyze, Summary Task: Students read a text or
Perplexity aids in identifying relevant sources, choose a research topic, formulate a thesis
compare, contrast, and challenge article and summarize its main points.
while ChatPDF and Humata help pinpoint key statement, and outline their paper. They then
Critical and encountered knowledge. This process Subsequently, they use ChatPDF to obtain
topics and address specific reading questions. consult ChatGPT for structural suggestions
Reflective enables them to construct new automated highlights of key information. This
Scholarcy and Scite.ai engage students critically and critically assess these against their initial
Thinking meanings, engage in meaningful enables them to compare and contrast their
with the literature. ChatGPT and Quillbot are ideas, refining their approach. Tools like Scite.
discourse, and contribute to academic summaries with AI-generated ones, fostering
instrumental in enhancing writing skills. ai are used to gather pertinent information from

73
dialogue with unique insights and critical evaluation.
various sources.
perspectives.

Enriching the Teaching-Learning Experience by Using AI Tools

However, the dialogue effectively helped to dispel these misconceptions. Educators began to see
ChatGPT not merely as a tool that could be misused but as a potential tutor capable of providing sub-
stantial learning assistance. Despite this progress in understanding AI among educators, three attendees
noted a reluctance among Mount Holyoke College students to use AI tools due to fears of plagiarism and
cheating. This observation in their own classrooms and interactions with their students underscores the
need for enhanced training and clearer communication about AI use in educational settings. Attendees
called for more explicit guidelines from the administration on AI’s role in higher education and effective
ways to inform students about ethically using AI in their coursework.
In addition to addressing misconceptions about AI, the conversation also delved into the educators’
interest in fostering inclusivity within the classroom. Attendees were introduced to a variety of AI-
powered tools designed to create more inclusive learning environments. These tools, including Curipod,
Education Copilot, and Yippity, aid in the design of class and course materials while offering progress
analysis and feedback. Platforms like Quizlet, Mango Languages, and Duolingo are renowned for provid-
ing personalized learning experiences that cater to individual student needs, thus enabling educators to
support diverse learning styles. They can be integrated seamlessly into classrooms, allowing students to
progress at their own pace and focus on areas needing improvement, with real-time progress monitoring
by instructors.
Beyond classroom instruction, Text-to-Speech (TTS) tools like Google Cloud Speech-to-Text and IBM
Watson Speech to Text enhance pronunciation practice and intonation understanding by converting text
into audio. Video captioning and subtitling tools, such as YouTube, Amara, and Subtitle Edit, improve
accessibility, while applications like InVideo, Lumen5, and Raw Shorts enrich lessons with dynamic
visuals and voiceovers. AI’s role extends to critical areas such as pronunciation, writing, listening, and
speaking, providing immediate feedback and tailored learning experiences. These tools are crucial in
helping students enhance their language skills, boost confidence, and deepen cultural understanding.
This follow-up conversation illuminated key insights, clarifying misconceptions about AI in education
and offering practical ideas for its integration in L2 classrooms to foster inclusivity. It highlighted how
AI tools could transform the classroom into a multidimensional and engaging space, accommodating
and inspiring students from diverse backgrounds and learning needs.

CONCLUSION AND FUTURE DIRECTIONS

Emerging technologies, particularly artificial intelligence, have become a pivotal part of daily life, revo-
lutionizing the educational landscape. While AI has rendered learning more interactive, engaging, and
dynamic, research gaps remain, particularly concerning non-English language learning and in-person
instruction contexts outside of Asia and Europe. These gaps are most pronounced in empirical research
assessing AI’s impact on performance in L2 classroom activities.
This study explored the perceptions of L2 educators and learners in the United States regarding
technology and AI adoption in education. It aimed to clarify misconceptions about AI and highlight
the need for more comprehensive understanding and implementation strategies in L2 classrooms. The
findings indicate that technology is an essential component of both life and education. Despite initial
reservations, there is a growing curiosity among educators and learners about how AI can enhance
language learning experiences. The study underscored the potential of AI to make classrooms more
dynamic and tailored to learners’ needs. Traditional classrooms face challenges such as limited access

74

Enriching the Teaching-Learning Experience by Using AI Tools

to authentic resources and constraints in creating personalized learning environments. AI offers a solu-
tion to these challenges, providing opportunities for tailored language learning and preparing learners
for a technology-centric world.
AI tools support the development of essential language skills such as time management, memoriza-
tion, interpersonal communication, presentation, creative and critical thinking, and also play a key role
in creating inclusive classrooms. They enable a shift from generic teaching methods to individualized
learning trajectories, addressing diverse student needs. As education evolves, it’s crucial to recognize
AI’s applicability and adapt teaching practices accordingly. Ethical use of AI, coupled with training for
educators and students, can enhance the teaching-learning experience and maximize academic success.
AI should be seen as an opportunity to unlock each student’s potential, creating dynamic, inclusive, and
effective language learning environments.
Future research should focus on evaluating the tangible impact of AI tools by analyzing learners’ prog-
ress and outcomes before and after using these technologies. Such studies would help correlate positive
perceptions with actual improvements in language proficiency, applicable to both online and in-person
instruction. Embracing AI as an ally in language education offers a comprehensive, integrative approach
to academic experiences, paving the way for more universal and effective language learning strategies.

REFERENCES

Abdul Rahman, N. A., Zulkornain, L. H., & Hamzah, N. H. (2022). Exploring artificial intelligence using
automated writing evaluation for writing skills. Environment-Behaviour Proceedings Journal, 7(SI9),
547–553. doi:10.21834/ebpj.v7iSI9.4304
Adipat, S., Laksana, K., Busayanon, K., Piatanom, P., Mahamarn, Y., Pakapol, P., & Ausawasowan, A.
(2022). The world of technology: Artificial intelligence in education. Special Education, 2(43), 2142–2146.
Alharbi, W. (2023). AI in the foreign language classroom: A pedagogical overview of automated writing
assistance tools. Education Research International, 2023, 1–15. doi:10.1155/2023/4253331
Aziz, R. (2023). Creativity in higher education: The effect of personality on students’ creative thinking
skills. Thinking Skills and Creativity Journal, 6(1), 44–51. doi:10.23887/tscj.v6i1.54916
Borenstein, J., & Howard, A. (2021). Emerging challenges in AI and the need for AI ethics education.
AI and Ethics, 1(1), 61–65. doi:10.1007/s43681-020-00002-7
Dodigovic, M. (2007). Artificial intelligence and second language learning: An efficient approach to
error remediation. Language Awareness, 16(2), 99–113. doi:10.2167/la416.0
Ennis, R. H. (2015). Critical thinking: A streamlined conception. In M. Davies & R. Barnett (Eds.), The
Palgrave Handbook of Critical Thinking in Higher Education. doi:10.1057/9781137378057_2
Fryer, L. K., Nakao, K., & Thompson, A. (2019). Chatbot learning partners: Connecting learning
experiences, interest and competence. Computers in Human Behavior, 93, 279–289. doi:10.1016/j.
chb.2018.12.023

75

Enriching the Teaching-Learning Experience by Using AI Tools

Gayed, J. M., Carlon, M. K. J., Oriola, A. M., & Cross, J. S. (2022). Exploring an AI-based writing
assistant’s impact on English language learners. Computers and Education: Artificial Intelligence,
3(100055), 100055. Advance online publication. doi:10.1016/j.caeai.2022.100055
Howard, K. B. (2023). Supporting learners with special educational needs and disabilities in the foreign
languages classroom. Support for Learning, 38(3), 154–161. doi:10.1111/1467-9604.12449
Kohnke, L. (2023). L2 Learners’ perception of a chatbot as a potential independent language learning
tool. Int. J. Mobile Learning and Organization, 17(1/2), 214–226. doi:10.1504/IJMLO.2023.128339
Li, X., Li, B., & Cho, S. J. (2023). Empowering Chinese language learners from low-income families to
improve their Chinese writing with ChatGPT’s assistance afterschool. Languages (Basel, Switzerland),
8(4), 238. doi:10.3390/languages8040238
Marzuki, W., Widiati, U., Rusdin, D., Darwin, & Indrawati, I. (2023). The impact of AI writing tools on
the content and organization of students’ writing: EFL teachers’ perspective. Cogent Education, 10(2),
2236469. Advance online publication. doi:10.1080/2331186X.2023.2236469
Miller, T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial Intel-
ligence, 267, 1–38. doi:10.1016/j.artint.2018.07.007
Roe, J., Renandya, W. A., & Jacobs, G. M. (2023). A review of AI-powered writing tools and their im-
plications for academic integrity in the language classroom. Journal of English and Applied Linguistics,
2(1), 22–30. doi:10.59588/2961-3094.1035
Roschelle, J., Lester, J., & Fusco, J. (Eds.). (2020). AI and the future of learning: Expert panel report
[Report]. Digital Promise. https://circls.org/reports/ai-report
Sabuncuoglu, A. (2020). Designing one year curriculum to teach artificial intelligence for middle school.
In Proceedings of the 2020 ACM Conference on Innovation and Technology in Computer Science Educa-
tion (ITiCSE ’20). Association for Computing Machinery. 10.1145/3341525.3387364
Samea Qoura, A., & Moustafa Elmansi, H. (2023). Artificial intelligence in language education:
Implementations and policies required [Conference presentation]. The first national conference for the
educational studies sector. 10.21608/foej.2022.180319.1169
Sellar, S., & Gulson, K. N. (2021). Becoming information centric: The emergence of new cognitive
infrastructures in education policy. Journal of Education Policy, 36(3), 309–326. doi:10.1080/026809
39.2019.1678766
Singer, N. (2023). Ban or embrace? Colleges wrestle with A.I.-generated admissions essays. The New
York Times. https://www.nytimes.com/2023/09/01/business/college-admissions-essay-ai-chatbots.html
Sun, Z., Yu, Z. C., & Xu, F. Y. (2023). Analysis and improvement of classroom teaching based on
artificial intelligence. In H. Niemi, R. D. Pea, & Y. Lu (Eds.), AI in Learning: Designing the Future.
Springer. doi:10.1007/978-3-031-09687-7_7
Wahyuni, D. S. (2022). Integrated classroom-chatbot experience: An alternative solution for English as
foreign language learners. English Language Education and Current Trends, 1(1), 63–68. doi:10.37301/
elect.v1i1.36

76

Enriching the Teaching-Learning Experience by Using AI Tools

Zablotsky, B., Black, L. I., Maenner, M. J.; Schieve, L. A., Danielson M. L., Bitsko, R. H., Blumberg,
S. J., Kogan, M. D. & Boyle C. A. (2019). Prevalence and trends of developmental disabilities among
children in the United States: 2009–2017. Pediatrics 144(4). doi:10.1542/peds.2019-0811
Zawacki-Richter, O., Marín, V. I., Bondand, F., & Gouverneur, M. (2019). Systematic review of research
on artificial intelligence applications in higher education–Where are the educators? International Journal
of Educational Technology in Higher Education, 16(39), 39. Advance online publication. doi:10.1186/
s41239-019-0171-0
Zheng, L., Niu, J., Zhong, L., & Gyasi, J. F. (2021). The effectiveness of artificial intelligence on learn-
ing achievement and learning perception: A meta-analysis. Interactive Learning Environments, 1–15.
doi:10.1080/10494820.2021.2015693

KEY TERMS AND DEFINITIONS

AI Tools: Software programs equipped with artificial intelligence, designed to perform specific tasks
by learning and adapting based on the information and user interactions.
Enriching: Improving or enhancing the quality of something.
Higher Education: Level of schooling that follows secondary education, such as college, university,
or vocational training, where students pursue specialized studies and advanced degrees.
Inclusive Education: An educational approach that aims to ensure all students, regardless of their
backgrounds, abilities, or challenges, have equal access to learning opportunities.
Innovative Pedagogies: Teaching methods that introduce new ideas, creative approaches, or novel
techniques to enhance the learning experience.
Innovative Technology: Advanced or novel technological developments that introduce new methods,
ideas, or products.
Integration: The process of combining or incorporating different elements, systems, or groups to
work together effectively as a whole.
L2 Classroom: A learning environment where students are taught a second language that is not their
native tongue.
Language Acquisition: The process through which individuals learn a language, whether it be their
native tongue (first language acquisition) or an additional language (second language acquisition).
Language Learning Skills: Abilities and techniques used to effectively acquire language.
Linguistic Needs: Specific areas or aspects of language learning that require focused attention or
improvement, such as vocabulary, grammar, pronunciation, listening, speaking, reading, or writing skills.
Multidimensional Tools: Tools or resources that offer multiple features or capabilities, addressing
various aspects or needs within a single platform or system.

77
78

Chapter 5
A Qualitative Journey on
Instructors’ Perceptions
of Artificial Intelligence
in EFL Education
Nazmi Dincer
https://orcid.org/0000-0002-2901-5367
Turkish Air Force Academy, Turkey

Samet Bal
Turkish Airlines, Turkey

ABSTRACT
Artificial intelligence influences education, particularly language instruction. Despite its expanding
attention, few studies have examined teachers’ views on AI in education. This qualitative study explores
EFL teachers’ AI-related views and insights. The study uses semi-structured interviews with 21 instruc-
tors from diverse universities to uncover complex attitudes toward AI, pedagogical ideologies, perceived
benefits and drawbacks of AI, and privacy concerns. The study highlights four main themes: AI’s capac-
ity to adapt to individual learning needs, its influence on pedagogical dynamics, the need for technical
proficiency to integrate AI, and ethical and security issues related to AI use. These results highlight the
perceived benefits and challenges educators face when using AI and emphasize the need for continued
research to develop successful AI integration techniques for language instruction.

INTRODUCTION

The technological advancements of the digital era have catalyzed a significant metamorphosis across
different sectors of society, not least within the labor market, and more pointedly in education (Kannan
& Munday, 2018). The surge in Artificial Intelligence (AI) technologies, and their potential impact on
education, has captured the attention of both researchers and practitioners, provoking intriguing debates

DOI: 10.4018/979-8-3693-0872-1.ch005

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

and explorations (Popenici & Kerr, 2017). AI’s remarkable capacity for adaptive learning, bespoke
instruction, and student engagement presents a plethora of unexplored opportunities within modern
education (Chen et al., 2020). Simultaneously, it poses new challenges that necessitate a comprehensive
understanding of the real-world intricacies involved in its integration (Knox, 2020).
At the heart of this pedagogical metamorphosis, the teachers are the key actors harnessing these in-
novative technologies to enrich students’ learning experiences. Yet, a gap exists in the current research
landscape, with limited studies focusing on teachers’ perceptions towards AI integration in education and
specifically language classrooms (Haristiani, 2019). The attitudes, beliefs, and experiences of instructors
constitute a crucial determinant of the successful realization of AI-driven instruction and, consequently,
its impact on learner outcomes (Celik, 2017; Malik et al., 2022).
Examining the perspectives of EFL teachers warrants special attention due to the inherent complexities
of language instruction. Beyond the confines of subject-specific knowledge, language learning extends
into a wider ambit, including linguistic proficiency, cultural appreciation, and communicative skills
(Dodigovic, 2009). The incorporation of AI in this sensitive instructional ecosystem thus calls for a
more profound exploration of language teachers’ viewpoints and their interactions with these emerging
technologies.
While AI is not an unfamiliar concept in educational technology discourse, its accelerating advance-
ments and expanding influence warrant a refreshed and more focused scrutiny (Holmes et al., 2019).
Considering the broad spectrum of AI’s potential applications in language instruction, coupled with a
wide variety of teacher perspectives, the narrative surrounding AI integration is multifaceted and complex.
This qualitative study endeavors to unearth these narratives by probing the beliefs and insights of
EFL teachers concerning AI’s integration into language instruction. By broadening our comprehension
of teacher perspectives, this study aims to underpin more effective AI implementation strategies, thereby
enhancing language learning experiences and equipping teachers to adeptly navigate the ever-evolving
educational landscape. In this respect, this study seeks answers to the following questions:

1. How do EFL teachers perceive the use of AI in language classrooms?

2. What are the perceived benefits and challenges of AI in the language learning and teaching process
from the perspective of EFL teachers?
3. What concerns do EFL teachers have about the impact of AI on teaching and learning?

ARTIFICIAL INTELLIGENCE AND EDUCATION

Artificial Intelligence (AI), as a discipline, falls within the purview of computer science, specifically
dedicated to the design and development of software and hardware systems capable of mirroring facets
of human intelligence. The scope of these capabilities is quite expansive, including the ability to learn
from experiences and surroundings, apply gained knowledge to troubleshoot issues, comprehend and
process complex content, and refine performance continually through self-assessment and rectification
of errors (Clark, 2020). AI fundamentally aims at fabricating machines that can emulate human cogni-
tion and learning patterns.
The genesis of the term ‘Artificial Intelligence’ can be traced back to 1956 when John McCarthy
introduced it at the Dartmouth Conference, thereby marking the inception of AI as an independent aca-
demic discipline. The journey of AI has been characterized by alternating periods of intense enthusiasm

79

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

and ‘AI Winters’ - phases marked by diminished funding and interest due to inflated expectations and
consequent disappointments (Haenlein & Kaplan, 2019). However, the past two decades have witnessed
a consistent surge in AI interest and developments, catalyzed by exponential growth in computational
power, availability of vast datasets or ‘big data’, and advancements in learning algorithms, particularly
those associated with deep learning.
With its widespread applications across diverse sectors, including healthcare, transportation, and
finance, education has not remained untouched. The application of artificial intelligence to education,
known as AIEd, has been a topic of academic research for over three decades. This field explores learn-
ing in various settings, such as traditional classrooms and workplaces, with the aim of supporting formal
education and lifelong learning. AIEd combines interdisciplinary fields like AI, education, psychol-
ogy, neuroscience, linguistics, sociology, and anthropology to create adaptive learning environments
and other AIEd tools (Clark, 2020). These tools are designed to be flexible, inclusive, personalized,
engaging, and effective. The core objective of AIEd is to make educational, psychological, and social
knowledge explicit and precise, which is often left implicit (Self, 1998). In simpler terms, AIEd goes
beyond being a driving force behind smart educational technology; it also helps us gain deeper insights
into the process of learning (Luckin et al., 2016). For instance, it reveals how learning is influenced by
factors like socioeconomic context, physical environment, and technology. These insights can guide
the development of future AIEd software and enhance non-technological approaches to learning. AIEd
enables us to observe and understand the small steps learners take when acquiring knowledge in subjects
like physics, as well as identify common misconceptions (Lameras & Arnab, 2021). Teachers can then
apply this understanding in their classrooms. AI relies on computer software programmed to interact
intelligently with the world, requiring both knowledge about the world and algorithms for processing
that knowledge effectively.
The dynamic growth and widespread application of artificial intelligence across diverse sectors find
a mirrored reflection in the sphere of education. As of 2020, the global AI market boasted a valuation
of approximately $62.35 billion, demonstrating an expected compound annual growth rate (CAGR) of
40.2% from 2021 through to 2028, a testament to the expanding demand and assimilation of AI in various
industries (Cardano et al., 2023). In the educational domain, this growth trajectory is even more striking.
The value of AI within the education sector stood at $1.1 billion in 2019 and is projected to reach $8.0
billion by 2024, indicative of an astounding CAGR of 47.0% (Cardano et al., 2023). This rapid growth
underscores the acknowledged capacity of AI to revolutionize personalized learning, amplify learner
engagement, and optimize educational outcomes. The steady increase in AI investments in the educational
sector heralds a paradigm shift towards technologically enriched, individualized learning environments.
However, the swift integration of AI also highlights the essentiality of continuous research to effectively
understand and address associated challenges.
Artificial Intelligence (AI) finds its applications in the field of education in a myriad of ways, signifi-
cantly contributing to the technological advancement of learning processes. Examples of such integration
include the use of AI in instructional technologies like intelligent tutoring systems, automated grading
mechanisms, and chatbots (Clark, 2020; Heffernan & Heffernan, 2014). These AI-facilitated systems offer
extensive opportunities for all parties involved in the education process, as noted by Chen et al., (2020).
Historical examinations of AI’s educational usage have highlighted the system’s capabilities to enhance
student collaboration and tailor learning experiences to individual student’s needs (Luckin et al., 2016).
Furthermore, AI plays a vital role in organizing learning activities, offering adaptive feedback on learn-
ing progress (Koedinger et al., 2012), alleviating teachers’ workload in collaborative knowledge creation

80

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

(Roll & Wylie, 2016), and even predicting students’ academic trajectory, such as potential dropout risks
or admission possibilities (Popenici & Kerr, 2017).
AI also enables comprehensive profiling of students’ backgrounds (Cohen et al., 2017), consistent
monitoring of students’ academic progression (Swiecki et al., 2019; Gaudioso et al., 2012), and sum-
mative assessments, as observed in the case of automated essay grading (Vij et al., 2020; Yuan et al.,
2020; Okada et al., 2019). However, the current utilization of AI in education has yet to reach the levels
of adoption and integration seen in other sectors, like finance and health.
A successful transition to AI-based educational systems mandates the active involvement of all stake-
holders, particularly teachers, in the stages of AI development, from conception to integration (Langran
et al., 2020; Qin et al., 2020). The role of teachers remains pivotal to ensuring the effective and seam-
less inclusion of AI into the educational landscape, a factor crucial for maximizing the benefits that AI
promises to deliver in the realm of education (Malik et al., 2022).

ARTIFICIAL INTELLIGENCE IN EFL EDUCATION

Given the multifaceted nature of EFL learning, which involves gaining linguistic competence, promoting
communicative skills, and understanding cultural nuances, AI can play a critical role. The application
of AI within the realm of EFL teaching shows remarkable potential (AbdAlgane & Othman, 2023).
Through intelligent tutoring systems, adaptive learning platforms, and AI-powered language learning
applications, AI can address this diverse range of learning requirements. Yet, there has been a disagree-
ment among academics and educators over the use of AI technology in language learning environments
(Alshumaimeri & Alshememry, 2023).
Numerous studies highlight the advantages of AI in language acquisition since it offers the prospect
of personalized instruction. For instance, it has been discovered that AI systems can analyze learner input
(Alhalangy & AbdAlgane, 2023), evaluate the grammar skills of learners and offer advanced feedback
(Koraishi, 2023), and provide more useful grammatical review (Nagata, 1996). The majority of early
AI research focused on sentence structure, while more recent work demonstrates that AI can do more
as a result of advancements in computer technology. For example, the use of AI in language classrooms
has been shown to assist students in a number of ways, including by facilitating genuine interaction (Lu,
2018), supporting cooperative responsibilities (Jiang, 2022), strengthening reading comprehension (Bai-
ley et al., 2021), developing oral performance (Jeon, 2021), and boosting inspiration (Yin et al., 2021).
AI-powered educational systems can customize learning materials to align with each student’s learning
pace and language proficiency. This individualized approach to instruction, which can be challenging
to implement in traditional classroom environments, is facilitated by AI (Chen et al., 2020). AI allows
learners to receive immediate, tailored feedback on aspects of language use, including pronunciation
and grammar, promoting real-time language practice and enhancement. Furthermore, AI can simulate
conversational scenarios, offering EFL learners a non-judgmental environment to practice their English
skills. Such AI conversational platforms can be specifically designed to cater to learners’ unique interests
or needs, thereby boosting motivation and engagement (Coniam, 2014).
Notwithstanding these favorable arguments, other research had conflicting outcomes. Early on in its
development, the optimistic perspectives on artificial intelligence in the study of language were seen as
exaggerated (O’Brien, 1993) and misinterpreted (Last, 1989). In addition, while considering the potential
of AI in the course of the 90s, Salaberry (1996) expressed skepticism about its usefulness in acquiring

81

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

languages and instruction. Hu and Cooper (2014) propose that AI has little effect on students’ learning,
while other contemporary research argues that AI is not a valid means of instruction (Gallacher et al.,
2018). Additionally, AI-generated language is often unnatural and inappropriate (Sigge & Sumakul,
2021) and lacks contextual relevance (Wilson et al., 2021). Concerning the use of AI in classrooms, the
difficulties may stem from the constrained educational structure of AI applications (Zawacki-Richter,
2019) or the insufficient instructional knowledge of instructors (Sumakul, 2019).
It is a well-known fact that enriching EFL with AI is not devoid of hurdles. Debates surrounding
the AI’s capacity to interpret and teach cultural subtleties, the potential decrease in face-to-face human
interactions, privacy and security concerns related to student data, and the evolving role of the teacher
in an AI-empowered classroom persist (Langran et al., 2020; Luckin et al, 2016).
Despite these challenges, the promise that AI holds for EFL learning contexts is compelling and con-
tinues to kindle interest among educators and technologists. As this dynamic field continues to evolve,
the need to explore EFL teachers’ experiences and perceptions of AI grows, holding the potential to
guide the course of future AI integration strategies in language classrooms.

METHODOLOGY

In order to gain a rich and comprehensive understanding of teachers’ perceptions and experiences con-
cerning the application of Artificial Intelligence (AI) in English as a Foreign Language (EFL) teaching
settings, this study employed a qualitative research methodology. This approach was chosen due to its
suitability for exploratory research, as it enables the researcher to delve deeper into personal experiences,
perceptions, motivations, and emotions, which are often essential in understanding complex phenomena
such as the integration of AI in teaching.
An integral component of our qualitative approach was the utilization of semi-structured interviews.
Semi-structured interviews, by virtue of their flexible and open-ended nature, allowed the researchers
to gather detailed and nuanced data directly from the participants in their own words. Each interview
was conducted individually, spanned approximately 30 minutes, and was audio-recorded, subject to the
participant’s consent. The interview guide comprised a series of broad, open-ended questions pertaining
to their experiences and perceptions of AI tools, but the interviewers were also free to explore emerg-
ing themes and unexpected responses in depth. This approach not only ensured that the key research
questions were addressed but also allowed new ideas and perspectives to surface during the discussion.
In terms of data analysis, thematic analysis was used to interpret the interview transcripts. This involved
several steps: (1) transcribing the interviews, (2) getting familiar with the data, (3) identifying and coding
potential themes, (4) reviewing and refining the themes, and finally (5) defining and naming the themes
(Braun & Clarke, 2006). This rigorous process ensured a thorough and systematic analysis of the data.
The trustworthiness of the study was also considered. Techniques such as member checking, where
participants were given the opportunity to review and confirm the accuracy of their responses, and peer
debriefing, in which the research team collectively reviewed and discussed the findings, were conducted
to increase the validity and reliability of the results.
This qualitative research methodology, with its focus on capturing rich, detailed, and complex data,
was crucial in enabling a deep and holistic understanding of how EFL instructors perceive and experi-
ence the integration of AI in their teaching practices.

82

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

PARTICIPANTS

Table 1 illustrates that the study includes a total of 21 instructors, out of which approximately 57% are
female (12 instructors) and the remaining 43% are male (9 instructors). The average age for female in-
structors is approximately 36 years, while for male instructors; it’s about 35 years, signifying proximity
in age demographics between the genders. Considering their professional experience, the average years
of teaching for female instructors is about 9 years, with a range from 1 to 22 years. Similarly, the male
instructors have an average of about 9 years of experience, ranging from 4 to 18 years, suggesting a
comparable level of professional experience across both genders in the study.
It is noteworthy to highlight that institutional disparities may have a substantial impact on instructors’
viewpoints about the integration of artificial intelligence in EFL instruction. Variables such as the pres-
ence of resources, the characteristics of the student population, and the objectives of the institution might
influence their experiences and attitudes toward the incorporation of artificial intelligence. Teachers at
well-endowed private institutions may have more favorable perspectives as a result of their superior ac-
cess to artificial intelligence (AI) technologies, while educators in underprivileged public schools may
encounter difficulties in using such technology. Furthermore, the perspectives of teachers regarding AI in
EFL instruction might be influenced by their level of experience. Experienced instructors who have been
in the profession for a long time may exhibit greater skepticism or want more persuasion when it comes
to embracing new technology, due to their well-established teaching approaches. Conversely, recently
hired educators, who are often better acquainted with digital resources, may exhibit more receptiveness
and flexibility in incorporating artificial intelligence into their instructional methods.
In this study, purposeful sampling was implemented to gather information-rich cases that provide
in-depth insight into the integration of AI-supported applications in teaching EFL. This technique was
particularly suited for this study because it enabled the selection of instructors who have substantial
experience with the use of these AI tools in their teaching practices.
First, the initial candidate pool was identified from various foreign language schools across different
universities in Turkey. These were EFL instructors who were known, either through professional networks,
previous research, or institutional records, to have some level of engagement with AI applications in their
pedagogy. To refine this list, the researchers sent out an initial survey or conducted preliminary interviews
to gauge the extent of each instructor’s experience with the AI tools and their general tech-savviness.
This assisted researchers in determining whether they had ‘hands-on experience’, as highlighted in our
selection criteria. Next, researchers anayzed the specific AI applications the instructors used, focusing
on those who utilized a diverse range of tools. This ensured that the sample represented a wide spectrum
of AI applications in the classroom.
In addition to the profile of the instructors, Table 2 also provides an interesting snapshot of their
technological utilization in response to the question about their familiarity with AI-supported educational
applications. Instructors used these applications once or more than once for instructional purposes. The
most widely adopted application among the instructors is Duolingo, a language learning platform used
by 20 instructors. Grammarly, a writing assistant enhancing clarity and checking for plagiarism, is the
next most prevalent tool, being used by 19 instructors. Other notable applications include ChatGPT, an
AI chatbot used as a tutoring tool by 16 instructors, and Turnitin, a plagiarism detection tool, used by
15 instructors. Further down the list, Canva, Quillbot, and Achieve3000 are used by 12, 8, and 8 instruc-
tors respectively, signifying their importance in content creation and improving reading comprehension.
Transcription service Otter.ai and voiceover platform Murf.ai are used by 7 and 6 instructors respectively.

83

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

Video creation platforms Vyond and Synthesia are used by 5 instructors each. Lastly, the less prevalent
applications include Slide.ai for presentation generation, Knowji for vocabulary learning, ChatYoutube
for interactive video engagement, and Copilot for AI-assisted lesson plan generation, used by 3, 3, 2, and
1 instructor(s) respectively. This diversity of tools illustrates the wide range of digital resources being
harnessed by the participants in the teaching environment.

Table 1. Participants

Instructors Gender Age Years of Exp.

Instructor 1 Female 27 1
Instructor 2 Female 31 3
Instructor 3 Female 28 3
Instructor 4 Female 29 4
Instructor 5 Female 35 7
Instructor 6 Female 34 7
Instructor 7 Female 45 12
Instructor 8 Female 39 14
Instructor 9 Female 42 15
Instructor 10 Female 43 16
Instructor 11 Female 47 20
Instructor 12 Female 50 22
Instructor 13 Male 30 4
Instructor 14 Male 32 5
Instructor 15 Male 33 6
Instructor 16 Male 35 8
Instructor 17 Male 36 9
Instructor 18 Male 36 10
Instructor 19 Male 40 11
Instructor 20 Male 42 17
Instructor 21 Male 40 18

FINDINGS

This section illustrates the primary findings derived from the semi-structured interviews with 21 EFL
instructors with regard to their experiences and perceptions of Artificial Intelligence (AI) integration
in the classroom. The insights gathered have been arranged under four major themes: AI Adaptability,
Influence on Pedagogical Dynamics, Technological Proficiency, and Ethical and Security Concerns.
Each theme is further subdivided into several subthemes, allowing for a comprehensive exploration of
the many aspects of AI usage in the EFL teaching environment. The interview data has been analyzed
and is presented in a way that provides an in-depth understanding of the nuances and complexities of AI

84

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

in the educational realm while keeping the focus on the voices and lived experiences of the educators
themselves. The findings aim to offer a detailed picture of the current state of AI in EFL classrooms,
shedding light on both its potential advantages and the challenges it may pose.

Table 2. AI-supported applications

Number of
Application Information
Instruction
Duolingo To provide lessons in multiple languages, using a variety of interactive exercises 20
Writing assistant that helps users correct grammatical errors, enhance clarity and
Grammarly 19
engagement, and check for plagiarism
Chatgpt A chatbot that acts as a tutor 16
Turnitin To detect potential plagiarism 15
Canva To generate content 12
Quillbot A writing tool that improves the quality of written text 8
To improve reading comprehension, vocabulary, and writing proficiency by providing
Achieve3000 8
leveled reading materials tailored to individual skill levels.
To convert spoken language into written text, enabling real-time transcriptions, and note-
Otter.ai 7
taking
To convert text into lifelike speech using customizable voiceovers, enhancing the
Murf.ai 6
auditory experience of digital content.
Vyond To create grade animated videos 5
To create synthetic videos, enabling the generation of personalized video content without
Synthesia 5
traditional filming.
Slide.ai To generate presentation 3
Knowji To learn vocabulary 3
ChatYoutube To chat with YouTube videos by asking questions 2
Copilot To generate lesson plans with AI-generated templates 1

AI Adaptability

The first emergent theme was the adaptability of AI in EFL classrooms. This theme embodies sub-themes
such as personalization of learning, reinforcement of learning, supplementation in teaching, and acces-
sibility of instruction. Teachers largely recognized the value of AI in tailoring learning to individual
needs. “AI allows me to tailor the learning experience to each student’s unique needs and progress,”
shared one participant. The potential for AI to reinforce learning also emerged. Another teacher ex-
plained, “AI tools provide additional practice opportunities, reinforcing the knowledge acquired during
lessons.” The instructors also viewed AI as a supplement to traditional teaching, “AI can handle aspects
such as grammar checks, freeing me up for more interactive teaching,” revealed one participant. Lastly,
instructors valued the increase in instructional accessibility provided by AI, with one teacher noting,
“AI enables students to continue their language practice outside the classroom, fostering a continuous
learning environment.”

85

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

Table 3. The thematic framework of the data

Theme Subtheme Sample Codes

Customized lesson plans,
Personalization Adaptive learning exercises
Specific learning goals
Additional practice,
Reinforcement Reinforcing classroom lessons
Progress tracking

Adaptability Grammar checks,

Pronunciation correction
Teaching Supplementation
Automated writing check
Real-time error detection
Anytime availability,
Off-classroom language practice
Accessibility
Compatibility
Mobile
Facilitator role,
Content curator role
Shifting role of educators
Guide role
Support role
Integration of AI tools,
Modifying lesson plans,
Influence on teaching strategies
Impact on Personalized feedback
Pedagogy Interactive teaching
Automated grading,
Real-time performance tracking
Alteration of assessment methods
Formative assessment
Predictive analytics
Increased self-learning,
Change in student engagement patterns
Greater student participation
Comfort with tech tools,
Teacher tech-savviness
Previous experience with Edtech
Familiarity with AI Understanding AI functionality, Confidence in utilizing AI tools
Technological
Proficiency Training in AI tools,
Professional development
Tech support requirements
Technological glitches,
Adoption barriers
Difficulty in integrating AI tools
Protection of student data, Confidentiality of learner information
Privacy issues
Anonymity concerns

Ethical and Fear of AI misuse,

Misuse apprehensions
Security Unethical AI applications
Concerns Reliability of AI-generated results, Accuracy of AI language
Trust in AI
feedback
Policies and regulations Need for robust tech policies, Adherence to AI usage regulations

86

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

Influence on Pedagogical Dynamics

The second emergent theme encapsulated the impact of AI on teaching dynamics. This theme was clas-
sified into sub-themes like the evolving role of teachers, alteration of teaching strategies, modification
of assessment methods, and changes in student engagement. The role of teachers is seen to be shifting
in the face of AI integration, as one participant stated, “With AI, I’ve transitioned from being a mere
deliverer of information to more of a guide and facilitator in the learning process.” The influence on
teaching strategies was another prominent sub-theme. “Incorporating AI necessitated a revision of my
teaching approaches,” mentioned one teacher. Changes in assessment methodology were another facet,
“The use of AI tools for grading and providing immediate feedback has revolutionized our assessment
methods,” another participant highlighted. Teachers also noted a difference in student engagement after
the introduction of AI, with one stating, “The use of AI tools has sparked higher student involvement
and proactive participation.”

Technological Proficiency

The third theme, technological proficiency, was further categorized into teacher’s comfort with technology,
familiarity with AI, need for professional development, and barriers to AI adoption. Teachers’ comfort
levels with technology generally influenced their stance toward AI. One participant confessed, “While
I’m adept with tech tools in general, AI does pose a new learning curve.” The necessity for professional
development to fully harness AI was another key insight, “To use AI to its full potential in our classrooms,
more targeted training is required,” revealed another teacher. Several participants also discussed hurdles
they experienced while adopting AI, “Despite my competence with technology, integrating AI tools into
my curriculum has its challenges,” shared one participant.

Ethical and Security Concerns

The final theme encompassed ethical and security concerns related to AI usage in classrooms. This theme
is divided into sub-themes such as potential privacy issues, fear of misuse, trust in AI, and the need for
robust policies and regulations. Teachers expressed concern over data privacy, “While AI has potential,
the security of our students’ information is a crucial factor,” voiced one participant. Another echoed
similar sentiments regarding misuse, “AI is a powerful tool but could lead to problems if misused or if
it provides inaccurate feedback.” The reliability of AI also emerged as a concern, “How can we ensure
the AI’s outputs are consistently accurate and reliable?” questioned one educator. Lastly, participants
underscored the importance of firm policies and regulations, “Clear guidelines and regulatory policies
are necessary to ensure ethical application and prevent misuse of AI in classrooms,” shared another
participant.
In sum, these findings reveal the multifaceted perspectives of teachers toward the incorporation of
AI in EFL classrooms. The identified themes encompassed the practical applications and potential chal-
lenges of AI, indicating a need for comprehensive training for teachers, strategic integration of AI into
curriculum planning, careful attention to data security, and the development of robust policies for AI use
in educational settings. The nuanced insights gathered from the teachers’ experiences can contribute to
shaping more informed, effective, and ethical practices for the integration of AI in language education
moving forward.

87

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

PRACTICAL APPLICATIONS OF AI IN EFL EDUCATION

As for the practical implementation of AI in EFL Education, it is crucial to acknowledge that the sub-
sequent case studies are directly based on the experiences of the interviewed instructors in the present
investigation. These real-world instances exemplify a wide array of inventive ideas and tactics that
these educators have used in their classrooms. Every example demonstrates the use of AI technologies
in real-world scenarios, providing significant insights into their practical effectiveness and influence.
These tales not only demonstrate the adaptability of AI in language education but also provide specific
instances of its implementation, as described by the instructors themselves. Our objective is to narrow the
divide between theoretical comprehension and actual execution by illustrating the concrete advantages
and difficulties of incorporating AI into EFL teaching methods via the presentation of these scenarios.

Case: Implementing AI Chatbot for Interactive

Language Practice in a Flight School

A renowned aviation university in Turkey has included an AI-driven chatbot, known as “Sky Tutor”,
into its English language instruction program. The chatbot may be accessed using the following link:
https://chat.openai.com/g/g-hgsIGvQci-sky-tutor. The program’s objective was to improve the aviation
English proficiency of student pilots, a crucial competency for conducting international flight opera-
tions. The institution’s classroom management system included Sky Tutor. The trainee pilots utilized
the chatbot to participate in regular practice sessions, specifically targeting aviation-specific vocabulary
and phraseology, in addition to enhancing their overall English proficiency. The chatbot’s artificial intel-
ligence was optimized to prioritize aircraft communication protocols and international radiotelephony
expressions. The trainees exhibited significant progress in their skills in aviation English, displaying a
clear increase in their capacity to successfully communicate in simulated international flight settings.
The AI chatbot offered personalized attention and prompt feedback, which were crucial elements in the
trainees’ advancement. This instance serves as a prime example of the effective implementation of an
AI chatbot in the realm of specialized language instruction. The AI’s capacity to adjust to the precise
language requirements of aviation, along with the ease of online accessibility, made Sky Tutor an indis-
pensable tool in the trainees’ educational progression.

Figure 1. Customized GPT for aviation training

88

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

Case: Implementing AI for Vocabulary Practice

An instructor at a public university’s English language school included ChatGPT into the curriculum
to augment vocabulary acquisition. The approach included the instructor formulating precise prompts
pertaining to vocabulary subjects and instructing students on how to engage using ChatGPT. Students
used the AI technology to engage in exercises including new vocabulary within different scenarios,
receiving instant feedback on their usage and grammar. They participated in activities such as phrase
construction, synonym/antonym identification, and simulated contextual conversations. Each week,
pupils in the classroom were assigned distinct vocabulary subjects. Utilizing ChatGPT, individuals par-
ticipated in focused activities that included formulating sentences using unfamiliar terms, investigating
alternative words with similar or opposite meanings, and participating in simulated dialogues specifi-
cally designed to enhance their vocabulary. For example, when studying weather-related vocabulary,
students might request ChatGPT to generate phrases including these words, and thereafter construct their
own sentences for evaluation. During simulated dialogues, students engaged with ChatGPT in a man-
ner resembling real-life conversations, where they discussed the weather. This provided them with an
opportunity to learn vocabulary in a contextual manner. The practical and engaging method, along with
instant AI feedback, enhanced students’ comprehension and application of new terminology in real-life
situations. The AI’s flexibility allowed a customized educational encounter, accommodating the distinct
requirements and speed of each learner. This approach offered a more captivating and dynamic means
of acquiring language, surpassing conventional methods of rote memorizing. The constant availability
of ChatGPT allowed students to engage in language practice at any time, resulting in a more regular
and engaging learning experience. This instance emphasizes the significant impact of AI on language
teaching, namely in improving the extent and efficacy of vocabulary acquisition.

Case: Implementing AI-Based Text-to-Speech to Generate Listening Materials

At a higher education institution, an English teacher employed an innovative language learning method
by utilizing MURF.AI, an advanced text-to-speech technology, to produce realistic podcasts and audio
resources for classroom instruction. She understood the need to include relevant and practical material,
so she created scripts covering a wide range of subjects, including casual chats and in-depth debates on
contemporary global issues. These scripts were customized to suit the specific interests and educational
levels of her pupils. Utilizing MURF.AI’s technology, she was able to convert these texts into podcasts
that showcased a diverse array of authentic voices. The presence of many accents and speaking styles
was crucial since it provided students with exposure to the abundant range of English speech they would
experience in authentic scenarios. Every podcast was meticulously constructed to include aspects of nar-
rative, conversation, and informative material, making them not only instructive but also interesting for
the students. The listening sessions in the classroom were organized based on these podcasts that were
created by artificial intelligence. Following each session, the instructor organized activities like group
discussions, vocabulary assessments, and comprehension drills. The purpose of these exercises was to
strengthen listening comprehension skills and promote active involvement with the topic. Students often
engaged in activities that required them to contemplate the material, articulate their viewpoints, and
generate replies or alternative conclusions to the podcast tales, augmenting their abilities in critical think-
ing and creative language use. The use of AI technology in language instruction has shown remarkable
efficacy. Students indicated greater involvement and enhanced auditory understanding. The users valued

89

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

the podcasts’ authenticity, as it facilitated their adaptation to different English accents and colloquial
expressions. This greatly improved their comprehension of real-life language and boosted their confi-
dence in using English. Overall, this study illustrates the capacity of AI to transform language learning
by showcasing how technology can provide immersive, tailored, and very efficient learning situations.

Figure 2. Text-to-speech application

DISCUSSION

The discussions that arise from this study provide significant insights into the complex perceptions and
attitudes of EFL teachers toward the integration of AI in language classrooms. Four main themes emerged
from the qualitative analysis, each revealing intricate dimensions of teachers’ experiences and beliefs.
These themes, in turn, were classified into multiple sub-themes that further nuanced our understanding
of the dynamics at play. Each theme is discussed below, drawing connections with existing literature
and reflecting on the implications of the findings.

Adaptability of AI

The theme of “Adaptability of AI in EFL Teaching” emerged as a core concept in teachers’ perceptions
of AI, revealing their recognition of AI’s potential to significantly enhance language teaching and learn-
ing. First, a key advantage perceived by teachers regarding AI was its ability to foster “Personalization
of Learning”. This was characterized by AI’s ability to align instruction to each learner’s pace, ability,
and learning style. For example, one participant noted, “With AI, every student gets a unique learning
experience tailored to their strengths and weaknesses.” This perspective aligns with Chen et al.’s (2020)
findings, which highlighted the ability of AI-driven adaptive learning environments to offer individual-
ized education that caters to the diverse learning needs of students. Yet, as Clark (2020) cautions, while
personalization is a significant asset of AI, there is a need for educators to carefully balance personal-
ized learning with collaborative learning experiences that can foster social and communication skills.
“Reinforcement of Learning” emerged as another sub-theme, emphasizing the unique role of AI in
providing learners with additional practice opportunities outside formal classroom settings. One teacher
expressed, “AI-based tools enable students to practice their language skills. They provide that extra
practice that is often needed to truly master a foreign language.” This reflects Kannan and Munday’s
(2018) assertions, which lauded the reinforcement potential of AI in facilitating continuous practice for

90

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

students, thereby improving language acquisition. However, Holmes et al. (2019) advised that while
reinforcement is important, it should not be devoid of critical and creative thinking skills, which are
equally vital for comprehensive language learning.
“Supplementation in Teaching” was observed in teachers’ narratives which affirmed AI’s role in
aiding their instructional efforts. A teacher mentioned, “AI tools are not replacing us; they are support-
ing us, helping us teach more effectively. They handle routine tasks, giving us more time to engage with
students on a deeper level.” This aligns with Edwards and Cheok’s (2018) perspective, which depicted
AI as a tool to support and supplement human instruction, allowing teachers to focus more on fostering
student engagement and less on administrative tasks. Additionally, Scholars such as Chin, Wu, and Hong
(2011), Lee et al. (2008), and You et al. (2006) argue against the possibility or feasibility of artificial
intelligence assuming the role of teachers. They contend that AI lacks the necessary capabilities to fully
replace human educators in the classroom. Nonetheless, Lameras and Arnab (2021) have suggested that
while AI can supplement teaching, ongoing professional development for teachers is necessary to ensure
the effective implementation and use of AI tools in classrooms.
Lastly, “Accessibility of Instruction” underpinned the potential of AI in extending the reach of lan-
guage instruction beyond classroom boundaries. Teachers were appreciative of how AI-enabled learning
to happen anywhere, any time. One teacher shared: “AI breaks down walls; it allows learning to happen
everywhere. The classroom is not confined to four walls anymore.” This sentiment echoes Wang and
Chen’s (2020) research, which emphasized AI’s role in supporting continuous and ubiquitous learning,
thus increasing the accessibility of language instruction.

Impact on Pedagogy

The second central theme that emerged from the teachers’ perceptions was the “Impact on pedagogy”,
indicating their cognizance of the substantial implications of AI integration on their instructional practices.
This theme encompassed four critical sub-themes: Shifting Role of Educators, Influence on Teaching
Strategies, Alteration of Assessment Methods, and Change in Student Engagement Patterns. First, the
‘Shifting Role of Educators’ sub-theme was evident in teachers’ insights about how the integration of
AI is revolutionizing their roles within the classroom. As one teacher expressed, “With AI, our role is
changing from a knowledge provider to a learning facilitator.” This sentiment is congruent with the
findings of Holmes et al. (2019), who argued that the introduction of AI is transforming the traditional
role of teachers, moving them towards a more facilitative, guiding role. However, Cook (2020) advises
that in this transformative phase, educators must not lose sight of their crucial humanistic role in foster-
ing emotional and social learning, which is something AI cannot replace.
Teachers also highlighted the “Influence on Teaching Strategies” brought about by AI technologies.
One teacher noted, “AI has changed my teaching strategies; it enables me to use more interactive and
learner-centered methods.” This statement corroborates Bostrom and his colleagues’ (2014) research,
emphasizing that AI’s capabilities can lead to more student-centered pedagogical strategies, enhancing
both learning effectiveness and engagement. Yet, Larsen-Freeman (2019) warns of the need for pedagogi-
cal balance; while AI encourages innovative teaching strategies and traditional methods, emphasizing
direct teacher-student interaction, the sharing of knowledge and experiences, and real-time adjustment to
the learning flow according to student responses, still hold merit and can be effective in certain learning
scenarios. These methods allow for a high degree of emotional, cultural, and contextual nuance that AI,
despite its many benefits, currently cannot fully replicate (Buckingham, 2019). For instance, in teaching

91

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

language, nuances such as idiomatic expressions, cultural references, and the subtleties of verbal and
non-verbal communication can be better explained and modeled by human teachers. Moreover, traditional
methods like cooperative learning, group discussions, role-playing, storytelling, and many more, play
an essential role in promoting critical thinking, creativity, teamwork, and social skills among students
(Johnson & Johnson, 2009). These are competencies that an AI-driven pedagogical approach may not
be able to cultivate as effectively due to its algorithmic nature.
Another sub-theme of “Alteration of Assessment Methods’ emerged from teachers” perceptions
about the potential of AI to revolutionize assessment in the language classroom. An instructor stated, “AI
provides real-time feedback and can assist in regular assessments, making it easier for us to track and
measure students’ progress.” This echoes Hooda and his colleagues’ (2022) work, which highlighted the
potential of AI in providing immediate, personalized feedback, thereby enhancing formative assessment
processes. Nonetheless, as Griffin and Care (2014) point out, while computer-based assessments offer
promising advancements in assessment, human judgment and interpretation remain essential, particularly
in complex language assessments requiring nuanced evaluation. For example, evaluating a learner’s
proficiency in pragmatic skills, such as the appropriate use of language in various social contexts, or as-
sessing a learner’s ability to communicate creatively and effectively, require nuanced understanding and
interpretation that AI systems, as of now, cannot fully replicate. That’s to say; AI can efficiently evalu-
ate language learners’ vocabulary usage, grammatical structures, and pronunciation patterns, which are
largely rule-based aspects of language learning (Chen et al., 2020). It’s also worth noting that language
is not merely a system of rules; it is also a medium for expressing thoughts, emotions, and cultural nu-
ances, which may not always adhere strictly to predefined linguistic structures (Larsen-Freeman, 2019).
Lastly, the “Change in Student Engagement Patterns” sub-theme arose from teachers observing altera-
tions in how students interact and engage with the learning material due to AI. One teacher remarked,
“AI-based tools have brought about new engagement patterns. Students now spend more time learning
interactively rather than passively receiving information.” This aligns with Zheng et al.’s (2020) study,
which noted the transformative effect of AI on student engagement, encouraging active learning. However,
Alam (2021) reminds us that while AI can foster increased engagement, a one-size-fits-all approach is
insufficient, as different students engage differently with AI tools.

Technological Proficiency

In the theme of “Technological Proficiency”, the sub-themes of “Teacher tech-savviness”, “Familiarity

with AI”, “Professional development needs”, and “Adoption barriers” collectively address the competencies
and challenges teachers face while incorporating AI in EFL instruction. First, “Teacher tech-savviness”
is a crucial aspect that influences the effectiveness of AI implementation in the language classroom.
A high degree of competency and proficiency with technology among teachers can translate into more
seamless integration and better utilization of AI tools (Pilco et al., 2022). For example, a teacher who
is comfortable with technology is likely to exploit the benefits of AI-driven personalized learning more
effectively, creating adaptive learning paths for their students. On the other hand, the sub-theme “Famil-
iarity with AI” suggests the necessity of understanding specific AI functionalities, its capabilities, and
its limitations. This knowledge goes beyond general tech-savviness. Without this familiarity, teachers
may either underutilize the potential of AI or over-rely on it, ignoring areas where human instruction is
irreplaceable (Lameras & Arnab, 2021).

92

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

Addressing the “Professional development needs,” many teachers highlighted the need for appropri-
ate training to successfully integrate AI into their teaching. Research by Avci et al. (2020) has already
demonstrated that professional development programs that provide hands-on, context-specific training
in technology use significantly enhance teachers’ self-efficacy and willingness to integrate technology.
In the case of AI, such training would be beneficial not only in using AI tools but also in understanding
how these tools can be pedagogically integrated to improve language learning outcomes (Kannan &
Munday, 2018).
Finally, the sub-theme “Adoption barriers” brings attention to the practical challenges teachers face,
which include lack of time, resources, or institutional support. These barriers are consistent with those
found in previous research on educational technology integration (Malik et al., 2022). Addressing these
barriers would require systemic efforts at the school or district level to ensure adequate resources, in-
cluding time for teachers to learn and experiment with AI tools, technical support, and integration of AI
technologies into the curriculum and assessment methods.

Ethical and Security Concerns

The final theme of “Ethical and Security Concerns” encapsulates several pressing issues associated with
the increasing use of AI in educational settings, particularly within the EFL classroom. This includes
“Privacy Issues”, “Misuse Apprehensions”, “Trust in AI”, and the necessity for “Policies and Regula-
tions”. Starting with “Privacy Issues”, participants shared concerns regarding data collection, storage,
and potential misuse, echoing the broader societal concerns about AI and data privacy. These worries
are not unfounded; AI-driven educational tools collect vast amounts of data about learners to function
effectively (Clark, 2020). This data, if mishandled or misused, could potentially lead to privacy violations.
This concern aligns with similar findings from Qin et al. (2020), emphasizing the need for stringent data
privacy measures when implementing AI in education.
“Misuse Apprehensions” refer to fears that AI technology could be misused either by students, who
might rely excessively on AI for learning tasks thereby undermining their learning process, or by enti-
ties for commercial exploitation. As stated by Cardano et al. (2023), ensuring the ethical usage of AI in
education is a collective responsibility involving teachers, students, and AI tool developers.
Trust in AI” emerged as another sub-theme, reflecting teachers’ concerns about the accuracy and
reliability of AI tools. Indeed, the credibility of AI systems plays a significant role in their acceptance
and effectiveness in education. As Bostrom and Yudkowsky (2014) pointed out, trust in AI systems,
especially in their ability to aid learning without causing harm, is vital to the successful integration of
AI into the classroom.
The need for “Policies and Regulations” was a recurring concern among teachers. They noted the
absence of clear guidelines about the use of AI in education, particularly in relation to data privacy and
ethical usage. These findings are congruent with those of Luan et. al (2020), who highlighted the need
for appropriate regulation and governance mechanisms to address ethical and security issues related to
AI use in education.

93

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

CONCLUSION

The advent of AI presents a transformative potential in various sectors, and its implications for educa-
tion, particularly language teaching, are immense. Through this qualitative study, we sought to explore
and understand the perceptions of EFL teachers towards the incorporation of AI in language classrooms.
The study has revealed that EFL teachers hold multifaceted beliefs about AI integration into their
pedagogical practice. Broadly, these beliefs coalesce around four major themes, including the adaptability
of AI to individual learning needs, the impact of AI on teaching dynamics, the technological proficiency
needed for effective AI integration, and the ethical and security concerns associated with AI use.
Our findings underscore that AI, with its ability to provide personalized learning, reinforcement, and
accessible resources, offers significant potential to support language learning. However, AI’s influence
on teaching dynamics also necessitates a shift in teachers’ roles, strategies, and assessment methods,
and a change in student engagement patterns, further underscoring the need for professional develop-
ment and the cultivation of teachers’ tech-savviness and familiarity with AI. Moreover, the study also
highlighted the importance of addressing teachers’ concerns around privacy, misuse, trust, and the need
for clear policies and regulations related to AI use in education.
The insights derived from this study contribute to the evolving narrative around the integration of AI
in language education. They shed light on the complex dynamics that educators navigate in their attempt
to incorporate AI technologies into their classrooms. The responses also elucidate some of the potential
hurdles that need to be overcome, such as barriers to adoption, professional development needs, and the
necessity for policies and regulations governing AI use.
As we advance further into the digital era, the integration of AI into language classrooms will become
increasingly crucial. It is, therefore, of paramount importance that we continue to explore and understand
the nuances of this integration from the teachers’ perspectives. Such an understanding will guide the
development of more informed strategies for AI implementation, ultimately enriching language learning
experiences for students and empowering teachers in the evolving educational landscape. The study’s
findings, while illuminating, are also a launchpad for further inquiry. Additional research is needed to
explore these themes in different contexts, with varied student populations, and over an extended period
to fully comprehend the long-term implications of AI use in language teaching.
In conclusion, while AI offers exciting possibilities for language teaching, it also presents unique chal-
lenges. Addressing these challenges requires an informed, nuanced approach that balances the potential
benefits of AI with a commitment to ethical, pedagogically sound practices. As educators, policymakers,
and researchers, we are all stakeholders in this endeavor. The future of language teaching is undoubtedly
intertwined with AI, and it is our shared responsibility to navigate this path effectively and responsibly.

REFERENCES

AbdAlgane, M., & Othman, K. A. J. (2023). Utilizing artificial intelligence technologies in Saudi EFL
tertiary level classrooms. Journal of Intercultural Communication, 23(1), 92–99. Advance online pub-
lication. doi:10.36923/jicc.v23i1.124

94

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

Alam, A. (2021, November). Possibilities and apprehensions in the landscape of artificial intelligence in
education. In 2021 International Conference on Computational Intelligence and Computing Applications
(ICCICA) (pp. 1-8). IEEE. https://doi.org/10.1109/ICCICA52458.2021.9697272
Alhalangy, A., & AbdAlgane, M. (2023). Exploring the impact of AI on the EFL context: A case study of
Saudi universities. Journal of Intercultural Communication, 23(2), 41–49. doi:10.36923/jicc.v23i2.125
Alshumaimeri, Y. A., & Alshememry, A. K. (2023). The extent of AI applications in EFL learning
and teaching. IEEE Transactions on Learning Technologies. Advance online publication. doi:10.1109/
TLT.2023.3322128
Bailey, D., Southam, A., & Costley, J. (2021). Digital storytelling with chatbots: Mapping L2 participa-
tion and perception patterns. Interactive Technology and Smart Education, 18(1), 85–103. doi:10.1108/
ITSE-08-2020-0170
Bostrom, N., Yudkowsky, E., & Frankish, K. (2014). The Cambridge handbook of artificial intelligence.
In K. Frankish & W. M. Ramsey (Eds.), The ethics of artificial intelligence (Vol. 316, p. 334). Cambridge
University Press.
Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychol-
ogy, 3(2), 77–101. doi:10.1191/1478088706qp063oa
Cardona, M. A., Rodríguez, R. J., & Ishmael, K. (2023). Artificial Intelligence and the Future of Teaching
and Learning: Insights and Recommendations. U.S. Department of Education, Office of Educational
Technology. https://policycommons.net/artifacts/3854312/ai-report/4660267/
Celik, I., Dindar, M., Muukkonen, H., & Järvelä, S. (2022). The promises and challenges of artificial
intelligence for teachers: A systematic review of research. TechTrends, 66(4), 616–630. doi:10.1007/
s11528-022-00715-y
Chen, L., Chen, P., & Lin, Z. (2020). Artificial intelligence in education: A review. IEEE Access : Practi-
cal Innovations, Open Solutions, 8, 75264–75278. doi:10.1109/ACCESS.2020.2988510
Chin, K. Y., Wu, C. H., & Hong, Z. W. (2011). A humanoid robot as a teaching assistant for primary
education. In 2011 Fifth International Conference on Genetic and Evolutionary Computing (pp. 21-24).
IEEE. 10.1109/ICGEC.2011.13
Clark, D. (2020). Artificial intelligence for learning: How to use AI to support employee development.
Kogan Page Publishers.
Cohen, I. L., Liu, X., Hudson, M., Gillis, J., Cavalari, R. N., Romanczyk, R. G., Karmel, B. Z., &
Gardner, J. M. (2017). Level 2 Screening With the PDD Behavior Inventory: Subgroup Profiles and
Implications for Differential Diagnosis. Canadian Journal of School Psychology, 32(3-4), 299–315.
doi:10.1177/0829573517721127
Coniam, D. (2014). The linguistic accuracy of chatbots: Usability from an ESL perspective. Text & Talk,
34(5), 545–567. doi:10.1515/text-2014-0018
Dodigovic, M. (2007). Artificial intelligence and second language learning: An efficient approach to
error remediation. Language Awareness, 16(2), 99–113. doi:10.2167/la416.0

95

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

Edwards, B. I., & Cheok, A. D. (2018). Why not robot teachers: Artificial intelligence for addressing
teacher shortage. Applied Artificial Intelligence, 32(4), 345–360. doi:10.1080/08839514.2018.1464286
Gallacher, A., Thompson, A., Howarth, M., Taalas, P., Jalkanen, J., Bradley, L., & Thouësny, S. (2018).
“My robot is an idiot!”–Students’ perceptions of AI in the L2 classroom. Future-proof CALL: language
learning as exploration and encounters–short papers from EUROCALL, 70-76.
Gaudioso, E., Montero, M., & Hernandez-del-Olmo, F. (2012). Supporting teachers in adaptive educa-
tional systems through predictive models: A proof of concept. Expert Systems with Applications, 39(1),
621–625. doi:10.1016/j.eswa.2011.07.052
Griffin, P., & Care, E. (Eds.). (2014). Assessment and teaching of 21st-century skills: Methods and ap-
proach. Springer. doi:10.1007/978-94-017-9395-7
Haenlein, M., & Kaplan, A. (2019). A brief history of artificial intelligence: On the past, present, and future
of artificial intelligence. California Management Review, 61(4), 5–14. doi:10.1177/0008125619864925
Haristiani, N. (2019). Artificial Intelligence (AI) chatbot as language learning medium: An inquiry. In
Journal of Physics: Conference Series (Vol. 1387, No. 1, p. 012020). IOP Publishing. doi:10.1088/1742-
6596/1387/1/012020
Heffernan, N. T., & Heffernan, C. L. (2014). The ASSISTments ecosystem: Building a platform that
brings scientists and teachers together for minimally invasive research on human learning and teaching.
International Journal of Artificial Intelligence in Education, 24(4), 470–497. doi:10.1007/s40593-014-
0024-x
Hooda, M., Rana, C., Dahiya, O., Rizwan, A., & Hossain, M. S. (2022). Artificial intelligence for
assessment and feedback to enhance student success in higher education. Mathematical Problems in
Engineering, 2022, 1–19. Advance online publication. doi:10.1155/2022/5215722
Jeon, J. (2021). Exploring AI chatbot affordances in the EFL classroom: Young learners’ experiences
and perspectives. Computer Assisted Language Learning, 1–26. doi:10.1080/09588221.2021.2021241
Jiang, R. (2022). How does artificial intelligence empower EFL teaching and learning nowadays? A
review on artificial intelligence in the EFL context. Frontiers in Psychology, 13, 1049401. doi:10.3389/
fpsyg.2022.1049401 PMID:36467167
Kannan, J., & Munday, P. (2018). New trends in second language learning and teaching through the lens
of ICT, networked learning, and artificial intelligence. Círculo de Lingüística Aplicada a la Comuni-
cación, 76, 13–30. doi:10.5209/CLAC.62495
Knox, J. (2020). Artificial intelligence and education in China. Learning, Media and Technology, 45(3),
298–311. doi:10.1080/17439884.2020.1754236
Koedinger, K. R., Corbett, A. T., & Perfetti, C. (2012). The Knowledge‐Learning‐Instruction frame-
work: Bridging the science‐practice chasm to enhance robust student learning. Cognitive Science, 36(5),
757–798. doi:10.1111/j.1551-6709.2012.01245.x PMID:22486653
Koraishi, O. (2023). Teaching English in the age of AI: Embracing ChatGPT to optimize EFL materials
and assessment. Language Education and Technology, 3(1).

96

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

Lameras, P., & Arnab, S. (2021). Power to the teachers: An exploratory review on artificial intelligence
in education. Information (Basel), 13(1), 14. doi:10.3390/info13010014
Langran, E., Searson, M., Knezek, G., & Christensen, R. (2020, April). AI in teacher education. In Society
for Information Technology & Teacher Education International Conference (pp. 751-756). Association
for the Advancement of Computing in Education (AACE).
Larsen-Freeman, D., & DeCarrico, J. (2019). Grammar. In An introduction to applied linguistics (pp.
19–34). Routledge. doi:10.4324/9780429424465-2
Last, R. W. (1989). Artificial intelligence techniques in language learning. Halsted Press.
Lee, E., Lee, Y., Kye, B., & Ko, B. (2008). Elementary and middle school teachers’, students’, and
parents’ perception of robot-aided education in Korea. In EdMedia+ Innovate Learning (pp. 175-183).
Association for the Advancement of Computing in Education (AACE).
Lu, X. (2018). Natural Language processing and intelligent computer‐assisted language learning (ICALL).
The TESOL encyclopedia of English language teaching, 1-6. doi:10.1002/9781118784235.eelt0422
Luan, H., Geczy, P., Lai, H., Gobert, J., Yang, S. J., Ogata, H., Baltes, J., Guerra, R., Li, P., & Tsai, C.
C. (2020). Challenges and future directions of big data and artificial intelligence in education. Frontiers
in Psychology, 11, 580820. doi:10.3389/fpsyg.2020.580820 PMID:33192896
Luckin, R., Holmes, W., Griffiths, M., & Forcier, L. B. (2016). Intelligence unleashed: An argument for
AI in education. Pearson Education.
Malik, G., Tayal, D. K., & Vij, S. (2019). An analysis of the role of artificial intelligence in education
and teaching. In Recent Findings in Intelligent Computing Techniques: Proceedings of the 5th ICACNI
2017, Volume 1 (pp. 407-417). Springer Singapore. 10.1007/978-981-10-8639-7_42
Nagata, N. (1996). Computer vs. workbook instruction in second language acquisition. CALICO Jour-
nal, 53–75.
O’Brien, P. (1993). eL: AI in CALL. In M. Yazdani (Ed.), Multilingual multimedia. Bridging the lan-
guage barrier with intelligent systems (pp. 85–139). Intellect.
Okada, A., Whitelock, D., Holmes, W., & Edwards, C. (2019). e‐Authentication for online assessment: A
mixed‐method study. British Journal of Educational Technology, 50(2), 861–875. doi:10.1111/bjet.12608
Pace-Sigge, M., & Sumakul, D. T. (2021). What teaching an algorithm teaches when teaching students
how to write academic texts. Linguistic, Educational and Intercultural Research 2021 (LEIC Research
2021), 78.
Qin, F., Li, K., & Yan, J. (2020). Understanding user trust in artificial intelligence‐based educational sys-
tems: Evidence from China. British Journal of Educational Technology, 51(5), 1693–1710. doi:10.1111/
bjet.12994
Roll, I., & Wylie, R. (2016). Evolution and revolution in artificial intelligence in education. International
Journal of Artificial Intelligence in Education, 26(2), 582–599. doi:10.1007/s40593-016-0110-3

97

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

Salaberry, M. R. (1996). A theoretical foundation for the development of pedagogical tasks in computer-
mediated communication. CALICO Journal, 14(1), 5–34. doi:10.1558/cj.v14i1.5-34
Salas-Pilco, S. Z., Xiao, K., & Hu, X. (2022). Artificial intelligence and learning analytics in teacher
education: A systematic review. Education Sciences, 12(8), 569. doi:10.3390/educsci12080569
Self, J. (1998). The defining characteristics of intelligent tutoring systems research: ITSs care, precisely.
International Journal of Artificial Intelligence in Education, 10, 350–364.
Selwyn, N. (2019). Should robots replace teachers?: AI and the future of education. John Wiley & Sons.
Steenbergen-Hu, S., & Cooper, H. (2014). A meta-analysis of the effectiveness of intelligent tutoring
systems on college students’ academic learning. Journal of Educational Psychology, 106(2), 331–347.
doi:10.1037/a0034752
Sumakul, D. T. (2019). When robots enter the classrooms: Implications for teachers. In International
Conference on Embedding Artificial Intelligence (AI) in Educational Policy and Practice for Southeast
Asia, Jakarta, Indonesia. SEAMEO SEAMOLEC.
Swiecki, Z., Ruis, A. R., Gautam, D., Rus, V., & Williamson Shaffer, D. (2019). Understanding when
students are active‐in‐thinking through modeling‐in‐context. British Journal of Educational Technology,
50(5), 2346–2364. doi:10.1111/bjet.12869
Vij, S., Tayal, D., & Jain, A. (2020). A machine learning approach for automated evaluation of short
answers using text similarity based on WordNet graphs. Wireless Personal Communications, 111(2),
1271–1282. doi:10.1007/s11277-019-06913-x
Wilson, J., Ahrendt, C., Fudge, E. A., Raiche, A., Beard, G., & MacArthur, C. (2021). Elementary teach-
ers’ perceptions of automated feedback and automated scoring: Transforming the teaching and learning
of writing using automated writing evaluation. Computers & Education, 168, 104208. doi:10.1016/j.
compedu.2021.104208
Yin, J., Goh, T. T., Yang, B., & Xiaobin, Y. (2021). Conversation technology with micro-learning: The
impact of chatbot-based learning on students’ learning motivation and performance. Journal of Educa-
tional Computing Research, 59(1), 154–177. doi:10.1177/0735633120952067
You, Z. J., Shen, C. Y., Chang, C. W., Liu, B. J., & Chen, G. D. (2006). A robot as a teaching assistant in
an English class. In Sixth IEEE International Conference on advanced learning technologies (ICALT’06)
(pp. 87-91). 10.1109/ICALT.2006.1652373
Yuan, S., He, T., Huang, H., Hou, R., & Wang, M. (2020). Automated Chinese essay scoring based on
deep learning. CMC-Computers Materials & Continua, 65(1), 817-833. https://doi.org/.2020.010471
doi:10.32604/cmc
Yurtseven Avci, Z., O’Dwyer, L. M., & Lawson, J. (2020). Designing effective professional develop-
ment for technology integration in schools. Journal of Computer Assisted Learning, 36(2), 160–177.
doi:10.1111/jcal.12394

98

A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

Zawacki-Richter, O., Marín, V. I., Bond, M., & Gouverneur, F. (2019). Systematic review of research on
artificial intelligence applications in higher education–where are the educators? International Journal
of Educational Technology in Higher Education, 16(1), 16–39. doi:10.1186/s41239-019-0171-0

KEY TERMS AND DEFINITIONS

Artificial Intelligence: A digital realm where machines mimic human cognition to solve tasks.
Artificial Intelligence in Education: Infusing smart algorithms into learning environments to en-
hance teaching and student performance.
CAGR: CAGR stands for Compound Annual Growth Rate, which is a measure used to express the
mean annual growth rate of an investment over a specified time period longer than one year.
EFL: It stands for “English as a Foreign Language” which refers to the study or learning of English
by speakers with different native languages.
Generative Artificial Intelligence: The branch of AI that crafts new content based on patterns from
data.
Large Language Models: Massive digital libraries trained on vast text data to predict and produce
language.
Technological Proficiency: It refers to teachers’ ability to effectively use and integrate technology
in their teaching practices.

99
A Qualitative Journey on Instructors’ Perceptions of Artificial Intelligence

APPENDIX

Interview Questions

1. What are your initial thoughts about the integration of Artificial Intelligence (AI) in language
teaching?
2. Can you describe any past experiences you have had with using technology, particularly AI, in your
classroom?
3. How do you perceive AI could assist your language classroom?
4. Do you think AI could be a useful tool to facilitate language practice for your students? Could you
provide some examples?
5. In what ways do you believe AI could enhance learner motivation in language learning?
6. Do you have any concerns about the impact of AI on your role as a teacher? Could you elaborate?
7. How do you think AI could affect student-teacher interactions?
8. What are your thoughts on the potential benefits and drawbacks of using AI in the classroom?
9. Do you have any privacy concerns related to the use of AI in the classroom?
10. How confident do you feel about your competency in using AI effectively for language teaching?
11. Can you comment on the availability and effectiveness of technical support for AI integration in
your school?
12. How have your pedagogical beliefs shaped your perspectives on AI integration in language education?
13. What kind of changes do you foresee in the teaching and learning process with AI integration in
the future?
14. How would you like to be supported as a teacher in order to enhance the use of AI in your classroom?

100
101

Chapter 6
AI-Powered Lesson Planning:
Insights From Future EFL Teachers

Banu Çiçek Başaran Uysal

https://orcid.org/0000-0002-4978-0891
Eskisehir Osmangazi University, Turkey

İlknur Yüksel
Eskisehir Osmangazi University, Turkey

ABSTRACT
This chapter explores the integration of artificial intelligence (AI) into language education, focusing
on the perspectives of pre-service English as a foreign language (EFL) teachers. Employing a mixed-
methods approach, the study investigates the effectiveness of AI-powered lesson plans, specifically
designed for teaching writing to 5th-grade students. Through a comprehensive evaluation rubric and
qualitative analysis, the research identifies strengths, areas for improvement, and suggested changes in
AI-generated lesson plans. Findings highlight the tool’s success in engagement, appropriateness, and
overall structure, while indicating challenges in differentiation and assessment. The chapter concludes
with implications for teacher training in AI literacy, emphasizing the need for educators equipped to
harness the potential of AI in diverse language teaching settings.

INTRODUCTION

In the dynamic domain of technology, it is rare for a groundbreaking advancement to get noticed and
exert impact as fast as ChatGPT has. Recently, this AI-powered language model has rapidly received
global appeal, captivating both experts and casual internet users with its remarkable powers. Generative
AI has been applied in various ways to support language education. It has the potential to revolutionize
language education by providing innovative tools and approaches to enhance language learning and
teaching. These tools can provide more interactive and personalized language learning experiences for
students (Lee et al., 2022); immediate feedback on learners’ language (Fu et al., 2020); and authentic

DOI: 10.4018/979-8-3693-0872-1.ch006

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

AI-Powered Lesson Planning

language practice (Bibauw et al., 2019). While AI has been increasingly incorporated into K–12 educa-
tion, little research has been conducted on the trust and attitudes of teachers towards the use and adoption
of AI-powered educational technology (Nazaretsky et al., 2022).
Teachers’ perspectives and conceptions of employing AI in schools are also crucial to consider when
understanding how generative AI influences pedagogy and learning. Analyzing and comprehending the
adoption of AI is of great significance but challenging (Pedró et al., 2019). As with most new technol-
ogy, teachers need to be equipped with AI literacy such as providing hands-on activities (Lee & Perret,
2022) to provide an understanding of the benefits and challenges of using AI in language teaching and
learning. Thus, integration of AI to teacher education is of great importance. The pre-service teachers
should be trained how and when to use AI, and how to improve their teaching performance with AI-
powered applications.
Lesson planning is one of the crucial steps where teachers will decide on the technology integration
to enhance the overall quality of teaching (Kehoe, 2023). Lesson planning is a roadmap for teachers
to address the diverse needs and preferences of learners, promoting inclusive and equitable education.
Additionally, for pre-service teachers, lesson planning is a critical component in the development of
pedagogical competence, as it enables them to reflect on, modify and implement lesson plans, assess
student learning, and create effective learning media and select and apply effective learning techniques
and tools. (König, Bremerich-Vos, Buchholtz, Fladung, & Glutsch, 2019). AI integration starts at lesson
planning where teachers decide on where, how, and why to use AI (Kehoe, 2023).
Additionally, AI could help teachers to design effective lessons at the first step of lesson prepara-
tion. It has the capacity to greatly revolutionize the process of lesson planning in education. First, AI
systems can scan massive volumes of educational data to detect student learning patterns, strengths, and
weaknesses, helping teachers create more personalized and engaging classes. AI can anticipate student
concerns and help teachers address them by using predictive analytics (Yildirim, Arslan, Yildirim, &
Bisen, 2021). AI-powered systems may also select and recommend instructional articles, videos, and
interactive materials, saving teachers’ time. AI-driven evaluation technologies can also provide real-time
feedback on student achievement, allowing teachers tailor lessons to specific learning needs. In the end,
AI can help teachers improve lesson planning, engage students, and create more inclusive learning envi-
ronments (Kehoe, 2023). However, the studies on what teachers think about AI-powered lesson planning
are scarce in literature. In fact, it is crucial to investigate teachers’, especially pre-service teachers’ views
on the benefits or hinders of AI in lesson planning process as they are the ones who will or will not use
AI in lesson planning and their perspectives could reveal what they need to use AI in the process and
how AI could be use more effectively in learning and teaching process.
Addressing this need, this chapter aims to show how future EFL teachers perceive the integration of AI
technologies like ChatGPT in their lesson planning process. Pre-service teachers’ views on AI-powered
lesson planning can help create targeted professional development programmes that give pre-service
teachers the skills and expertise to use these technologies effectively, to explore the problems and ethi-
cal dilemmas of AI integration in education, preparing future educators to handle complex technology
issues in the classroom. AI-powered lesson planning from the perspective of pre-service teachers can
help stakeholders improve digital teacher training by being more informed, flexible, and responsive.
Thus, it can be claimed that exploring the evaluations and beliefs of future teachers using AI for their
teaching preparation, could shed light on the effectiveness and practicality of in such tools in educational
settings. Additionally, this research can inform the development of training programs that specifically
address the needs and concerns of EFL teachers incorporating AI into their teaching practices.

102

AI-Powered Lesson Planning

This chapter investigates the evaluations and beliefs of English as a Foreign Language (EFL) pre-
service teachers who explored the potential of ChatGPT for creating lesson plans for young learners.
After discussing the AI technologies in language teaching and teacher education, the results are presented
and discussed accordingly.

LITERATURE REVIEW

AI in Language Teaching

The increasing use of Artificial intelligence (AI) in education (i.e., machine learning, adaptive learn-
ing, natural language processing, and data mining (Pokrivčáková, 2019)) highlights AI’s potential to
revolutionize learning and teaching. The incorporation of AI in language education has resulted in the
creation of AI-powered digital learning applications that aid in language acquisition. For example, Ghali
et al. (2018) examined the efficacy of an artificial intelligence tool known as the Intelligent Tutoring
System in the context of grammar instruction. The study found that by giving students individualized
instruction based on student performance data and quick feedback on their responses, this application
enhanced learner’s comprehension of grammar. In a similar vein, Dewi et al. (2021) investigated AI-
powered platforms like Duolingo, Google Translate, and Grammarly to validate whether they improve
language proficiency. The study’s findings suggest that AI has a positive impact on English language
learning and should be included to improve student learning outcomes. Moreover, Fitria (2021) recom-
mended the use of Grammarly, an AI-powered software, to enhance students’ writing proficiency. In
addition, Toncic (2020) proposed that AI grammar checkers provide significant benefits to instructors
by minimizing their workload when grading students’ papers. Some of these applications utilize AI-
enabled automatic scoring systems, which have been shown to enhance learners’ motivation to continue
studying (Fu et al., 2020).
In addition to these AI-powered platforms, chatbots have been popular as innovative tools in lan-
guage teaching, offering unique opportunities to enhance language learning experiences. For example,
ChatGPT can be used by learners in text-based tasks ranging from simple inquiries to more complex
assignments. Kasneci et al. (2023) investigated the efficacy of ChatGPT in assisting university students
with research and writing assignments and detected that ChatGPT improves students’ abilities in critical
thinking and problem-solving.
Critical viewpoints on AI’s use in education highlight its potential to revolutionize education by en-
hancing efficiency and customizing learning experiences. However, concerns include incorrect use of
AI technology, changing roles of instructors and students, and social and ethical issues. It is crucial to
approach AI with caution, avoiding its default supremacy. The integration of AI brings unprecedented
potential but also presents complex obstacles, causing a paradigm change in teaching and learning.
Ethical implications include widespread acceptability and substantial difficulties, economic injustice,
transparency, speed, and a human-centered approach (Verdegem, 2021). The use of AI in education
also raises issues regarding fair access to computing infrastructure and equipment, transparency, and
speed. Ultimately, it is essential to take a cautious and deliberate approach to AI integration, addressing
the accompanying obstacles, ethical concerns, and providing fair access to its advantages (Williamson,
Eynon, Knox, & Davies, 2023).

103

AI-Powered Lesson Planning

Teachers’ Perspectives on AI

As Yau et al. (2022) highlighted, there is a need to take teachers’ perspectives into account when de-
signing ecologically valid AI education programs. In line with this argument, several studies have been
carried out to explore teachers’ viewpoints on the use of AI-powered tools in educational settings (Al
Darayseh, 2023; Kuleto et al., 2023). The majority of these studies affirm that teachers hold favorable
attitudes towards integrating chatbots into language learning and teaching (An et al., 2023; Pokrivčáková,
2019; Sütçü & Sütçü, 2023). Multiple studies on ChatGPT have demonstrated positive attitudes among
educators toward its application in education (Limna et al., 2023; Rudolph et al., 2023), despite notable
ethical concerns and limitations (Willems, 2023; Zhai, 2022).
The tech-savvy students appreciate its impressive functionalities, while teachers are both astonished
and concerned. Teachers’ main concerns about ChatGPT is its potential for academic misconduct, par-
ticularly regarding cheating (Willems, 2023) The AI-powered chatbot is capable of engaging in complex
discussions based on human input, and it can also do diverse jobs like composing essays or finishing
examinations. There is a possibility that students may exploit the chatbot to plagiarize replies or seek
assistance in completing tasks, potentially engaging in cheating. Furthermore, there is apprehension re-
garding the potential adverse effects of employing ChatGPT on students’ educational encounters (Zhai,
2022). The AI-powered tool has the capability to produce conversational replies based on user input, but
it lacks the ability to instruct students on critical thinking or the cultivation of original ideas. There is
concern that students may excessively depend on the chatbot and rely on it for problem-solving instead of
cultivating their own ideas, perhaps leading to a significant deterioration in the quality of learning results.
Rudolph et al. (2023) proposed that learners may get advantages from experiential learning by using
the potential of ChatGPT to provide diverse problem-solving situations. ChatGPT offers the option for
students to have individualized training sessions. Hence, AI-marking may reduce the burden of mark-
ing for instructors, enabling them to allocate more time towards class preparation. ChatGTP provides
significant benefits specifically tailored for learners.
Baskara and Mukarto (2023) conducted a study that revealed the efficacy of ChatGPT in reducing
the workload of instructors. The authors highlighted the utility of ChatGPT in supporting educators with
tasks such as designing lesson plans, creating educational resources, and facilitating classroom activities.
Similarly, Kasneci et al. (2023) supported this assertion by stating that ChatGPT has the potential to
reduce the workload of instructors by providing personalized resources and feedback. This allows them
to focus on other important aspects of teaching, such as offering captivating and interactive sessions.
Zhai (2022) verified the significance of ChatGPT in evaluating the academic achievements of students.
According to the study, the tool can provide students with automated assessment and feedback, as well
as assistance in proofreading and modifying their written assignments. The study conducted by Moore
et al. (2022) provided more support for this assertion by demonstrating that ChatGPT can aid instructors
in evaluating students’ answers. Rudolph et. al. (2023) highlighted the substantial assistance provided by
ChatGPT in analyzing and evaluating student performance. This includes generating tasks, quizzes, and
assignments, assessing student work, and offering valuable comments tailored to individual students.

AI in Teacher Education

Several studies have discussed the benefits of generative AI technologies like ChatGPT, to help teachers/
instructors prepare for their teaching. Van der Berg & du Plessis (2023) outline the use of ChatGPT to

104

AI-Powered Lesson Planning

create customized scenarios for assessing and critically evaluating lesson plans. Aldeman et al. (2021)
show how generative AI technologies can foster inspiration and encourage self-reflection in teachers.
Huang et al. (2023) emphasize how AI can enhance professional development through teaching assess-
ment models and recommendations for better teaching methods. Finally, Liu et al. (2020) show that AI
can provide automated language project assessment and individualized multimodal feedback.
In order to fully benefit from generative AI technologies, however, teachers require effective train-
ing to understand what such tools offer and how best they can be used to help prepare for teaching and
learning. Dincer (2018) shows how instructors feel challenged when trying to incorporate technology
into their teaching and concludes that they require training to properly deploy instructional technology.
Similarly, Liden and Nilros (2020) argue that teachers need to be provided with detailed instruction such
as the effective use of chatbots, how to integrate them into existing lesson plans, and how to monitor
student engagement and achievement to effectively integrate chatbots into pedagogical methodologies.
Adding such training into teacher education, especially into pre-service education, is thus critical to
ensure a competent use of AI-powered tools in language learning and teaching. As such training is fairly
new and improvement is crucial, the study described in this chapter examines the critical evaluation of
AI-powered lesson plans by pre-service EFL teachers.
As the first step to improve teacher education programs with training on the use of AI-powered tools,
pre-service teachers’ perspectives and evaluations of AI-powered ramifications should be examined. Ad-
dressing this, the study investigating the EFL future teachers’ critical evaluations of AI-powered lesson
plans is presented in the following sections.

RESEARCH METHODOLOGY

This study used a mixed-methods approach, which allows simultaneous collection and analysis of both
quantitative and qualitative data. This research methodology is in line with the study’s objective, which
is to extensively investigate the lived experiences and perspectives of pre-service teachers in the context
of language instruction. Additionally, the use of a mixed-methods design derives from its adaptability,
which permits the incorporation of various data sources to obtain a broader understanding of the research
inquiries (Creswell, 2012). This methodology is especially useful for researching complex phenomena,
such as the incorporation of artificial intelligence into language instruction, for which a single approach
could not adequately capture the complexity and breadth of the phenomenon. This design made it pos-
sible to provide a comprehensive and complementary analysis of the various facets of AI integration in
language instruction.

The Aim of the Study

This study aims to explore and understand how pre-service English as a Foreign Language (EFL) teach-
ers assess the effectiveness of lesson plans powered by AI, specifically ChatGPT. The primary focus is
on gaining insights into the perspectives, criteria, and judgments employed by pre-service EFL teachers
when evaluating the impact and appropriateness of AI-generated lesson plans. Through a comprehensive
examination of their assessments, the research seeks to contribute valuable insights into integrating AI in
educational practices, particularly within the context of language education. Accordingly, the following
research question has been asked within the scope of the study:

105

AI-Powered Lesson Planning

• How do pre-service English as a Foreign Language (EFL) teachers assess the effectiveness of les-
son plans powered by artificial intelligence (AI)?

Participants of the Study

The study involved a diverse group of 43 college students who were actively engaged in a comprehensive
training program to become proficient English as a Foreign Language (EFL) teachers. The participants,
aged between 21 and 23, were selected from the third year of the undergraduate program. Of the 43
participants, 17 were male and 26 were female, contributing to a balanced sample. Convenience sam-
pling was chosen as the selection process to accommodate the participants’ availability and willingness
to participate in the study. This diverse group of college students provided valuable insights into the
integration of AI in language instruction, considering their current training and future career aspirations
as EFL teachers.
The participants were enrolled in two key English Language Teaching (ELT) methodology courses,
specifically “Teaching Language Skills” and “Teaching English to Young Learners.” These courses
played a fundamental role in their professional development as they inquired into both the theoretical
foundations and practical aspects of teaching English. The curriculum of these courses included careful
exploration of pedagogical theories and methodologies, preparing the participants with a solid under-
standing of the complexities of language teaching. Additionally, these courses incorporated theory with
in-class demonstrations, where the prospective teachers actively applied theoretical knowledge to real
classroom scenarios. Additionally, as a requirement of these courses, the participants were expected to
write ELT lesson plans to accompany the in-class teaching demonstrations. The participants not only
learned about effective teaching strategies but also had the opportunity to enhance their teaching practice
through hands-on experience.

Data Collection Procedures and Tools

The authors employed a three-step data collection process to unravel the beliefs of future EFL teachers
concerning the use of artificial intelligence in lesson planning. In the initial phase, participants engaged
in the creation of AI-powered EFL lesson plans, specifically designed for teaching writing to 5th-grade
students. As illustrated in Figure 1, the prompt used to generate lesson plans was as follows: “Write me
a lesson plan for Turkish learners of English in 5th grade to improve their writing skills. The topic of the
lesson is superheroes, and the duration is 90 minutes.” All of the participants used the same prompt to
create AI-powered lesson plans. This immersive experience aimed not only to familiarize the participants
with ChatGPT but also to evaluate its practical utility in the pedagogical context.

Figure 1. Screenshot of the prompt for AI-generated writing lesson plan for 5th graders

106

AI-Powered Lesson Planning

As participants explored the hands-on lesson planning facilitated by ChatGPT, the subsequent phase
involved a comprehensive assessment of the effectiveness of the generated lesson plans (Figure 10 and
Figure 11 in the Appendix). The authors decided to employ an AI-powered rubric for evaluating the
AI-generated lesson plans (Table 3 in the Appendix). The reason was the inherent alignment between
the tool’s capabilities and the nature of the study. GPT, or Generative Pre-trained Transformer, is a lan-
guage model designed to generate coherent and contextually relevant text based on the input it receives.
Given the complexity of language and the pedagogical considerations involved in crafting a rubric for
an AI-generated educational resource, utilizing a rubric generated by the same AI system provided a
harmonious and contextually appropriate framework. This approach aimed to maintain consistency
in linguistic patterns, educational terminology, and evaluative criteria, thereby enhancing the rubric’s
relevance to the specific characteristics of the GPT-generated lesson plans.
The AI-written rubric was then reviewed and edited by the authors based on the literature (Carlson
et al., 2023; Dwivedi et al., 2023). After the designing process, the final tool emerged as a structured
5-point evaluation rubric, comprising 30 items and 10 sub-dimensions. The internal consistency of the
rubric, as measured by Cronbach’s alpha, was found to be .875, indicating high internal consistency
(Creswell, 2012). This high level of internal consistency suggests that the evaluation rubric is reliable
and consistent in measuring the effectiveness of the generated lesson plans. Additionally, the use of a
structured 5-point evaluation rubric with 30 items allows for a comprehensive assessment of various
aspects of the lesson plans, ensuring a thorough evaluation process. By employing the rubric, the par-
ticipants were asked to examine the AI tool’s capacity to yield desired learning outcomes, construct
coherent lesson structures, present meaningful content, and ensure the overall appropriateness of the
lesson plans for the specified student profile.
Following the quantitative assessment, participants were prompted to articulate their evaluations in a
qualitative format. This crucial step aimed to unearth the underlying rationale behind their rubric scores.
Participants were encouraged to provide detailed justifications, offering insights into the specific aspects
of the AI-generated lesson plans that influenced their scoring. This qualitative layer added depth to the
evaluation process, enriching the understanding of the participants’ perceptions and preferences. The
final phase of data collection inquired into the participants’ beliefs about the integration of AI in language
teaching and its potential impact on their professional development. For this phase, a series of probing
questions were addressed to the participants. The participants were asked to report on the prospect of
incorporating ChatGPT into their future professional endeavors, to reflect on alternative applications
of the tool in language teaching, and to consider how they could leverage the AI tool for their personal
growth as English language teachers. Questions such as “Do you think you will use this tool in your
professional life?” inquired about the participants’ inclination toward practical adoption. The inquiry
into other potential uses of ChatGPT for language teaching aimed to uncover innovative perspectives
and applications beyond the immediate context of lesson planning. Meanwhile, questions like “How can
you use this tool for improving yourselves as English language teachers?” examined the participants’
introspective analysis, encouraging them to envision the tool as a catalyst for continuous professional
development. An overview of the data collection procedures can be viewed in Figure 2 below.
This triangulation of data—quantitative evaluation scores, qualitative justifications, and beliefs ex-
pressed through open-ended questions—enabled the researcher to gain a comprehensive understanding of
participants’ experiences and perspectives. The data collected from the participants allowed the researcher
to explore the tool’s effectiveness not only in lesson planning but also in broader educational contexts.
The participants’ reflections on AI written lesson planning would reveal their teaching philosophies,

107

AI-Powered Lesson Planning

priorities and beliefs. By considering both quantitative evaluation scores and qualitative justifications, the
researcher gained a holistic understanding of the participants’ experiences and perspectives, ultimately
providing a rich foundation for future research and implementation of the tool.

Figure 2. Overview of the data collection procedures

Data Analysis

To investigate the insights garnered from the evaluation rubric, the researchers employed a descriptive
statistical approach. The primary aim was to probe into the assessments provided by 43 prospective EFL
teachers regarding AI-powered lesson plans. This involved computing total ratings on the rubric, not
only for an overall assessment but also for each sub-category presented within the rubric. In addition,
the researchers incorporated qualitative data to enhance the quantitative findings with a deeper level of

108

AI-Powered Lesson Planning

comprehension. This holistic approach sought to illuminate the reasons behind the scores assigned in the
rubric, aiming for a comprehensive grasp of the participants’ evaluations of AI-generated lesson plans.
In the qualitative analysis phase, the researchers initiated an in-depth exploration of the data. By
utilizing memoing techniques, they established associations among emerging concepts, facilitating a
sophisticated comprehension of the qualitative components of the evaluations. Memoing is a key tech-
nique in qualitative research, where researchers write down their thoughts, insights, and interpretations
of the data throughout the research process. Memoing can help to deepen the analysis, generate new
ideas, and communicate the findings (Birks, Chapman, & Francis, 2008). Following this exploration, the
research team convened for collective negotiation to establish a common coding scheme. This method,
a critical component of qualitative analysis, laid the foundation for rendering qualitative insights into
structured and analyzable data.
To maintain uniformity among the two raters, the researchers coded 10% of the data, namely select-
ing five files randomly. Thorough coding and analysis of these data were conducted to evaluate and
confirm the consistency amongst different raters. In the coding process, each selected file was care-
fully examined, and relevant themes, patterns, or categories were identified and labeled. This involved
a line-by-line analysis of the content, with careful consideration given to the context of the data. The
researchers engaged in a collaborative discussion to ensure a shared understanding of the coding crite-
ria and to resolve any discrepancies that arose during the process. Afterward, the researchers gathered
again to utilize the percentage of agreement as a standard for inter-rater reliability. The results showed
83% consensus among the researchers, emphasizing the credibility of the qualitative analysis process
(Graham et al., 2012). Subsequently, the research team directed their focus to the remaining dataset.
The following phase involved an in-depth coding process and a thorough analysis. Once the coding was
completed, the researchers gathered once more to collectively identify and garner the primary findings,
ensuring a holistic synthesis of both quantitative and qualitative dimensions.

RESULTS

This part presents the results of the study in a detailed manner, specifically addressing the research is-
sues at hand. By methodically analyzing the collected data, the following sections provide a thorough
examination of important themes and trends.
Before presenting the findings of the study, it is worth mentioning how the generated lesson plans
were formatted. When asked, ChatGPT started by writing a title for the lesson and then produced the
outcomes (objectives) of the lesson. The materials to be used in the class were the following section
of the lesson plan and the stages of the writing class were as follows: (i) introduction (15 minutes), (ii)
vocabulary building (10 minutes), (iii) warm-up activity (10 minutes), (iv) main writing activity (30
minutes), (v) peer review (15 minutes), (vi) class discussion and reflection (15 minutes) and (vii) closure
(no time specification).

Evaluating AI-Powered Lesson Plans

The first research question was, “How do pre-service English as a Foreign Language (EFL) teachers
assess the effectiveness of lesson plans powered by artificial intelligence (AI)?” To answer this question,
the researchers first employed descriptive statistics for the rubric. In the rubric, the scores ranges from the

109

AI-Powered Lesson Planning

lowest score for the criteria as 1 (very poor) to the highest score 5 (very good). The overall mean score
of the whole rubric was 3.54 (SD =.45), which indicated positive evaluations for the AI-generated lesson
plans. For further exploration, the sub-dimensions of the rubric were also analyzed in the same manner.
The scores obtained from the rubric suggest high evaluations for some aspects of AI-powered lesson
plans, such as engagement and student interaction (M = 4.11, SD =.65), appropriateness (M = 4.05, SD
=.78), and lesson structure and organization (M = 3.89, SD =.52). For example, for student interaction,
the lesson plan provided several discussion opportunities for the learners at the beginning of the writing
class related with the topic of the lesson. Figure 3 illustrates the introduction stage of the lesson. Since
the prompt asked to design a writing lesson based on superheroes, the AI tool suggested opening the
lesson with a brief discussion about superheroes. Later, the tool integrated another discussion activity
around the key characteristics of superheroes. In other words, the tool followed communicative activities
to activate the existing schemata of the learners about superheroes.

Figure 3. The introduction stage of the AI-generated lesson plan

On a similar note, the activities provided in the lesson were also considered appropriate for the age
(5th graders) and language proficiency (A1) (MoNE, 2018) of the learners. Similarly, the lesson structure
and organization of the AI-powered writing lesson also scored high on the rubric. Figure 4 presents the
main writing activities of the lesson. The AI tool included a template for the writing activity (step 1),
asked students to use the newly studied vocabulary items in a meaningful way (step 2), enhanced creative
writing (step 3), and added monitoring of the teacher (step 4).

Figure 4. The writing stage of the AI-generated lesson plan

110

AI-Powered Lesson Planning

On the other hand, for differentiation and adaptation (M = 2.71, SD =.77) and assessment and feed-
back (M = 2.98, SD =.85), the same lesson plans were scored below average. To give an example, for
differentiation and adaptation, ChatGPT suggested that the participants could change the lesson plan
“based on the specific needs and dynamics” of their classes; they felt the lesson was not satisfying in
this regard. S3 (Student/participant 3) stated that the lesson plan lacked specific assessment criteria for
the students’ written work and suggested that the lesson plan needed improvements in terms of “incor-
porating differentiation measures, such as modified activities or supplemental materials, would help
meet the unique requirements of students and providing them with suitable challenges and assistance”.
Furthermore, for assessment and feedback, the AI-generated lesson plan included a separate stage in
the lesson after the main writing activity called “peer review”. Figure 5 below presents this stage of the
lesson. Although the procedure of this stage was presented, future EFL teachers pointed out the need
for a rubric.

Figure 5. The peer-review stage of the AI-generated writing lesson

One of the pre-service teachers, S25 wrote “specific criteria or rubric should be provided for as-
sessing student work” while S7 underlined that in this stage the teacher needs to give a “checklist or
rubric to the students and they give feedback based on the criteria in the rubric”. Some participants
also observed that there should be a rubric for the main writing task and another one for the speaking
activities in the lesson.
These results indicate that AI-powered lesson plans excel in areas such as engagement and student
interaction, as well as appropriateness and lesson structure. However, they appear to struggle with dif-
ferentiation and adaptation, as well as assessment and feedback. This suggests a need for improvement
in these specific areas to enhance the overall effectiveness of AI-generated lesson plans. The results can
be seen in Table 1 below.
To gain a better understanding of the scores given to the generated lesson plans and to explore the
participants’ reasoning for those scores, qualitative analysis was conducted as a follow-up. The findings
revealed that the participants were generally content with the ELT lesson planning of the AI tool but had
some reservations. The emerged themes can be grouped as follows: strengths of the AI-powered lesson
plan, areas for improvement, and suggested changes.

111

AI-Powered Lesson Planning

Table 1. Results obtained from the evaluation rubric*

Sub-Dimension M SD
Engagement and Student Interaction 4.11 .65
Appropriateness 4.05 .78
Lesson Structure and Organization 3.89 .52
Overall Effectiveness 3.73 .58
Learning outcomes 3.62 .93
Content and Resources 3.60 .71
Time Management 3.53 .89
Reflection and Extension 3.24 .86
Assessment and Feedback 2.98 .85
Differentiation and Adaptation 2.71 .77
Overall score 3.54 .45
*The rubric ranged from 1 (very poor) to 5 (very good).

Table 2. Frequency of the themes emerged for evaluating the AI-powered lesson plans

Themes and Codes Frequency

Strengths 232
Engaging Introduction 43
Clear Outcomes 39
Vocabulary Building 34
Creativity and Collaboration 38
Variety of Activities 41
Reflective closure 37
Areas for Improvement 111
Measurable Outcomes 29
Detailed Instructions 32
Time Management 26
Assessment Criteria 24
Suggested Changes 344
Enhanced Warm-up 33
Interactive Vocabulary Activities 30
Activity Examples 32
Context Development 28
Clear Instructions 31
Assessment Clarity 29
Optimized Time Management 25
Extension Activities 25

112

AI-Powered Lesson Planning

Strengths of AI-Powered Lesson Plans

As illustrated in Table 2, the participants mentioned quite a few strengths of AI-generated ELT lesson
plans for teaching writing to 5th graders by using the topic of superheroes. Firstly, the engaging introduc-
tion is a positive aspect as it utilizes visuals of superheroes, effectively capturing students’ attention and
creating an engaging atmosphere. This engagement strategy plays a crucial role in generating interest and
establishing a positive tone for the entire lesson. For example, the lesson plan included a description of
how the visuals of superheroes are incorporated into an interactive activity where students must identify
and name the superheroes. This activity not only grabs students’ attention but also activates their prior
knowledge and builds anticipation for the rest of the lesson.
Secondly, the lesson plan demonstrates clarity in its outcomes, which are generally clear and specific,
providing a well-defined roadmap for both teachers and students. Clear outcomes contribute signifi-
cantly to effective lesson planning, guiding participants throughout the learning process. In that sense,
the participants reported that

Lesson plan the AI created has clear objectives. The objectives of the lesson are well-defined and focused
on developing students’ writing skills. (S9)

The learning objectives that AI plan consists of are fully clear, specific, and aligned with the activities
as well as measurable, and achievable. (S14)

Moreover, the incorporation of vocabulary building was recognized as a strength, employing diverse
techniques such as visuals, matching exercises, and sentence usage. Vocabulary building is crucial in
this lesson plan because it helps students expand their language skills and enhances their ability to
comprehend and express ideas related to superheroes. By introducing new vocabulary through visuals,
matching exercises, and sentence usage, students not only learn new words but also gain the confidence
to use them effectively in their own writing and communication. This multifaceted approach ensures
that different learning styles are accommodated, reinforcing the understanding of newly introduced
vocabulary. Figure 6 shows the suggested pre-teaching vocabulary stage of the lesson.

Figure 6. Pre-teaching vocabulary stage of the AI-generated writing lesson

The results revealed that the AI-powered lesson plan also excels at fostering creativity and collabora-
tion through a writing activity that encourages students to imagine and describe their own superheroes,
with an emphasis on peer feedback and collaboration. This approach not only stimulates creativity but

113

AI-Powered Lesson Planning

also contributes to a supportive classroom environment. Furthermore, the inclusion of a variety of ac-
tivities, ranging from brainstorming to writing, peer review, and a concluding stage, is a commendable
aspect. This diversity caters to different learning preferences, maintaining student interest throughout
the lesson. For instance, the brainstorming activity appeals to students who prefer collaborative and
interactive learning, as they can engage in discussions and share ideas with their peers. On the other
hand, the writing activity caters to students who excel in individual expression and prefer reflective
learning. By including both collaborative and individual activities, the lesson plan accommodates a
range of learning preferences and ensures that all students can actively participate and contribute. The
participants commented as follows:

Students will love to work with the superheroes; the lesson will spark the creativity of the students by
making them imagine and write a plot for their superheroes, and peer feedback is also a great way to
encourage teamwork and collaboration. (S6)

By providing superhero-themed writing prompts, like imagining a superpower or designing a superhero

character, it sparks students’ creativity and critical thinking. (P35)

The opportunity for expressing their creativity and practicing their writing skills independently is pro-
vided by the individual writing tasks. Engaging in the peer feedback activity encourages collaboration
and aids students in cultivating their critical thinking and communication skills. (P40)

Lastly, as another positive aspect, the lesson plan concludes with a reflective stage, allowing stu-
dents to summarize and share their achievements. This reflective closure promotes metacognition and
reinforces key takeaways from the lesson. For instance, as part of the reflective closure, students could
be asked to write a short reflection on what they learned during the lesson and how they can apply their
new knowledge in real-life situations. This activity prompts students to think metacognitively about
their learning process, encouraging them to evaluate their progress and make connections between the
lesson content and their own experiences. The screenshot of suggested reflection stage in AI-powered
lesson plan is given in Figure 7:

Figure 7. Post-lesson reflection stage of the AI-generated writing lesson

Concerning this theme, the pre-service teachers underlined the importance of reflection for improv-
ing the target language skills and stated:

114

AI-Powered Lesson Planning

The wrap-up and reflection stages allow students to reflect on their learning and celebrate their ac-
complishments, instilling a sense of satisfaction and success. (S13)

In this way, the lesson plan gives an opportunity for students to reflect on their own learning and make
advancements on their writing. (S20)

In summary, the strengths observed in the lesson plan, including the engaging introduction, clear
outcomes, vocabulary building, creativity and collaboration, variety of activities, and reflective closure,
collectively contribute to a well-structured and effective learning experience.

Areas for Improvement

In addition to the strengths mentioned above, the prospective EFL teachers also identified some areas
for improvement in the generated lesson plans. Firstly, the need for measurable outcomes is highlighted,
as some outcomes lack specificity, posing challenges in assessing their achievement. To address this, it
is recommended that outcomes be clearly stated using measurable and observable language, ensuring a
more accurate evaluation of student progress. For example, instead of stating an outcome as “Students
will understand the concept of present simple tense,” a more measurable and observable outcome could
be “Students will be able to demonstrate their knowledge of the present simple tense by verbally express-
ing their daily routines.” Figure 8 illustrates the outcomes generated by ChatGPT.

Figure 8. The outcomes of the AI-generated writing lesson

Related to the problems about the learning outcomes the participants observed that not every learn-
ing activity had an outcome, they were not specific, and detailed. Although in the rubric the score for
learning outcomes was high (M=3.62, SD=.93), the specificity and the measurability of the generated
outcomes were identified as problematic by the participants.

Firstly, there should be an outcome for each activity, but this lesson plan just gives an objective for the
during-stage activity. (S4)

To begin with, the objectives of the plan, not each outcome line, are specific and align with the purpose
of the activities. (S11)

115

AI-Powered Lesson Planning

Especially for the outcome, it should be more detailed. It says that students will work in pairs or small
groups. There should not be an uncertainty like this. Is it in pairs or small groups? If it is in small groups,
how many students will be in groups? (S17)

Secondly, the instructions for certain activities, notably the post-writing activity and peer review, were
identified as lacking specificity and clarity. To enhance the overall execution of the lesson, it is suggested
that detailed instructions be provided for each activity. To give an example, proper instruction needs to
have step-by-step guidance, level- and age-appropriate language use, and a time limit. This ensures a
smoother and more effective implementation of the lesson plan. For example, S8 indicated that “the les-
son plan could benefit from providing more explicit and detailed instructions for each activity or task.”
since clear instructions “help students understand what is expected of them and minimize confusion”
(S19). Additionally, about this point, one of the participants observed that the lesson plan did not have
instruction-checking questions (ICQs).

Another thing to improve is ICQs and clear instructions in the classroom. Young learners lose their at-
tention easily and if your instructions are not clear or if you do not check whether they understand you
or not, you are not going to have a fruitful class, even if it is perfect in every aspect of the paper. ICQs
are a must-have in the lesson plan of teachers who are teaching young learners, and this lesson plan
does not have them. (S1)

Thirdly, a notable area for improvement is identified in the domain of time management. The alloca-
tion of time for certain activities, particularly the introduction stage, is deemed excessive. To prevent
students from losing focus, the suggestion is made to adjust time allocations based on the nature of each
activity, promoting optimal engagement throughout the lesson. As S26 observed, “the time limit could
be edited to match with young learners’ attributes and eased to execute more successful lesson.” For
example, for the introduction stage, the lesson plan could allocate 10 minutes for brainstorming. This
would provide a clearer guideline for teachers to follow.
Lastly, the absence of explicit assessment criteria or rubrics for evaluating student work is recognized
as a deficiency in the lesson plan. S15 indicated that the “plan could be evolved to a better version by
adding a rubric for feedback.” To address this, it is recommended that clear assessment criteria be
incorporated, guiding both teachers and students in understanding expectations and facilitating a more
transparent evaluation process.

Suggested Changes for the AI-Generated Lesson Plans

Another recurring theme was how to enhance the generated lesson plans. The participants in the study
provided several suggestions for the tool and the lesson plans to improve their quality. Firstly, to enhance
the warm-up, it is suggested to infuse more creativity by having the teacher dress as a superhero. This
engaging approach, coupled with a context related to a recent superhero movie, can significantly elevate
student interest and set a positive tone for the lesson. For example, the teacher could dress as a well-
known superhero character like Spiderman or Wonder Woman. They could wear a costume complete
with a cape, mask, and emblem. Alternatively, the teacher could create their own superhero persona and
design a unique costume that reflects their personality and teaching style.

116

AI-Powered Lesson Planning

Secondly, for interactive vocabulary activities, the recommendation is to introduce engaging ele-
ments such as word search maps and crossword clues. These interactive tools can reinforce vocabulary
understanding in a more enjoyable manner, catering to diverse learning styles. For example, word search
maps can help students visually identify and recognize the spelling and meaning of vocabulary words.
By searching for words hidden in a grid, students are actively engaging with the vocabulary, which can
aid in memorization and comprehension. Crossword clues, on the other hand, require students to think
critically about the definitions and connections between words, helping them to understand and apply
the vocabulary in context.
Thirdly, to support students in the writing activity, it is proposed to provide examples of the expected
paragraph or story beforehand. This addition aims to guide students, ensuring a better understanding of
the task and fostering more confident and effective participation. By providing examples, the students
can better understand the task requirements and expectations. This can help them develop a clearer idea
of the structure, language, and content needed for their own writing. Additionally, seeing examples can
boost students’ confidence and reduce anxiety, as they have a model to follow and can better envision
what a successful piece of writing looks like.
Additionally, to strengthen the context, the proposed change suggests incorporating elements from
popular culture, such as discussing a recent Avengers movie. This adjustment aims to make the topic more
relatable and engaging for students, connecting the lesson to their real-life experiences. For example, the
teacher could start the lesson by asking students if they have seen the recent Avengers movie and what
they think about it. This can generate excitement and encourage students to actively participate in the
discussion. The teacher could also relate the topic of the lesson to themes or characters from the movie,
making connections between the fictional world and the lesson content.
Moreover, in terms of clear instructions, the recommendation is to add explicit guidance, especially
for post-writing activities. This change aims to eliminate uncertainties and ensure a smoother flow of the
lesson, contributing to a more seamless learning experience. For example, the teacher could provide a
set of questions or prompts for students to consider when sharing their work. These questions could ask
students to explain their thought processes, justify their choices, or reflect on what they learned from
the activity. Additionally, the teacher could model effective sharing techniques, such as active listening
and constructive feedback, to ensure a productive and inclusive sharing session.
Furthermore, to address the absence of clear assessment criteria, the proposed change suggests in-
cluding specific assessment criteria or rubrics. This addition aims to provide transparency and clarity on
how student work will be evaluated, facilitating a more structured assessment process. The lesson plans
should include evaluation criteria for student work as appendices. Also, to optimize time management,
the suggestion is to adjust time allocations for activities based on the attention span of the students. This
change aims to ensure optimal engagement throughout the lesson, preventing potential lapses in focus
or off-task behavior.
Lastly, the recommendation includes integrating extension activities for students who finish early. This
addition aims to provide additional challenges and opportunities for exploration, catering to the varying
pace of student learning and promoting continuous engagement. Additionally, the recommendation sug-
gests incorporating regular breaks into the lesson plan to allow students to recharge and maintain their
focus. These short breaks can help prevent fatigue and increase productivity during the lesson. Moreover,
it is important to create a healthy learning environment by minimizing distractions and providing the
necessary resources for students to complete their work effectively. By implementing these strategies,
educators can ensure that students are actively engaged and motivated to participate in the lesson.

117

AI-Powered Lesson Planning

Synthesizing Quantitative and Qualitative Findings

To answer the research question, which probes into the future teachers’ assessments of AI-powered lesson
plans, the researchers collated the findings obtained from the evaluation rubric and the qualitative data.
As can be seen in Figure 9, the findings revealed that the AI-powered lesson plan demonstrates notable
strengths in the domains of engagement and student interaction, appropriateness, and overall lesson
structure and organization. Qualitative analysis reveals a consensus among participants, acknowledging
the lesson plan’s engaging nature, particularly in the warm-up and writing activities. This result aligns
with the quantitative analysis, where rubric scores affirm high evaluations for engagement and student
interaction (M = 4.11, SD =.65). Additionally, the appropriateness of the lesson plan, characterized by
its alignment with 5th-grade students and improved instructions, is supported by both qualitative recog-
nition and high rubric scores (M = 4.05, SD =.78) The well-structured nature of the lesson plan, with
commendable transitions between stages and activities, is echoed in qualitative analysis and corroborated
by high rubric scores for lesson structure and organization (M = 3.89, SD =.52).

Figure 9. Overview of the evaluation of AI-powered lesson plans

However, the lesson plan also exhibits areas for improvement, particularly in differentiation and adap-
tation, as identified in both qualitative feedback and low rubric scores (M = 2.71, SD =.77). Participants
expressed concerns about the inadequacy of differentiation, advocating for more tailored activities to

118

AI-Powered Lesson Planning

address varying proficiency levels and cultural relevance. Similarly, deficiencies in feedback and assess-
ment criteria were identified, impacting the overall evaluation process. The quantitative analysis further
underscores these concerns, with below-average scores for assessment and feedback (M = 2.98, SD =.85).
To address these areas for improvement, proposed changes focus on enhancing differentiation strate-
gies, refining assessment methods, and introducing diverse language practice activities. These changes
aim to elevate the overall quality and effectiveness of the lesson plan by accommodating diverse learning
needs, providing clearer assessment criteria, and enriching language practice opportunities.
All in all, the AI-powered lesson plan has been praised for its engagement, student interaction, ap-
propriateness, and overall structure and organization. Participants acknowledged its engaging nature,
particularly in warm-up and writing activities. The plan’s alignment with 5th-grade students and clear
instructions were also praised. However, there are areas for improvement, particularly in differentiation
and adaptation. Participants criticized the inadequacy of differentiation and the lack of feedback and
assessment criteria. The quantitative analysis also showed below-average scores for assessment and
feedback. To address these issues, proposed changes include enhancing differentiation strategies, refining
assessment methods, and introducing diverse language practice activities. These changes aim to improve
the lesson plan’s overall effectiveness by accommodating diverse learning needs, providing clearer as-
sessment criteria, and enriching language practice opportunities. In conclusion, while the lesson plan has
strengths, addressing these areas is crucial for optimizing its effectiveness in a diverse classroom setting.

DISCUSSION

The findings of this study provide an in-depth analysis of how pre-service English as a Foreign Language
(EFL) instructors evaluate the efficacy of AI-powered lesson plans. The study’s goal was to identify
differences in numerous areas of artificial intelligence-generated lesson plans and contextualize the find-
ings within the larger framework of the research objectives. By integrating quantitative and qualitative
data, this work provides significant contributions to the field of language instruction by highlighting the
benefits and limitations of AI-powered lesson design.
In terms of the benefits of lesson plans, the results reveal several notable benefits of AI-generated
lesson plans, particularly in terms of student involvement and interaction, overall class structure and
organization, and propriety. Higher rubric scores, which indicate positive ratings, are consistent with
the participants’ qualitative comments. A diversity of activities, a thought-provoking introduction, clear
objectives, vocabulary growth, cooperation and creativity, and a reflective conclusion all help to create
a cohesive and effective educational experience for the future teachers participating in the study. These
findings comply with related studies on the merits of AI in language teaching such as Baskara and
Mukarto (2023) and Kasneci et al. (2023), which indicated that ChatGPT provided significant support
in reducing teachers’ workload, saving time and energy in creating learning materials, and designing
learning activities.
Participants in the study questioned the use of AI-powered lesson plans, and for areas for improve-
ment, they identified differentiation and adaptability, evaluation and feedback, and defined assessment
criteria. Participants reported some concerns about the lack of differentiation, emphasizing the neces-
sity for activities that are more adaptable to varied skill levels and cultural significance. Furthermore,
weaknesses in the criteria for delivering feedback and grading performance were discovered, affecting
the overall evaluation process. These findings are supported by quantitative data, which reveals that

119

AI-Powered Lesson Planning

differentiation and adaptation, as well as assessment and feedback, received below-average scores. The
proposed changes aim to address these concerns by including more student-centered activities, creating
clear and explicit evaluation criteria, and improving assessment methodologies to respond to students’
diverse learning needs while simultaneously ensuring a clear and effective evaluation approach. These
results point out the similar apprehension commonly mentioned in the related literature. For instance,
Zhai (2022) underlined the fact that AI lacks the emotional support and the interpersonal connection
necessary for effective teaching despite its huge potential to deliver specific and pertinent information.
Thus, as the participants reported, ChatGPT possesses remarkable qualities in generating educational
resources including lesson plans, visual presentations, worksheets, and assessment assignments, none-
theless, it cannot replace teachers.
Participants make useful suggestions for increasing the quality of artificial intelligence-generated les-
son plans. Among the suggested measures are increasing the amount of creativity in warm-up activities,
including interactive vocabulary exercises, giving visuals for writing tasks, strengthening the contextual
framework through its relationship to popular culture, and streamlining time management. Participants
suggested adjustments to activity time allotment, clear instructions, and straightforward evaluation
methods. The modifications are intended to remove ambiguity, provide more clear work instructions,
and ensure maximum involvement throughout the educational session.
While the transition from positive evaluations to effective classroom implementation requires careful
consideration of pedagogical strategies, teacher roles, and student engagement, the preliminary results of
the study suggest advantageous uses of AI in education. The findings underscore that ChatGPT can be
a valuable tool for English language teachers in generating lesson plans and providing a wide range of
ideas and activities. Its flexibility allows for personalized lesson plans based on individual student needs
and interests, saving time and effort for teachers seeking inspiration and diversifying teaching strate-
gies. As for teacher professional development, the data suggests that ChatGPT can serve as a resource
for teachers, helping them stay updated on language teaching advancements and providing insights into
different approaches and methodologies. It can assist teachers in designing materials, activities, and
resources for language teaching. Additionally, the participants indicated that ChatGPT can be utilized
to improve their problem-solving skills, self-evaluate, and assess their teaching practices, and assist in
overcoming challenges such as student engagement and time management.
The clarity in outcomes and vocabulary building received commendations, aligning with the literature’s
emphasis on the importance of clear learning objectives and effective vocabulary instruction (Ghali et al.,
2018; Dewi et al., 2021). The study’s participants recognized the significance of well-defined outcomes
and diverse vocabulary-building techniques, such as visuals, matching exercises, and sentence usage,
in facilitating language acquisition.
The study’s focus on creativity and collaboration in writing activities draws parallels with the litera-
ture’s exploration of the benefits of AI tools in promoting critical thinking and problem-solving (Kas-
neci et al., 2023). The participants acknowledged the AI-powered lesson plans for fostering creativity
through activities that encourage students to imagine and describe their own superheroes, emphasizing
the positive impact on students’ creative expression and collaboration.
The variety of activities and reflective closure received positive feedback, reinforcing the literature’s
recognition of diverse instructional strategies and the importance of metacognition in learning (Toncic,
2020; Liu et al., 2020). The study’s participants appreciated the inclusion of activities ranging from
brainstorming to writing, peer review, and reflective closure, catering to different learning preferences
and promoting reflective thinking.

120

AI-Powered Lesson Planning

Despite the strengths identified, the study revealed areas for improvement, particularly in differentia-
tion and adaptation, and assessment and feedback. The participants expressed concerns about the need
for more tailored activities to address varying proficiency levels and cultural relevance, aligning with
literature that highlights the challenges of effectively integrating AI tools into diverse classroom settings
(Dincer, 2018).
The deficiency in explicit assessment criteria and feedback, as identified in both qualitative feedback
and low rubric scores (M = 2.98, SD =.85), supports existing literature emphasizing the importance of
clear assessment methods and criteria (Meyer et al., 2023). The study’s participants recognized the need
for measurable outcomes, detailed instructions, and explicit assessment criteria to enhance the overall
execution of the lesson plans. In addition, the results support the literature’s emphasis on the need for
effective differentiation strategies, clear assessment criteria, and diverse language practice activities
(Liden & Nilros, 2020).

CONCLUSION

In conclusion, this study contributes valuable insights into the evolving role of teachers in an AI-augmented
educational landscape. It is crucial to comprehend not only AI’s technical functionalities but also educa-
tors’ perceptions and experiences as tools like ChatGPT become potential ultimate lesson planners. By
bridging the gap between generative AI and the social dynamics of language education, this research
opens avenues for informed integration, ensuring that AI serves as a supportive ally in shaping the future
of language learning and teaching.
This chapter investigated the assessment of AI-powered lesson plans by pre-service EFL teachers,
offering valuable insights into both the strengths and areas for improvement in integrating artificial intel-
ligence into language education. The findings underscore the positive impact of AI on aspects such as
engagement, clarity of outcomes, vocabulary building, creativity, and collaboration, while also identifying
specific challenges related to differentiation, adaptation, and assessment practices. Still keeping in mind
that the paramount role of teachers to have effective and successful lesson as they implement the lesson
plans, AI is accepted by the participants in the study as an effective tool that can scaffold teachers with
good lesson planning components and ideas.

Implications

The implications of this study extend to both practitioners and researchers in the field of language
education. For educators, the identified strengths of AI-powered lesson plans highlight the potential
for enhancing student engagement, language acquisition, and collaborative learning experiences. The
study’s recommendations for improvement, particularly in the areas of differentiation and assessment,
provide practical insights for educators seeking to optimize the use of AI tools in diverse classroom set-
tings. Additionally, the study emphasizes the importance of clear communication of learning objectives,
explicit assessment criteria, and the need for tailored activities to address students’ varying proficiency
levels. For practice, the teachers could ask ChatGPT to propose specific assessment criteria or rubrics,
differentiated learning tasks, and better learning outcomes based on their context of teaching. To achieve
this, the teachers need AI literacy and competency.

121

AI-Powered Lesson Planning

In the rapidly evolving landscape of educational technology, the role of teachers becomes pivotal in
ensuring the effective integration and utilization of AI-powered tools. As this study underscores the benefits
and challenges associated with AI-powered lesson planning, it becomes evident that preparing teachers
to harness the potential of artificial intelligence is crucial for maximizing its impact in the classroom.
Training AI-ready teachers involves more than just technical proficiency; it encompasses developing
a practical understanding of AI’s capabilities, limitations, and its pedagogical implications. Educators
need to be equipped with the skills to navigate AI-powered environments, interpret data-driven insights,
and tailor their instructional approaches to complement the capabilities of AI tools. In other words, the
teachers need to have AI literacy skills and AI competency to productively use generative chatbots for
educational purposes. Moreover, fostering a mindset of adaptability and continuous learning is essential,
considering the dynamic nature of technological advancements. By investing in comprehensive training
programs, educational institutions can empower teachers to leverage AI not as a replacement but as a
powerful ally, enhancing their capacity to create innovative and personalized learning experiences for
their students. As we move towards an AI-augmented educational future, nurturing a team of AI-ready
teachers is not merely advantageous but imperative for ensuring the transformative potential of technol-
ogy in the hands of skilled and informed educators.
For researchers, the understanding of AI’s role in language education contributes to the ongoing
discourse on technology-enhanced pedagogy. The study suggests that while AI holds promise in certain
aspects of lesson planning, addressing specific challenges is imperative for its effective integration. Fu-
ture research endeavors could focus on refining AI algorithms to better cater to diverse learning needs,
exploring innovative strategies for adapting AI-powered lesson plans to different cultural contexts, and
developing comprehensive frameworks for assessing student performance in AI-powered language
learning environments.

Suggestions for Future Research

The study points towards several promising avenues for future research. Although the present study imple-
mented a hands-on approach for AI lesson planning, future research could focus on the implementation
of AI-powered lessons in real classrooms. It would be interesting to observe and investigate if AI lesson
plans can accommodate the diverse language teaching settings and/or how the teachers evaluate them
after actual implementation in the class. Furthermore, exploring the long-term impact of AI integra-
tion in language education, both on student outcomes and teacher practices, presents an intriguing area
for future inquiry. Longitudinal studies could provide insights into the sustainability of positive effects
and the potential adaptations required over time. Additionally, comparative studies across different AI
platforms and tools could offer a comprehensive understanding of the strengths and limitations inherent
in various AI-powered approaches.

Limitations of the Study

Despite the valuable insights gained, this study is not without limitations. Firstly, the sample primar-
ily consisted of 43 pre-service EFL teachers, potentially limiting the generalizability of the findings to
experienced educators. Future research could benefit from a more diverse participant pool, including in-
service teachers with varied levels of technological proficiency. Secondly, the study focused on a specific
context and topic (teaching writing to 5th graders using the theme of superheroes). While this specificity

122

AI-Powered Lesson Planning

allowed for a detailed examination, it may restrict the broader applicability of the findings. Replicating
the study across different language skills, grade levels, and topics could provide a more comprehensive
understanding of AI’s effectiveness in diverse educational settings. Lastly, the study employed a single
AI tool for lesson plan generation (ChatGPT). While this allowed for a focused investigation, different
AI tools may yield varied results. Comparative studies involving multiple AI platforms could offer a
nuanced understanding of the strengths and limitations inherent in each tool.
In conclusion, this study contributes to the growing body of research on AI in language education,
offering practical insights for educators and valuable considerations for future research endeavors. As
technology continues to evolve, understanding the intricacies of AI’s role in language teaching becomes
increasingly critical. By addressing the identified limitations and building on the implications and future
research directions outlined in this study, educators and researchers can collectively contribute to the
refinement and effective integration of AI into language education, ultimately enhancing the learning
experiences of students in an ever-evolving educational landscape.

REFERENCES

Al Darayseh, A. (2023). Acceptance of artificial intelligence in teaching science: Science teachers’ per-
spective. Computers and Education: Artificial Intelligence, 4, 100–132. doi:10.1016/j.caeai.2023.100132
Aldeman, N. L. S., Aita, K., Machado, V. P., da Mata Sousa, L. C. D., Coelho, A. G. B., da Silva, A. S.,
Mendes, A. P. D., Neres, F. J. D., & do Monte, S. J. H. (2021). Smartpath (k): A platform for teaching
glomerulopathies using machine learning. BMC Medical Education, 21(1), 248. doi:10.1186/s12909-
021-02680-1 PMID:33926437
Almutairi, A., Gegov, A., Adda, M., & Arabikhan, F. (2020). Conceptual artificial intelligence framework
to improving English as second language. WSEAS Transactions on Advances in Engineering Education,
17, 87–91. doi:10.37394/232010.2020.17.11
An, X., Chai, C. S., Li, Y., Zhou, Y., Shen, X., Zheng, C., & Chen, M. (2023). Modeling English teach-
ers’ behavioral intention to use artificial intelligence in middle schools. Education and Information
Technologies, 28(5), 5187–5208. doi:10.1007/s10639-022-11286-z
Baskara, R. (2023). Exploring the implications of ChatGPT for language learning in higher education.
Indonesian Journal of English Language Teaching and Applied Linguistics, 7(2), 343–358.
Bibauw, S., François, T., & Desmet, P. (2019). Discussing with a computer to practice a foreign language:
Research synthesis and conceptual framework of dialogue-based call. Computer Assisted Language
Learning, 32(8), 827–877. doi:10.1080/09588221.2018.1535508
Birks, M., Chapman, Y., & Francis, K. (2008). Memoing in qualitative research: Probing data and pro-
cesses. Journal of Research in Nursing, 13(1), 68–75. doi:10.1177/1744987107081254
Carlson, M., Pack, A., & Escalante, J. (2023). Utilizing OpenAI’s GPT-4 for written feedback. TESOL
Journal, 759, e759. Advance online publication. doi:10.1002/tesj.759
Chen, L., Chen, P., & Lin, Z. (2020). Artificial Intelligence in Education: A Review. IEEE Access :
Practical Innovations, Open Solutions, 8, 75264–75278. doi:10.1109/ACCESS.2020.2988510

123

AI-Powered Lesson Planning

Creswell, J. W. (2012). Educational research. Pearson.

Dewi, H. K., Putri, R. E., Rahim, N. A., Wardani, T. I., & Pandin, M. G. R. (2021). The use of AI (ar-
tificial intelligence) in English learning among university student: Case study in English Department,
Universitas Airlangga. https://doi.org/ doi:10.31235/osf.io/x3qr6
Dincer, S. (2018). Are preservice teachers really literate enough to integrate technology in their classroom
practice? Determining the technology literacy level of preservice teachers. Education and Information
Technologies, 23(6), 2699–2718. doi:10.1007/s10639-018-9737-z
Dwivedi, Y. K., Kshetri, N., Hughes, L., Slade, E. L., Jeyaraj, A., Kar, A. K., Baabdullah, A. M., Koo-
hang, A., Raghavan, V., Ahuja, M., Albanna, H., Albashrawi, M. A., Al-Busaidi, A. S., Balakrishnan,
J., Barlette, Y., Basu, S., Bose, I., Brooks, L., Buhalis, D., ... Wright, R. (2023). Opinion Paper: “So
what if ChatGPT wrote it?” Multidisciplinary perspectives on opportunities, challenges and implications
of generative conversational AI for research, practice and policy. International Journal of Information
Management, 71, 102642. doi:10.1016/j.ijinfomgt.2023.102642
Fitria, T. N. (2021). Grammarly” as AI-powered English Writing Assistant. Journal of English Language
Literature and Teaching, 5(1), 65-78.
Fu, S., Gu, H., & Yang, B. (2020). The affordances of AI‐enabled automatic scoring applications on
learners’ continuous learning intention: An empirical study in China. British Journal of Educational
Technology, 51(5), 1674–1692. doi:10.1111/bjet.12995
Ghali, M. A., Ayyad, A. A., Abu-Naser, S. S., & Abu, M. (2018). An Intelligent Tutoring System for
Teaching English Grammar. International Journal of Academic Engineering Research, 2(2), 1–6.
Graham, M., Milanowski, A., & Miller, J. (2012). Measuring and Promoting Inter-Rater Agreement of
Teacher and Principal Performance Ratings. Online Submission.
Hang, N. T. T. (2023). EFL Teachers’ Perspectives toward the Use of ChatGPT in Writing Classes:
A Case Study at Van Lang University. International Journal of Language Instruction, 2(3), 1–47.
doi:10.54855/ijli.23231
Hong, W. C. H. (2023). The impact of ChatGPT on foreign language teaching and learning: Opportuni-
ties in education and research. Journal of Educ. Technol. Innov., 5, 37–45.
Huang, W., Hew, K. F., & Fryer, L. K. (2022). Chatbots for language learning – are they really useful?
A systematic review of chatbot-supported language learning. Journal of Computer Assisted Learning,
38(1), 237–257. doi:10.1111/jcal.12610
Jaiswal, A., & Arun, C. J. (2021). Potential of artificial intelligence for transformation of the education
system in India. International Journal of Education and Development Using Information and Commu-
nication Technology, 17(1), 142–158.
Kannan, J., & Munday, P. (2018). New trends in second language learning and teaching through the lens
of ICT, networked learning, and artificial intelligence. Círculo de Lingüística Aplicada a la Comuni-
cación, 76, 13–30. doi:10.5209/CLAC.62495

124

AI-Powered Lesson Planning

KasneciE.SeßlerK.KüchemannS.BannertM.DementievaD.FischerF.NerdelC. (2023). Chatgpt for good?

on opportunities and challenges of large language models for education. https://doi.org/ doi:10.35542/
osf.io/5er8f
Kehoe, F. (2023). Leveraging generative ai tools for enhanced lesson planning in initial teacher educa-
tion at post primary. Irish Journal of Technology Enhanced Learning, 7(2), 172–182. doi:10.22554/
ijtel.v7i2.124
König, J., Bremerich-Vos, A., Buchholtz, C., Fladung, I., & Glutsch, N. (2019). Pre–service teachers’
generic and subject-specific lesson-planning skills: On learning adaptive teaching during initial teacher
education. European Journal of Teacher Education, 43(2), 131–150. doi:10.1080/02619768.2019.1679115
Kuleto, V., Ilić, M. P., Bucea-Manea-Țoniş, R., Ciocodeică, D. F., Mihălcescu, H., & Mindrescu, V.
(2022). The Attitudes of K–12 Schools’ Teachers in Serbia towards the Potential of Artificial Intelligence.
Sustainability (Basel), 14(14), 8636. doi:10.3390/su14148636
Lee, D., Kim, H., & Sung, S. (2022). Development research on an AI English learning support system
to facilitate learner-generated-context-based learning. Educational Technology Research and Develop-
ment, 71(2), 629–666. doi:10.1007/s11423-022-10172-2 PMID:36533222
Lee, I., & Perret, B. (2022). Preparing high school teachers to integrate AI methods into STEM class-
rooms. Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 12783–12791. doi:10.1609/
aaai.v36i11.21557
Li, R. (2020). Using artificial intelligence in learning English as a foreign language: An examination of
IELTS Liulishuo as an online platform. Journal of Higher Education Research, 1(2). Advance online
publication. doi:10.32629/jher.v1i2.178
Lidén, A., & Nilros, K. (2020). Perceived benefits and limitations of chatbots in higher education (Dis-
sertation). Retrieved from https://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-96327
Limna, P., Kraiwanit, T., Jangjarat, K., Klayklung, P., & Chocksathaporn, P. (2023). The use of ChatGPT
in the digital era: Perspectives on chatbot implementation. Journal of Applied Learning and Teaching, 6(1).
Meyer, J. G., Urbanowicz, R. J., Martin, P. C. N., O’Connor, K., Li, R., Peng, P.-C., Bright, T. J., Tatonetti,
N., Won, K. J., Gonzalez-Hernandez, G., & Moore, J. H. (2023). ChatGPT and large language models
in academia: Opportunities and challenges. BioData Mining, 16(20), 20. Advance online publication.
doi:10.1186/s13040-023-00339-9 PMID:37443040
Ministry of National Education. (2018). Ortaöğretim İngilizce dersi (9, 10, 11 ve 12. sınıflar) öğretim
programı [Secondary school English course (grades 9, 10, 11 and 12) curriculum]. http://mufredat.meb.
gov.tr/ProgramDetay.aspx?PID=342
Nazaretsky, T., Ariely, M., Cukurova, M., & Alexandron, G. (2022). Teachers’ trust in AI‐powered
educational technology and a professional development program to improve it. British Journal of Edu-
cational Technology, 53(4), 914–931. doi:10.1111/bjet.13232

125

AI-Powered Lesson Planning

Öztürk, G., & Aydin, B. (2019). English language teacher education in turkey: Why do we fail and what
policy reforms are needed? Anadolu Journal of Educational Sciences International, 9(1), 181–213.
doi:10.18039/ajesi.520842
Pack, A., & Maloney, J. (2023). Using generative artificial intelligence for language education research:
Insights from using OpenAI’s ChatGPT. TESOL Quarterly, 57(4), 1571–1582. doi:10.1002/tesq.3253
Pedró, F., Subosa, M., Rivas, A., & Valverde, P. (2019). Artificial intelligence in education: Challenges
and opportunities for sustainable development. UNESCO.
Pokrivčáková, S. (2019). Preparing teachers for the application of ai-powered technologies in foreign
language education. Journal of Language and Cultural Education, 7(3), 135–153. doi:10.2478/jol-
ace-2019-0025
Republic of Türkiye Ministry of National Education. (2018). English Curriculum for Primary and
Secondary Schools. Retrieved from: https://mufredat.meb.gov.tr/Dosyalar/201812411191321-
%C4%B0NG%C4%B0L%C4%B0ZCE%20%C3%96%C4%9ERET%C4%B0M%20PROGRAMI%20
Klas%C3%B6r%C3%BC.pdf
Rudolph, J., Tan, S., & Tan, S. (2023). ChatGPT: Bullshit spewer or the end of traditional assessments
in higher education? Journal of Applied Learning and Teaching, 6(1).
Schuengel, C., & van Heerden, A. (2023). Editorial: Generative artificial intelligence and the ecology
of human development. Journal of Child Psychology and Psychiatry, and Allied Disciplines, 64(9),
1261–1263. doi:10.1111/jcpp.13860 PMID:37528517
SlimiZ. (2021). The impact of AI implementation in higher education on educational process future: A
systematic review, Research Square. doi:10.21203/rs.3.rs-1081043/v1
Sun, Z., Anbarasan, M., & Kumar, D. (2020). Design of online intelligent English teaching platform
based on artificial intelligence techniques. Computational Intelligence, 37(3), 1166–1180. doi:10.1111/
coin.12351
Sütçü, S. S., & Sütçü, E. (2023). English Teachers’ Attitudes and Opinions Towards Artificial Intel-
ligence. International Journal of Research in Teacher Education, 14(3).
Toncic, J. (2020). Teachers, AI Grammar Checkers, and the Newest Literacies: Emending Writing
Pedagogy. Digital Culture & Education, 12(1), 26–51.
Vall, R., & Araya, F. (2023). Exploring the benefits and challenges of ai-language learning tools. The
International Journal of Social Sciences and Humanities Invention, 10(01), 7569–7576. doi:10.18535/
ijsshi/v10i01.02
van den Berg, G., & du Plessis, E. (2023). ChatGPT and Generative AI: Possibilities for Its Contribution
to Lesson Planning, Critical Thinking and Openness in Teacher Education. Education Sciences, 13(10),
998. doi:10.3390/educsci13100998
Verdegem, P. (2021). Introduction: Why We Need Critical Perspectives on AI. In P. Verdegem (Ed.), AI
for Everyone?: Critical Perspectives (pp. 1–18). University of Westminster Press. doi:10.16997/book55.a

126

AI-Powered Lesson Planning

Willems, J. (2023). ChatGPT at Universities – The Least of Our Concerns (SSRN Scholarly Paper No.
4334162). doi:10.2139/ssrn.4334162
Williamson, B., Eynon, R., Knox, J., & Davies, H. C. (2023). Critical perspectives on AI in education:
Political economy, discrimination, commercialization, governance and ethics. In B. du Boulay, A. Mi-
trovic, & K. Yacef (Eds.), The handbook of artificial intelligence in education (pp. 555–573). Edward
Elgar Publishing Ltd. doi:10.4337/9781800375413.00037
Yang, H., & Kyun, S. (2022). The current research trend of artificial intelligence in language learning:
A systematic empirical literature review from an activity theory perspective. Australasian Journal of
Educational Technology, 38(5), 180–210. doi:10.14742/ajet.7492
Yau, K., Chai, C., Chiu, T., Meng, H., King, I., & Yam, Y. (2022). A phenomenographic approach on
teacher conceptions of teaching artificial intelligence (AI) in K-12 schools. Education and Information
Technologies, 28(1), 1041–1064. doi:10.1007/s10639-022-11161-x
Yildirim, Y., Arslan, E. A., Yildirim, K., & Bisen, I. E. (2021). Reimagining education with artificial
intelligence. Eurasian Journal of Higher Education, 2(4), 32–46. doi:10.31039/ejohe.2021.4.52
Zhai, X. (2022). ChatGPT User Experience: Implications for Education (SSRN Scholarly Paper No.
4312418). doi:10.2139/ssrn.4312418

ADDITIONAL READING

Boubker, O. (2024). From chatting to self-educating: Can AI tools boost student learning outcomes?
Expert Systems with Applications, 238, 121820. doi:10.1016/j.eswa.2023.121820
Cotton, D., Cotton, P. A., & Shipway, J. R. (2023). Chatting and cheating: Ensuring academic integrity
in the era of ChatGPT. Innovations in Education and Teaching International, 1–12. doi:10.1080/1470
3297.2023.2190148
Fütterer, T., Fischer, C., Alekseeva, A., Chen, X., Tate, T., Warschauer, M., & Gerjets, P. (2023). Chat-
GPT in education: Global reactions to AI innovations. Scientific Reports, 13(1), 15310. Advance online
publication. doi:10.1038/s41598-023-42227-6 PMID:37714915
Hashem, R., Ali, N., El Zein, F., Fidalgo, P., & Abu Khurma, O. (2023). Ai to the rescue: exploring the
potential of ChatGPT as a teacher ally for workload relief and burnout prevention. Research and Practice
in Technology Enhanced Learning, 19, 23. doi:10.58459/rptel.2024.19023
Javier, D. R. C., & Moorhouse, B. L. (2023). Developing secondary school English language learners’
productive and critical use of ChatGPT. TESOL Journal, 00, e755. doi:10.1002/tesj.755
Rudolph, J., Tan, S. & Tan, S. (2023). War of the chatbots: Bard, Bing chat, ChatGPT, Ernie and beyond:
The new AI gold rush and its impact on higher education. doi:10.37074/jalt.2023.6.1.23

127

AI-Powered Lesson Planning

Tlili, A., Shehata, B., Adarkwah, M. A., Bozkurt, A., Hickey, D. T., Huang, R., & Agyemang, B. (2023).
What if the devil is my guardian angel: ChatGPT as a case study of using chatbots in education. Smart
Learning Environments, 10(1), 15. Advance online publication. doi:10.1186/s40561-023-00237-x

KEY TERMS AND DEFINITIONS

AI Competence: The collective set of skills, knowledge, and attitudes required for effectively under-
standing, implementing, and navigating the use of artificial intelligence in educational settings.
AI Literacy: The set of skills covering understanding, utilizing, and critically evaluating artificial
intelligence technologies.
Generative AI: A wing of artificial intelligence (AI) that focuses on creating systems capable of
producing human-like outputs, such as language, images, or other forms of content.
Lesson Planning: The systematic process of designing and organizing instructional activities, ma-
terials, and assessments to achieve specific learning objectives within a given timeframe.
Pedagogical Context: The specific teaching and learning conditions, including instructional methods,
classroom dynamics, and educational objectives, within which a particular educational intervention or
tool, such as ChatGPT, is implemented.
Rubric Assessment: A systematic and structured evaluation process that utilizes a rubric with pre-
defined criteria and scales to assign numerical scores, providing a quantitative measure.

128
AI-Powered Lesson Planning

APPENDIX

Figure 10 and Figure 11 Screenshots of an Example AI-generated Writing Lesson Plan

Figure 10. Examples of AI-generated writing lesson plan

129
AI-Powered Lesson Planning

Figure 11. Examples of AI-generated writing lesson plan

130
AI-Powered Lesson Planning

Table 3. AI-generated lesson plan evaluation rubric

Very Good
Very Poor

Average

Good
Poor
Criteria

5
A. Learning outcomes:
1. Are the outcomes clear, specific, and aligned with the activities in the lesson?
2. Do the outcomes cover the necessary knowledge, skills, and understanding?
3. Are the outcomes measurable and achievable?
B. Content and Resources:
4. Is the content relevant for the target audience?
5. Are the resources well-selected and effectively utilized to support the lesson?
6. Are there multiple modalities or resources used to accommodate different learning styles?
C. Lesson Structure and Organization:
7. Is there a clear and logical sequence of activities or steps?
8. Is the lesson organized in a way that promotes engagement and understanding?
9. Are the instructions for each activity or task clear and easy to follow?
D. Differentiation and Adaptation:
10. Does the lesson plan provide strategies for differentiating instruction to meet the needs of
diverse learners?
11. Are accommodations or modifications suggested for students with special needs or English
language learners?
12. Does the lesson plan provide flexibility for the teacher to adapt it for different topics?
E. Assessment and Feedback:
13. Are there appropriate methods or tools for assessing student learning during and at the end
of the lesson?
14. Does the lesson plan include opportunities for providing timely and constructive feedback
to students?
15. Are there specific criteria or rubrics provided for assessing student work or participation?
F. Engagement and Student Interaction:
16. Does the lesson plan include strategies to engage students actively in the learning process?
17. Are there opportunities for student collaboration, discussion, or hands-on activities?
18. Does the lesson plan promote student interaction and participation?
G. Time Management:
19. Is the lesson plan realistically designed to fit within the available class time?
20. Are time estimates provided for each activity, allowing for smooth transitions?
21. Does the lesson plan allocate sufficient time for important components of the lesson?
H. Reflection and Extension:
22. Does the lesson plan include opportunities for students to reflect on their learning?
23. Are extension activities or suggestions provided to deepen students’ understanding or to
challenge advanced learners?
24. Does the lesson plan encourage connections to real-life situations or other subjects?
continues on following page

131
AI-Powered Lesson Planning

Table 3. Continued

Very Good
Very Poor

Average

Good
Poor
Criteria

5
I. Appropriateness:
25. Is the lesson plan appropriate for the level of the students?
26. Is the lesson plan suitable for the age of the learners?
27. Is the lesson plan appropriate for the EFL context?
J. Overall Effectiveness:
28. Does the lesson plan demonstrate coherence and alignment with instructional goals?
29. Does the lesson plan provide a clear roadmap for teachers to implement the lesson
effectively?
30. Does the lesson plan seem engaging, innovative, and likely to meet the needs of the
students?

132
133

Chapter 7
Discussions of Using AI
in Language Education
in Hong Kong
Siu-lun Lee
https://orcid.org/0000-0002-2306-9217
The Chinese University of Hong Kong, Hong Kong

Yongyin Chen
Independent Researcher, Hong Kong

ABSTRACT
This chapter sets out to investigate the discussions of using AI in language education in Chinese press in
Hong Kong. From 2018-2023, there are news articles showcasing the AI tools and potential use of AI in
language education in Hong Kong. This chapter discusses the debates on the use of artificial intelligence
in language education and analyses newspaper discourse to investigate the different views of stakeholders
in language education including students, teachers, educators, and policymakers in Hong Kong. A corpus
containing Hong Kong newspaper articles discussing and debating the effectiveness and challenges of
applying artificial intelligence in language education in Hong Kong has been constructed and analysed.

INTRODUCTION

Artificial intelligence has an impact on different aspects of human life. The use of artificial intelligence
has been actively discussed in the educational field. There are studies discussing the use of conversational
artificial intelligence in language classrooms (Jeon, 2022; Ji et al., 2023). Some research explores how
artificial intelligence and chatbot technology can shape future language learning and teaching (Kim
et al., 2019). The discussion about the development and impact of artificial intelligence as well as its
use in education has been a topic receiving the attention of linguists, educators, policymakers, and the
public in recent years (Chen et al., 2022; Zai et al., 2021). Topics relating to the use of artificial intel-
ligence in education have been widely discussed in Hong Kong’s public media (Chen, 2023) and there

DOI: 10.4018/979-8-3693-0872-1.ch007

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

Discussions of Using AI in Language Education in Hong Kong

are ongoing debates on these topics in Hong Kong press. Some newspaper articles suggest that the use
of artificial intelligence is effective in language learning in Hong Kong schools (Yeung, 2019). On the
other hand, some articles voice out that the students and the educational field are not benefiting from
artificial intelligence (Liu & Yau, 2023). This paper sets out to discuss the debates on the use of artificial
intelligence in language education and investigate the different views of the stakeholders in language
education including students, teachers, educators, and policymakers expressed in Hong Kong newspa-
pers. A corpus containing Hong Kong newspaper articles discussing and debating the effectiveness and
challenges of applying artificial intelligence in language education in Hong Kong has been constructed
and analysed. The research questions are set as follows: (i) to investigate the extent to which the Hong
Kong press expressed arguments in favour of the use of artificial intelligence in language education in
Hong Kong; and (ii) to analyse the range of arguments to oppose the use of artificial intelligence. This
is the first systematic investigation of opinions in Hong Kong’s public opinions expressed in printed
media concerning the use of artificial intelligence in language education in Hong Kong. This study will
shed some light on the discussions of the use of artificial intelligence in language education in the Hong
Kong context.

ARTIFICIAL INTELLIGENCE AND LANGUAGE LEARNING

It has been a long history of computer-assisted language learning (CALL). There have been some
discussions about the use of artificial intelligence (AI) in language education since OpenAI laid the
groundwork with GPT-1 on 11 June 2018 and marked the advancement of a natural language process-
ing model that can produce a coherent and contextually relevant response to a particular prompt. Then,
AI has been adopted and used in education in different forms. AI initially took the form of computer
and computer-related technologies, transitioning to web-based and online intelligent education systems,
and ultimately with the use of embedded computer systems, together with other technologies, the use
of humanoid robots and web-based chatbots to perform instructors’ duties and functions independently
or with teachers (Chassignol, et al., 2018; Pedró et al., 2019; Chen et al., 2020). These platforms can
help teachers review and grade students’ assignments more effectively and efficiently to achieve higher
quality in their teaching activities. There was also research demonstrating the design of AI applications
in language education (Sun et al., 2021), discussing how AI can change students’ learning styles and
habits (Kang & Kang, 2020), and modeling the role of teachers in the AI era (Cope et al., 2021; Schmidt
& Strasser, 2022). There was also a bibliometric analysis to study the research literature relating to the
use of AI in language education (Huang et al., 2023). This research reviewed 516 papers published from
2000 to 2019 relating to the theme and summarised the 10 most popular topics related to AI in language
education were, (1) automated writing evaluation, (2) intelligent tutoring systems for reading and writ-
ing, (3) automated error detection, (4) computer-mediated communication, (5) personalized systems
for language learning, (6) natural language and vocabulary learning, (7) web-resources and web-based
systems for language learning, (8) intelligent tutoring systems for writing in English for specific pur-
poses, (9) intelligent tutoring systems for pronunciation and speech training, and (10) affective states and
emotions (Huang et al., 2023). Given the rapid development of AI and its use in education, UNESCO
urged stakeholders to deal with ethics and transparency in data collection, use, and dissemination, to
develop a comprehensive view of public policy on AI for sustainable development, to develop quality
and inclusive data systems, to ensure inclusion and equity for AI in education, to enhance research on
AI in education, and to prepare teachers for an AI-powered education (Pedró et al., 2019).

134

Discussions of Using AI in Language Education in Hong Kong

The official launch of ChatGPT on 30 November 2022 took the world by surprise with its sophisticated
capacity. ChatGPT, a large language model-based chatbot developed by OpenAI, enables users to refine
and steer a conversation towards a desired length, format, style, level of detail, and language. Microsoft
announced that ChatGPT-powered features were coming to Bing on 7 February 2023. The access of
Bing and ChatGPT is free at the time when the author is writing this chapter. Research has been done
to identify opportunities and challenges of implementing generative AI chatbots in language education
(Rudolph, et al., 2023; Ng et al., 2023). Moorhouse, et al. (2023) suggested that language teaching
pedagogies have been reconceptualised after the global pandemic period and the use of technology in
language teaching and learning has increased and ‘seems to be the norm’ in the post-pandemic age and
generative AI tools have the potential to offer new and innovative ways to support both teaching and self-
directed language learning. Kohnke et al. (2023) studied the use of ChatGPT for language teaching and
learning and suggested that ChatGPT can help explain vocabulary, create vocabulary lists, and provide
sample sentences and sample texts in different genres. They demonstrated that ChatGPT can also create
grammar exercises and comprehension exercises and adjust difficulties according to learners’ needs.
On the contrary, there were also studies iterating the concerns of language educators, such as biases in
data training, wrong information provided by the Chatbots, and privacy issues (Baidoo-Anu & Owusu
Ansah, 2023; Chan, 2023).

TECHNOLOGY IN LANGUAGE LEARNING IN HONG KONG

The research literature on language education in Hong Kong tells us that universities have experience
using online teaching and learning materials to supplement their formal classes (Chin, 2023; Kataoka,
2023; Lee, 2011, 2016, 2018). Since 2009, universities in Hong Kong have encouraged and implemented
e-learning in undergraduate language courses (King, 2016). Because of the implementation of these
e-learning projects, universities have produced online materials to supplement face-to-face language
courses. The implementation of computer-assisted learning was also promoted in primary and second-
ary education in Hong Kong (Bai et. al., 2021). Lee (2016) discusses the implementation of e-learning
components in traditional face-to-face Cantonese classrooms, as well as the normalization process of
such implementation. During the Covid pandemic period, the demand for online learning materials was
particularly high (Yaacob, & Saad, 2020). Studies are showing that artificial intelligence, augmented
reality, big data, and social media, can enhance language learning by providing authentic, contextualised,
and collaborative learning experiences (Kessler, 2017). The results of a study by Lee (2022) suggested
that students’ acceptance of blended teaching and learning models has grown substantially throughout the
pandemic period. The global pandemic not only moved educational institutions throughout the world to
implement various forms of online teaching but also increased the value of virtually available resources
for self-learners as well as students taking formal language courses.
After the launch of ChatGPT in November 2022, the discussions on using AI in education and language
education in Hong Kong’s news media have been growing. There are diverse views among these news
articles. Yeung, (2019) suggests that the use of generative artificial intelligence is effective in language
learning in Hong Kong schools. On the other hand, Liu and Yau (2023) voice out that the students and
the educational field are not benefiting from artificial intelligence. Chan (2023) collected survey data
from students and teachers in Hong Kong universities and urged universities to develop AI education
policies for higher education, focusing on governance, operational and pedagogical dimensions, based

135

Discussions of Using AI in Language Education in Hong Kong

on the perceptions and implications of text-generative AI technologies. This chapter sets out to study the
diverse public views and debates about the use of AI in language education in Hong Kong.

THE STUDY

Data Collection and Methodology

An extensive corpus of Chinese-language newspaper articles concerning the use of artificial intelligence
in language education in Hong Kong has been compiled. More specifically, this database has focused on
press articles discussing the use of artificial intelligence in education which has drawn comments and
commentaries from members of the public as well as professional journalists. Newspaper articles were
retrieved from a number of sources, including the WiseOne (formerly WiseNews) database for the Hong
Kong press, as well as individual searches of fourteen leading Chinese newspapers, namely AM730,
Headline Daily (頭條日報), HK01 (香港01), Hong Kong Commercial Daily (香港商報), Hong Kong
Economic Journal (信報財經新聞), Hong Kong Economic Times (香港經濟日報), Master Insight (灼
見名家), Mingpao Daily (明報), Oriental Daily (東方日報), Sing Pao (成報), Sing Tao Daily (星島日
報), Sky Post (晴報), Ta Kung Pao (大公報), and Wen Wei Po (文匯報) in Hong Kong. The research
issues in investigating newspaper articles on discussions and comments relating to the use of artificial
intelligence in language education in Hong Kong were as follows: (i) to investigate the extent to which
the Hong Kong Chinese press expressed arguments in favour of the use of artificial intelligence in
language education in Hong Kong; and (ii) to analyse the range of argumentation to oppose the use of
artificial intelligence.
The data collection took place from March 2023 to September 2023, a total of 299 newspaper articles
were downloaded from the internet, and the text was then entered into the database. These articles were
initially searched using such terms 人工智能 ‘artificial intelligence’, 電腦輔助語言教學 ‘computer-
assisted language teaching and learning’, 電腦輔助語言學習 ‘computer-assisted language learning’, 網
上語言學習 ‘online language learning’, and closely related terms, as well as English terms as they also
appear in Chinese texts, such as ‘artificial intelligence’, ‘AI’, ‘generative AI’, and ‘ChatGPT’. Before
inclusion in the database, the articles were briefly reviewed to determine their relevance to the use of AI
in the language education in question and were grouped by the time of publication. These articles were
grouped before and after the launching time of ChatGPT, November 2023, to understand public views
and discussions before and after the official launch of generative AI and chatbots. Later, a further round
of filtering took place, after the researcher decided to categorise such data into clusters related to these
topics: (1) showcasing AI applications for language education, (2) arguments supporting the use of AI in
language education, and (3) views against the promotion of AI in language education. After classifying
the data according to the above incidents in terms of topic and timeline, there is a total of 259 articles
related specifically to these three topics discussed in the past five years (2018-2023).

136

Discussions of Using AI in Language Education in Hong Kong

RESULTS

Quantitative Results

To carry out a broad quantitative analysis of the opinions expressed by news reporters and columnists
in the newspapers investigated, the articles in our dataset have been grouped into three categories: (1)
showcasing AI applications for language education, (2) arguments supporting the use of AI in language
education, and (3) views against the promotion of AI in language education. This study was centrally
concerned with discussions, where public opinions on the use of AI in language education were explicitly
expressed. The limitations of adopting such an approach may be obvious, as, the subjective methodology
used by the investigator in deciding and identifying the main discussions in a particular newspaper text.
Two raters were recruited to review and verify the investigator’s categorisations and judgment on these
newspaper texts. Despite some inevitable subjectivity in making such decisions, given the familiarity of
the researcher with language pedagogies and the language education issues of society, the methodology
adopted was appropriate and effective in the qualitative analysis of texts.
Table 1 below shows that a total of 259 articles fall into three categories: (1) showcasing AI appli-
cations for language education, (2) arguments supporting the use of AI in language education (pro-AI
arguments), and (3) views against the promotion of AI in language education (anti-AI arguments).

Table 1. Discussions in the press relating to the use of AI in language education in Hong Kong, 2018-2023

Date Showcasing AI Applications Pro-AI Arguments Anti-AI Arguments

January 2018 – October 2022 32 (33%) 49 (43.7%) 3 (6%)
November 2022 – August 2023 65 (67%) 63 (56.3%) 47 (94%)
Total 97 (37.5%) 112 (43.2%) 50 (19.3%)

As can be seen from the above table, 37.5% of the articles in the dataset showcased the use of AI in
language education in Hong Kong. The number of these demonstrations doubled after November 2022
since the launch of generative AI ChatGPT. In the meantime, there are a number of articles (43.2%)
presenting arguments to support the use of AI in language education in Hong Kong. The distribution of
these arguments is quite even before the official launch of generative AI (43.7%, January 2018 - October
2022) and after the official launch of ChatGPT (56.3%, since November 2022). In the dataset, there
are 19.3% of the articles express views against the promotion of AI in language education. However,
this kind of discussion and concern increased rapidly from 6% (January 2018 - October 2022) to 94%
(November 2022 - August 2023). This indicates that many of the discussions against the use of AI in
language education were started after the official launch of the generative AI, ChatGPT.
In the discursive presentation of the qualitative data, which is presented a little later in this chapter,
the results of our analysis have been grouped according to those topics that emerged from this analysis
and illustrated by translated quotations from the Chinese newspaper articles in question. Here again,
however, there were limitations to the method of classification used in arriving at these results, as in
many cases more than one argument was present in any given text. The task for the researcher and raters,
therefore, was to make a judgment as to which argument was most salient in any given text, and this we
attempted to do, as accurately and consistently as possible.

137

Discussions of Using AI in Language Education in Hong Kong

Qualitative Results

The qualitative methodology employed by the researcher was used at many levels of analysis. First,
each of the articles in the database was carefully read to identify the major arguments presented in each
article, and to decide which of these arguments was most salient in a particular text. This then provided
the basis for the quantitative analysis of arguments as presented in Table 1. Following this, at a nar-
rower level of examination, the researchers were then able to examine individual articles in order to
determine how particular arguments were realised. One overarching result that emerged from this next
level of analysis was that reference to or presentation of ‘major arguments’ overlapped within individual
newspaper articles, contributing very often to a multi-layered discourse where a range of closely related
arguments find expression. This multilayering of argumentation can be seen in many of the excerpts
presented below. We shall first consider those arguments most frequently made in support of the use of
AI in language education in Hong Kong, before moving on to a discussion of arguments against such
use. The texts presented below were extracted from articles representing different styles or genres of
journalism, including opinion columns, feature articles, and news reports.

Showcasing the Use of AI in Language Education in News Media

In recent decades, the Hong Kong SAR government has promoted ‘trilingualism and biliteracy’, that is
the use of three spoken languages, Cantonese, Putonghua, and English, and two written codes, standard
written Chinese and written English, in official settings (Bacon-Shone et al., 2015; Bolton et al., 2020;
Bolton & Lee, 2020). Cantonese, English, and Putonghua are three major languages used in Hong
Kong, and both written Chinese and English are used in government announcements, in the education
domain, and in business sectors. As may be seen in Table 1, there were some cases of AI applications in
language education during 2018-2023. Before the official launch of generative AI in November 2022,
there were already some demonstrations of the use of AI in language teaching and learning. Articles
in Ta Kung Pao and Sing Tao Daily showcased the use of tools and applications to help students learn
English vocabulary and improve English reading skills, as in excerpts (1) and (2).

(1) An AI learning-oriented intelligent hardware product, “Xunfei Scanning Dictionary Pen,” has
been released. The core function of this dictionary pen is to scan and look up words, and it also
has corresponding innovative functions designed for listening, speaking, reading, and memorizing
English vocabulary. (Ta Kung Pao, 27/10/2020)

(2) Microsoft Teams recently launched the ‘Reading Progress’ feature, which introduces an English
article about ‘Food & Drink’ and distributes it to children at home to practise reading along with.
The AI function built into ‘Reading Progress’ automatically analyzes most of the students’ pronun-
ciation accuracy, helping teachers to understand which words are commonly misread by everyone
and to grasp the different learning situations of the whole class and individual students through the
teacher interface on Teams. This helps teachers and schools to further improve students’ learning
efficiency in limited face-to-face or online course hours according to different learning needs. (Sing
Tao Daily, 21/06/2022)

138

Discussions of Using AI in Language Education in Hong Kong

There were also AI applications that helped analyse Chinese sentences and morphological structures
to assist ethnic minority students learning Chinese as a second language in Hong Kong, as shown in
excerpt (3) below.

(3) Chinese words have a large variety of combinations, and ‘how to split Chinese sentences’ is a
complex problem. After years of research, he developed an analysis tool called HanMosaic, which
can split Chinese characters, sentences, and paragraphs, and distinguish between words and single
characters. People generally think that this requires a huge database to assist, but it turns out that
it only needs artificial intelligence that can learn on its own. The research results have been trans-
formed into an online dictionary designed for non-Chinese-speaking students. It automatically
dissects Chinese sentences into words, analyzes them one by one, and teaches stroke order and
radicals. It has already begun to be used in schools. (Hong Kong Economic Journal, 25/01/2019)

There were also discussions about using AI technology and applications to arouse students’ interest
in learning Chinese literature, as in excerpt (4) below.

(4) Students enjoy using AI to enhance their learning interests. Some students have even been simulated
by Li Bai’s Thoughts in the Silent Night and interacting with ancient people in the AI system in
their Chinese reading classes. (Hong Kong Economic Times, 13/04/2021)

In the dataset, there were also displays that AI can change students’ language learning styles. Excerpt
(5) shows that AI-based gamified applications changed students’ learning habits outside the language
classrooms.

(5) This application encourages children to learn through gamified experiences. The children receive
immediate feedback after practice and record poorly pronounced words to help improve them in
the future. It’s worth noting that the app also provides multiple scenario choices, such as school,
restaurant, airport, and hospital, among other daily situations. After selecting a scenario, an AI robot
will play different roles with children to practise English conversation in the form of sentences or
dialogues. (Sky Post, 08/03/2022)

There are news articles promoting the use of AI technology to match students’ language learning
needs to language schools and tutors, as shown in the excerpt (6).

(6) FluentUp, a local online language learning platform, uses its ‘efficient learning management system’
to analyze users’ preferences and needs through artificial intelligence, and then matches them with
language schools around the world in real-time. (Hong Kong Economic Times, 22/01/2019)

After the official launch of generative AI in November 2022, more varieties of applications used in
language education were demonstrated. Excerpts (7) and (8) illustrate using ChatGPT to help students’
English grammar and writing in English.

(7) Children can now learn English through the internet and smart devices, and ChatGPT can be a
useful tool to help them learn the tenses of English. (Sing Tao Daily, 21/07/2023)

139

Discussions of Using AI in Language Education in Hong Kong

(8) ChatGPT can help to improve English grammar. First, write the composition, and then give ChatGPT
the command ‘Please correct my English composition and correct my grammar errors’. A student
shared that ChatGPT can present grammar errors and improvement suggestions in a list, which is
more convenient. (Hong Kong Economic Times, 17/04/2023)

Excerpts (9) and (10) below demonstrate two mobile applications, SpokenBot and ReadOutLoud.
These two applications were developed by the Hang Seng University of Hong Kong. These applications
made use of generative AI technology to help students improve English and Putonghua pronunciation
and students’ accuracy in speaking English and Putonghua. SpokenBot helps students practise English
and Chinese vocabulary, assesses pronunciation when students read these vocabulary items in English
and in Putonghua, and assesses pronunciation on the sentence level. This application contains 100
scenarios with 3 levels of difficulties for students to practise. ReadOutLoud is a learning system that
downloads news from radio channels and government websites and generates English and Putonghua
speech samples. Students can record their reading of these pieces of news in English or Putonghua. The
systems can assess students’ English and Putonghua pronunciation.

(9) A team has successfully developed two free mobile applications, SpokenBot and ReadOutLoud, for
students and citizens to learn languages. These apps use artificial intelligence engines and chatbot
technology to help users improve their accuracy in English and Mandarin Chinese. (Wen Wei Po,
08/06/2023)

(10) The English and Mandarin Chinese learning program ReadOutLoud downloads news content from
radio stations and government news websites every day. Users first listen to AI-read Mandarin
Chinese or English news content, then record themselves reading the content. The AI engine will
analyze the recording in real-time, score it, and point out vocabulary that can be improved for
pronunciation. (Sing Tao Daily, 07/06/2023)

The advancement of linguistic research to predict child language development using AI technology
is also reported in the news media, shown in excerpt (11).

(11) Using electroencephalogram (EEG) test to collect data on 300 healthy Hong Kong children as a
benchmark, and then using artificial intelligence computing programs to predict their future lan-
guage development. (HK01, 13/07/2023)

The development of this electroencephalography test was a joint project led by a linguist, Patrick
Wong, who collaborated with Paediatrics doctors to construct a predictive algorithm to forecast language
development in individual children. With early intervention strategies, it could reduce the severity of
potential language impairment as well as optimise language learning for children, in particular Cantonese
and Mandarin pronunciation, at the earliest possible time. The research team thinks that it is important
to screen out children who may suffer from a developmental language disorder so that parents can act
and provide appropriate intervention and training as early as possible (The Chinese University of Hong
Kong, 2021).

140

Discussions of Using AI in Language Education in Hong Kong

‘Pro-AI’ Arguments

As may be seen in Table 1, 43.2% of the arguments in the newspaper texts were identifiable as ‘Pro-AI’,
in the sense that these produced arguments in favour of the use of AI in language education in Hong
Kong. These articles emphasized that the use of AI in language education can provide personalised
support for students, offer real-time assistance to students, and create an extended language classroom.
This section of the article presents a detailed account of the arguments that have been deployed in recent
debates in the Hong Kong Chinese press. These arguments clustered in three areas focusing on the use
of AI in language education can provide personalise teaching and support to students, offer real-time
assistance to students, and encourage students to learn anywhere.
Providing personalised teaching and support to students. The Chinese press emphasized a lot on
personalised language teaching and support to students. As AI systems become more mature, they can
make use of complex sets of data to understand students’ learning styles and needs and, in turn, adjust
course content according to students’ abilities and provide each student with the most appropriate learn-
ing materials, as shown in excerpts (12), (13) and (14).

(12) The integration of big data with technologies such as speech recognition and image recognition has
led to interdisciplinary and cross-domain development. The ‘smart adaptive learning’ technology
that simulates the one-on-one teaching process between teachers and students and gives personalised
teaching to the learning system has been widely used in the field of language education. (Wen Wei
Po, 18/11/2019)

(13) AI language translation has a significant impact on human language learning. In recent years,
students’ extracurricular English tutoring has been changed. (Ta Kung Pao, 22/12/2022)

(14) AI applications have already become trendy tutors in the field of language education. They can not
only impart knowledge to learners but also adjust teaching styles and progress according to their
needs, rhythm, and preferences. For example, the Duolingo language learning application can not
only teach you fluent French but also has an AI system that adjusts according to your learning
progress, strengthens your weak areas in learning, and reminds you to practise regularly. (AM730,
18/08/2023)

Offering real-time assistance to students. In addition, commentaries in the Chinese press suggested
that when students face learning difficulties after school and seek support, AI and generative AI can offer
real-time assistance to their learning difficulties. When AI systems can provide language support and
assistance at school and after school, the workload of teachers can be reduced and teachers can devote
more time and resources to take care of students’ psychological needs, as presented in excerpt (15) below.

(15) Using AI to provide students with learning, assessment, and feedback, as well as providing them
with appropriate learning progress and challenges, and switching to the next learning topic at
the appropriate time. As AI technology matures, machines can read students’ facial expressions
to determine their learning pace and to provide each student with the most appropriate learning
materials. After-school language tutoring and learning plans will also become more advanced,
permeating different learning methods in the learning process. When students are struggling with

141

Discussions of Using AI in Language Education in Hong Kong

homework or exam preparation at home, AI will be a great help to them. This will reduce the teach-
ing workload of teachers and free up more time to take care of students’ spiritual needs. (Sing Tao
Daily, 08/03/2021)

Learning anywhere and arousing students’ interest. The implementation of computer-assisted

language learning can break the limitations of time and space. This can be proved in the global pandemic
period, where various types of synchronous and asynchronous online language teaching attempts have
been made to solve the social distancing issues (Lee, 2022). There are arguments in the Hong Kong
Chinese press showing support that students can learn and practice anytime and anywhere with AI and
generative AI technology. Excerpt (16) below shows this view.

(16) From a student’s perspective, ChatGPT can provide personalised support and answer individual
questions. ChatGPT breaks the limitations of time and space, allowing students to use it anytime,
anywhere. Furthermore, ChatGPT can provide real-time language assistance to students, whether
it is after class, when teachers are busy, or even late at night. This greatly enhances their learning
efficiency. ChatGPT also allows students to explore different fields through real-time interactive
feedback and dialogue, making language learning more attractive and interactive, while also help-
ing to increase their interest in learning. (Sing Tao Daily, 07/04/2023)

‘Anti-AI’ Arguments

The major debates that emerged in the Chinese press revolved around a number of interlocking and
overlapping issues and themes. Those articles that were judged to present strong arguments ‘against the
use of AI in language education’ formed a small but significant minority, accounting for a total of 19.3%
of all the articles in the database. It was nevertheless considered important to give these ‘anti-AI’ argu-
ments close examination. The major arguments and themes in articles against AI were identified as an
infringement of intellectual property, stakeholders’ questions about the accuracy of answers provided
by generative AI, and challenges to teachers’ roles.
Infringing intellectual property and plagiarism. A major comment, among the articles in the data-
set, on the use of AI and generative AI in language teaching is the infringement of intellectual property
and the issues of plagiarism. Commentaries raised the issues about ethics, ghostwriting, and cheating
issues, as in excerpts (17) and (18) below.

(17) Artificial intelligence also involves a series of issues such as ethics, morality, intellectual property
rights, scientific research plagiarism, and cheating in exams. (HK01, 07/03/2023)

(18) If students violate the rules and use AI tools such as ChatGPT without the consent of others, it is
equivalent to using their works without permission, which involves an element of ‘deception’. If
relevant AI tools are used without exemption, they also meet the relevant definition. Therefore, the
school will treat such cases as ‘potential plagiarism’. (Headline Daily, 18/02/2023)

Questioning the accuracy of answers provided by generative AI. Some commentaries also questioned
the accuracy and credibility of the answers and suggestions provided by AI, as shown in the excerpt (19).

142

Discussions of Using AI in Language Education in Hong Kong

(19) The answers provided by ChatGPT are too generalized, inaccurate, low credibility, and outdated.
All these defects greatly affect the practicality of ChatGPT. (Master Insight, 20/02/2023)

Challenging teachers’ role. Some comments focused on the negative impact on human teachers once
AI applications were implemented in language education. An article in Sing Tao Daily worried generative
AI can damage the status of teachers and weaken students’ attention in class, as shown in excerpt (20).

(20) Although ChatGPT can help with natural language generation, it should be noted that it may have
some negative effects on the work of some teachers, such as damage to the power and status of
teachers and weakening of students’ passion and attention for teachers. (Sing Tao Daily, 2023-02-16)

DISCUSSION

The debate relating to the implementation of AI applications in language education shows the merits
of using AI, as well as the worries about this technological innovation towards language education, in
particular, and education, in general.
Generative AI is a new global trend that changes the way of searching for information. The good side
of using generative AI as a teaching tool is that it can cultivate students’ use of information technology and
enhance their information literacy. Generative AI can also do one-on-one tutoring, provide personalised
teaching and support to students, offer real-time support to students, and allow students to learn language
skills and study on their own. There is research aiming at setting up an AI curriculum framework for
secondary schools in Hong Kong to promote the use of AI in pre-tertiary classrooms (Chiu et al., 2022).
The opposite side raised their concerns that students may use generative AI to complete their home-
work, which does not help them grow and hinders the development of their critical thinking and problem-
solving skills. Commentaries on the ‘anti-AI’ side worried that the use of generative AI encourages
students to cheat and copy which, in a way, encourages academic dishonesty. The ‘anti-AI’ arguments
also emphasize generative AI’s errors and inaccuracy. Some articles echoed UNESCO’s suggestions
and urged setting up rules and regulations for the use of generative AI in education. Although universi-
ties have started to set policies and guidelines on the use of artificial intelligence in tertiary education,
some of these guidelines are very preliminary, for example, permission must be granted before using
AI in in-class exercises and assignments, the use of AI should be fully acknowledged similar to citation
of other sources, and encourage students to use AI ethically (The Chinese University of Hong Kong,
2023; The Hong Kong Polytechnic University, 2023). It is clear that more work is needed to deal with
the ethical issues relating to the use of AI in language education.
The data in this study also shows language teachers’ worries relating to their role in the teaching
process. To some extent, this is due to both teachers and learners lacking digital competencies to use
generative chatbots ethically and effectively to support language learning. Research on teachers’ and
students’ attitudes can be done in institutions to understand the needs of both teachers and students
so that institutions can plan adequate training on digital proficiency and ethics of using generative AI
technology in teaching and learning (Kohnke et al., 2023).

143

Discussions of Using AI in Language Education in Hong Kong

IMPLICATION

From the debate on the use of generative AI in language education, the impact brought about by genera-
tive AI on language education can be very prominent. The data in this study shows that issues concerning
the ethical use of generative AI are of primary concern to many stakeholders, research on these ethical
issues and setting precise and agreeable guidelines are of foremost importance to many educators, lan-
guage teachers, parents as well as students.
The dataset in this study shows that the number of ‘Pro-AI’ arguments (119 articles, 43.2%) is double
that of the ‘Anti-AI’ arguments (50 articles, 19.3%). The situation, in general, is more favourable to the
development and use of AI in language education. However, the barriers to the use of generative AI
in education cannot be neglected (Wang & Cheng, 2021). It is worth noting that in computer-assisted
language learning (CALL) literature, for effective implementation of innovative pedagogical technology,
not only do teachers need adjustments and training, but students also need training in terms of computer
efficacy, motivation for using the new technology, ethics and learning habits, and culture to naturalise
or normalise the use of such innovation in their academic life. Lee (2016) studied the normalisation
process of technological innovation in language education. This study compared students’ expectations
of technological innovation with institutional targets. The result showed that the characteristics, hab-
its, and expectations of students, though may be subject to change with the advancement of computer
technologies, may not always match with the pedagogical beliefs of the institution as well as teachers’
expectations. If such a mismatch happens, institutions/teachers need to understand students’ learning
habits and expectations, on the one hand; and on the other hand, instructional strategies, and training
for teachers and students need to be developed to smooth the normalisation process.
For sure, the technology of generative AI will continue to be advanced and more widely applied
in more aspects of human life. Language teaching pedagogy relating to the use of AI also needs to be
closely followed. This is a preliminary study about using AI in language education in Hong Kong. More
research on such use, including the development in curriculum design, change in teaching and learning
mode, extension of language classrooms, as well as language assessment, are needed to look at the dif-
ferent applications and effectiveness of this cutting-edge technology in the field of language education.

CONCLUSION

This chapter discusses the debates on the use of artificial intelligence in language education and analyse
Chinese newspaper discourse to investigate the different views of the stakeholders in language education
including students, teachers, educators, and policymakers in Hong Kong. A corpus containing Hong
Kong newspaper articles discussing and debating the effectiveness and challenges of applying artificial
intelligence in language education in Hong Kong has been constructed and analysed. From 2018-2023,
there are news articles showcasing the AI tools and potential use of AI in language education in Hong
Kong. In the meantime, there are debates about the use of AI in education and language education, in
particular. The ‘pro-AI’ arguments emphasized that the use of AI in language education can provide
personalised support for students, offer real-time assistance to students, and create an extended language
classroom, while the ‘anti-AI’ views concern the infringement of intellectual property, the accuracy of
answers provided by generative AI, and challenges to teachers’ roles if AI and generative AI technology
is implemented in language education. Studies on students’ learning habits, and expectations, as well

144

Discussions of Using AI in Language Education in Hong Kong

as readiness, will be important for administrators to investigate implementation plans and effectiveness.
On the pedagogical side, more research is needed to investigate language teaching approaches and as-
sessments incorporating AI technologies. Given the importance of artificial intelligence and related
technology in the age of the Internet, the popularity and research of such technology are likely to further
increase in the years to come.

REFERENCES

Bacon-Shone, J., Bolton, K., & Luke, K. K. (2015). Language use, proficiency and attitudes in Hong
Kong. Social Sciences Research Centre, HKU.
Bai, B., Wang, J., & Zhou, H. (2020). An intervention study to improve primary school students’ self-
regulated strategy use in English writing through e-learning in Hong Kong. Computer Assisted Language
Learning, 35(9), 2265–2290. doi:10.1080/09588221.2020.1871030
Baidoo-Anu, D., & Owusu Ansah, L. (2023). Education in the Era of Generative Artificial Intelligence
(AI): Understanding the Potential Benefits of ChatGPT in Promoting Teaching and Learning. Journal
of AI, 7(1), 52–62. doi:10.61969/jai.1337500
Bolton, K., Bacon-Shone, J., & Lee, S.-l. (2020). Societal multilingualism in Hong Kong. In P. Siemund
& J. Leimgruber (Eds.), Multilingual global cities: Dubai, Hong Kong and Singapore (pp. 160–184).
Routledge. doi:10.4324/9780429463860-12
Bolton, K., & Lee, S.-l. (2020). A socio-historical approach to multilingualism in Hong Kong. In P.
Siemund & J. Leimgruber (Eds.), Multilingual global cities: Hong Kong, Singapore, and Dubai (pp.
38–62). Routledge. doi:10.4324/9780429463860-4
Chan, C. K. Y. (2023). A comprehensive AI policy education framework for university teaching and learn-
ing. International Journal of Educational Technology in Higher Education, 2023(20), 38. doi:10.1186/
s41239-023-00408-3
Chassignol, M., Khoroshavin, A., Klimova, A., & Bilyatdinova, A. (2018). Artificial Intelligence trends in
education: A narrative overview. Procedia Computer Science, 136, 16–24. doi:10.1016/j.procs.2018.08.233
Chen, L. (2023, June 23). Hong Kong rolls out first AI curriculum for junior secondary students, including
lessons on ChatGPT, with ‘lives definitely affected by artificial intelligence’. South China Morning Post.
Chen, L., Chen, P., & Lin, Z. (2020). Artificial intelligence in education: A review. IEEE Access: Practi-
cal Innovations, Open Solutions, 8, 75264–75278. doi:10.1109/ACCESS.2020.2988510
Chen, X., Zhou, D., Xie, H., Cheng, G., & Liu, C. (2022). Two decades of artificial intelligence in
education: Contributors, collaborations, research topics, challenges, and future directions. Journal of
Educational Technology & Society, 25(1), 28–47.
Chin, A. C. (2023). A corpus-based approach to learning and teaching Cantonese. In S. L. Lee (Ed.),
The learning and teaching of Cantonese as a second language (pp. 184–195). Routledge.

145

Discussions of Using AI in Language Education in Hong Kong

Chiu, T. K. F., Meng, H., Chai, C.-S., King, I., Wong, S., & Yam, Y. (2022). Creation and Evaluation
of a Pretertiary Artificial Intelligence (AI) Curriculum. IEEE Transactions on Education, 65(1), 30–39.
doi:10.1109/TE.2021.3085878
Cope, B., Kalantzis, M., & Searsmith, D. (2021). Artificial intelligence for education: Knowledge and its
assessment in AI-enabled learning ecologies. Educational Philosophy and Theory, 53(12), 1229–1245.
doi:10.1080/00131857.2020.1728732
Huang, X., Zou, D., Cheng, G., Chen, X., & Xie, H. (2023). Trends, Research Issues and Applications
of Artificial Intelligence in Language Education. Journal of Educational Technology & Society, 26(1),
112–131.
Jeon, J. (2022). Exploring AI chatbot affordances in the EFL classroom: Young learners’ experiences
and perspectives. Computer Assisted Language Learning, 1–26. Advance online publication. doi:10.1
080/09588221.2021.2021241
Ji, H., Han, I., & Ko, Y. (2023). A systematic review of conversational AI in language education: Focus-
ing on the collaboration with human teachers. Journal of Research on Technology in Education, 55(1),
48–63. doi:10.1080/15391523.2022.2142873
Kang, B., & Kang, S. (2022). Construction of Chinese Language Teaching System Model Based on
Deep Learning under the Background of Artificial Intelligence. Scientific Programming, 2022, 1–10.
doi:10.1155/2022/3960023
Kataoka, S. (2023). Textbook Cantonese romanization. In S. L. Lee (Ed.), The learning and teaching of
Cantonese as a second language (pp. 196–216). Routledge.
Kessler, G. (2017). Technology and the future of language teaching. Foreign Language Annals, 2018(51),
205–218.
Kim, N.-Y., Cha, Y., & Kim, H.-S. (2019). Future English learning: Chatbots and artificial intelligence.
Multimedia-Assisted Language Learning, 22(3), 32–53.
King, I. (2016, July 29). E-learning is the way forward for quality education. South China Morning Post.
Kohnke, L., Moorhouse, B. L., & Zou, D. (2023). ChatGPT for Language Teaching and Learning. RELC
Journal, 54(2), 537–550. doi:10.1177/00336882231162868
Lee, S. L. (2011). 高班閱讀課的網上課件 [Online components for advanced Chinese reading classes].
Journal of Technology and Chinese Language Teaching, 2, 1–22.
Lee, S. L. (2016). E-Learning Readiness in Language Learning: Students’ Readiness Survey and Nor-
malization Process. Journal of Technology and Chinese Language Teaching, 7(2), 23–37.
Lee, S. L. (2018). Modular approaches in eLearning design. Journal of Technology and Chinese Lan-
guage Teaching, 9, 48–61.
Lee, S. L. (2022). Synchronous online language teaching: a reflection from Hong Kong. In S. Liu (Ed.),
Teaching the Chinese language remotely: Global cases and perspectives (pp. 235–251). Palgrave Mac-
millan. doi:10.1007/978-3-030-87055-3_10

146

Discussions of Using AI in Language Education in Hong Kong

Liu, O., & Yau, C. (2023, March 22). Who needs a teacher? As ChatGPT takes off in Hong Kong, edu-
cationists worry about impact on teaching, learning. South China Morning Post.
Moorhouse, B. L., Wong, K. M., & Li, L. (2023). Teaching with Technology in the Post-Pandemic
Digital Age: Technological Normalisation and AI-Induced Disruptions. RELC Journal, 54(2), 311–320.
doi:10.1177/00336882231176929
Ng, D. T. K., Lee, M., Tan, R. J. Y., Downie, J. S., & Chu, S. K. W. (2023). A review of AI teaching
and learning from 2000 to 2020. Education and Information Technologies, 2023(28), 8445–8501.
doi:10.1007/s10639-022-11491-w
Pedró, F., Subosa, M., Rivas, A., & Valverde, P. (2019). Artificial Intelligence and Language Learning:
Opportunities and Challenges. Working Paper on Language Policy. UNESCO. Retrieved from https://
unesdoc.unesco.org/ark:/ 48223/pf0000366994
Rudolph, J., Tan, S., & Tan, S. (2023). ChatGPT: Bullshit spewer or the end of traditional assessments
in higher education? Journal of Applied Learning & Teaching, 6(1), 342–363.
Schmidt, T., & Strasser, T. (2022). Artificial Intelligence in Foreign Language Learning and Teaching:
A CALL for Intelligent Practice. Anglistik: International Journal of English Studies, 33(1), 165–184.
doi:10.33675/ANGL/2022/1/14
Sun, Z., Anbarasan, M., & Kumar, D. P. (2021). Design of online intelligent English teaching platform
based on artificial intelligence techniques. Computational Intelligence, 2021(37), 1166–1180. doi:10.1111/
coin.12351
The Chinese University of Hong Kong. (2021, 24 August). A 30-minute EEG Test Forecasts Chil-
dren’s Language Development. CUHK in Touch. Retrieved from https://cuhkintouch.cpr.cuhk.edu.
hk/2021/08/7463/
The Chinese University of Hong Kong. (2023). Use of Artificial Intelligence Tools in Teaching, Learning
and Assessments: A Guide for Students. Hong Kong: The Chinese University of Hong Kong. Retrieved
from https://www.aqs.cuhk.edu.hk/documents/A-guide-for-students_use-of-AI-tools.pdf
The Hong Kong Polytechnic University. (2023). Guidelines for Students on the Use of Generative Arti-
ficial Intelligence. Hong Kong: The Hong Kong Polytechnic University of Hong Kong. Retrieved from
https://www.polyu.edu.hk/ar/ docdrive/polyu-students/Student-guide-on-the-use-GenAI.pdf
Wang, T., & Cheng, E. C. K. (2021). An investigation of barriers to Hong Kong K-12 schools incorporat-
ing Artificial Intelligence in education. Computers and Education: Artificial Intelligence, 2.
Yaacob, Z., & Saad, N. H. M. (2020). Acceptance of YouTube as a learning platform during the Covid-19
pandemic: The moderating effect of subscription status. TEM Journal, 4, 1732–1739. doi:10.18421/
TEM94-54
Yueng, P. (2019, 31 January). AI will be a game changer for Hong Kong education. China Daily Hong
Kong.
Zai, X., Chu, X., Chai, C. S., Jong, M. S. Y., Istenic, A., & Spector, M. (2021). A review of artificial
intelligence (AI) in education from 2010 to 2020. Complexity, 2021, 1–18. Advance online publication.
doi:10.1155/2021/8812542

147

Discussions of Using AI in Language Education in Hong Kong

KEY TERMS AND DEFINITIONS

Blended Teaching and Learning: Blended teaching and learning or hybrid learning in this chapter
is defined as an educational model that combines classroom face-to-face learning experiences with
online learning experiences.
Cantonese: The term ‘Cantonese’ refers to the language varieties used by immigrants who came to
Hong Kong from various districts in Guangdong province, including Macau, Panyu, Taishan, Xinhui,
and Zhongshan. Over time, their speech coalesced into the contemporary variety of Cantonese used in
Hong Kong from the late nineteenth century onwards. Cantonese is often used to refer to the entire Yue
subgroup of Chinese, which includes varieties of Cantonese spoken in southern China, Hong Kong,
Macau, Malaysia, Singapore, and among overseas Chinese in North America, Europe, and Australia. It
is currently estimated that there are about 70 million Cantonese speakers in the world. Cantonese has
been and is a major language variety used by people in daily life in Hong Kong.
Computer-Assisted Language Learning (CALL): Computer-assisted language learning (CALL)
or Computer-aided instruction (CAI) is briefly defined as the search for and study of applications of the
computer in language teaching and learning. CALL includes a wide range of information and commu-
nications technology applications and approaches to teaching and learning foreign languages.
Normalization Process: Normalization refers to a social process through which ideas and actions
come to be seen as ‘normal’ and ‘natural’ in everyday life. The normalization process refers to a social
organization that brings practice or practices into action.
Putonghua: Putonghua is the official language of the People’s Republic of China. It serves as the
common national language of the PRC. Under Hong Kong’s Basic Law and the promotion of trilingual-
ism and biliteracy, Putonghua has an official status in Hong Hong.
Standard Written Chinese: A baihua yundong 白話運動 (‘vernacular language movement’) was
started in 1917 by the scholar Hu Shi 胡適. This baihua literary movement advocated adopting the bai-
hua 白話(‘vernacular’) style of Chinese as a written language to revitalize the Classical Chinese literary
language and make it more accessible to the common people. Baihua is the form of written Chinese
based on the varieties of Chinese spoken throughout China, in contrast to wenyan 文言(‘classical Chi-
nese’) or (‘literary speech’) used in Imperial China up to the early twentieth century. This movement
succeeded in making baihua the language of textbooks, periodicals, newspapers, and public documents.
Baihua now commonly refers to the standard written Chinese or modern written Chinese. Since the early
1920s, this modern vernacular form has been the standard style of writing for speakers of all varieties
of Chinese throughout mainland China, Taiwan, Malaysia, and Singapore as written form of modern
standard Chinese. Standard written Chinese (presented in traditional characters) is used in all official
and educational contexts in Hong Kong.
Trilingualism and Biliteracy: Since the 1990s, the Hong Kong government has promoted ‘trilin-
gualism and biliteracy’, which refers to the spoken command of Cantonese, Putonghua, and English,
and literacy in written Chinese and English.

148
149

Chapter 8
What Are Students Saying
About AI as an Academic Tool
Lee Luan Ng
https://orcid.org/0000-0001-6741-6201
Universiti Malaya, Malaysia

Venosha Ravana
https://orcid.org/0000-0002-4941-5309
Tunku Abdul Rahman University of Management and Technology, Malaysia

ABSTRACT
The introduction of artificial intelligence, ChatGPT, and other machine learning technologies has shaken
up numerous industries across the globe. The World Economic Forum Future of Jobs Report 2023 pre-
dicts that due to a combination of macro trends and technology adoption, over the next five years jobs
in the education industry are expected to grow at least by 10%. Many learners in higher education are
integrating the use of AI when attending to their academic work, yet there is not much investigation
exploring how they plan and perceive the use of AI whilst completing their academic tasks. Therefore,
this chapter aims to (1) explore how learners’ intention of using AI affects their language learning be-
havior and (2) uncover the factors that influence the learners’ perceptions toward the usefulness of AI
as an academic support. Grounded in the theory of planned behavior (TPB), students from two tertiary
education institutions in Malaysia were asked to respond to a series of questions that explored their
perspectives on utilizing AI-powered tools to aid their academic writing.

INTRODUCTION

The Status Quo of AI in the Academia

AI-powered tools such as ChatGPT, Google Bard, Bing, QuillBot and Gradescope, to name a few,
have gained global attention as the new fad in the education sector (Lim et al., 2023). Reiss (2021)
had anticipated that AI was going to transform education, and those who would benefit the most were

DOI: 10.4018/979-8-3693-0872-1.ch008

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

What Are Students Saying About AI as an Academic Tool

students with special and differentiated needs. In fact, Haleem et al. (2023) made a case that students
could potentially utilize AI tools in their academic works without the teacher ever knowing, i.e. to check
grammar or sentence structures. Simultaneously, as indicated in Figure 1, there has been press cover-
age that highlighted the potential issues that are linked to the emergence of AI in the education context.

Figure 1. Excerpts extracted from the websites of different newspaper related to the influence of AI on
the instructors and learners.
Last retrieved from The New Straits Times online on 31/08/2023

Due to this, various universities worldwide have developed guides or policies related to students’ use
of AI tools in academic works to delimit potential issues concerning academic integrity and assessment.
Table 1 presents some noteworthy excerpts from three different university guidelines that can be found
publicly online.

150

Table 1. Selected university guidelines on AI usage

Topic/Source The Chinese University of Hong Kong Heriot Watt University United Kingdom University of Western Australia
1. Published online in March 2023 February 2023 February 2023
“… There are different types of AI tools, for instance “… Artificial intelligence (AI) content creation “… Artificial intelligence tools have been
generative AI tools (e.g., Chat GPT) which can be tools cover a range of skills e.g., writing, art / used to support learning at universities for
easily instructed using ordinary human language design, computer coding. They create content based many years. Spell-checkers, email spam filters,
2. Definition of AI tools to generate various formats of texts. Some AI tools on questions that the user inputs to the tool. There search engines, speech-to-text tools and
and examples according facilitate the creation of ‘original’ artwork (e.g. is a wide range of AI content creation tools, you recommendation systems all use AI algorithms to
to the institution DALL·E 2), translated text (e.g. Google Translate), may have heard of some of them e.g., ChatGPT, help us get things done at uni.
formulas (e.g. Sheet+), and computer code (e.g. OpenArt, Dalle-2, Hugging Face. You have Recently some generative artificial intelligence
OpenAI Codex), etc. applicable to a great variety of probably already used some of these tools without tools, such as ChatGPT and Bing, have become
use.” even realising, e.g., Microsoft Editor.” prominent.”
“…AI is a double-edged sword; we should use but “… UWA’s Academic Integrity Policy allows
“…Think carefully and critically about the risks,
3. Reminder for not abuse it, use it as research but not cheating tool, for the limited use of AI in research, study and
benefits and ethics before you make use of any
students and most importantly, use AI to think with you, but assessment. The policy permits you to use AI as
technology, including AI content creation tools.”
not for you.” educational and study tools.”
“…Students are prohibited from using any AI tools
in their assignments and assessments that count “…If you were to use an AI content tool to draft /
What Are Students Saying About AI as an Academic Tool

“…these tools must not be used as a replacement

towards students’ final grade of the course, or for write your assessment, then the assessment would
of your critical thinking and analysis skills. AI
evaluating their attainment of the desired learning not be your own work. If you do use an AI tool in
tools may only be used in an assessment where it
4. Regulations on the outcomes.” any way, ensure that you clearly identify any work
is explicitly permitted by your Unit Coordinator.
use of AI tools “…In courses where students are allowed or in an assessment which is not your own work e.g. if
Where it is permitted by your Unit Coordinator
expected to collaborate with or use AI tools, students you ask questions of an AI tool and use the answers,
to use AI, you must always cite and reference
may use these tools for in-class learning activities, then this would not be wholly your own work and
your uses of it.”
exercises or assignments as long as they explicitly should be identified and referenced appropriately.”
cite or acknowledge the use of these tools.”
“…Improper use of AI-generated material
in assignments for assessment is grounds for
“… Similar to other serious cases of academic “… The Heriot-Watt Student Discipline Policy academic misconduct. Remember, there is no
dishonesty, penalties for improper/unauthorized use clearly states that submitting work which is not time limit on when an occurrence of academic
5. Possible repercussions of AI tools in assignments/assessments may include your own is academic misconduct and a form of misconduct can be detected.
of undeclared use of AI reviewable/permanent demerit(s), failure grade cheating. Being found to have committed academic This means that even if improper use of AI is
for the course concerned, suspension from the misconduct has potentially severe consequences for not detected at the time of submission, it can
University.” your studies and future employment.” be in the future, and misconduct penalties can
be applied retrospectively, including after you
graduate.”

151

What Are Students Saying About AI as an Academic Tool

Generally, these tertiary learning institutions have acknowledged that the usage of AI tools among
students for academic-related tasks cannot be monitored or regulated fully at any given point. Based on
the definitions of AI given in the guidelines, universities also accept the existence of various AI-powered
tools that serve different purposes and highlight the multifaceted nature of AI support in academia. In-
terestingly, the use of tools like Microsoft Editor suggests that some students may have already unknow-
ingly utilized AI-powered features, highlighting the seamless integration of AI into academic workflows.
The increased media discourse regarding the ethics related to using AI to produce written products by
students has indirectly coerce universities to alert as well as remind students about the ethical, critical,
and balanced use of AI in academia. The idea of AI as a “double-edged sword” is introduced, empha-
sizing that AI should be used judiciously and responsibly. Students are advised to use AI as an aid in
their academic pursuits, helping them with problem-solving tasks, but not as a substitute for their own
intellectual efforts. Many institutions of higher learning began to come to terms on the importance of
promoting a balanced approach to AI usage in education.
While threats of disciplinary action may be apparent in the guidelines, it is still unclear to many as
to what extent are students willing to take the risk in getting some extra support for their assignments
or tests. It is an interesting premise worth exploring; that is to look at how students make sense of the
disruptive technology of AI in education while still adhering to rules, policies and guidelines set by their
respective higher learning institutions.

AI in English Language Teaching and Learning

In the context of English language teaching and learning, Ray (2023) had found AI-powered tools to
enhance students’ productivity in various proficiency-based tasks. In more specific instances, Lakkala
et al. (2022) had shown that Poetry Machine helped students to develop and revise poems written during
literature class while Su et al. (2023) claim that digital story writing (DSW) turned out to be an effective
and meaningful inquiry-based pedagogical approach in teaching writing to EFL students.
Some common areas that language instructors integrate AI into teaching and learning are assessment
and feedback, translation support and content creation. In terms of assessment and feedback, Duolingo
offers a wide range of language courses which can be personalized according to students’ starting
proficiency levels and provides instant feedback based on the listening, speaking, reading and writing
exercises performed (Maria et al., 2018). LanguageTool has also been recently added as an extension
to Microsoft Word and Google Docs as an official grammar and style checker (Puspitasari et al., 2022).
Secondly, there are recent developments for translation support that particularly helps EFL students apart
from ESL students. Other than Google Translate which offers text translation, voice translation, and im-
age translation, Deep Learning approach of AI can also be utilized for high-quality machine translations
(Birdsell, 2022) which allows EFL students to learn English using authentic materials. While content
creation is also fast becoming a blooming area with AI’s intervention as language exercises, quizzes,
and testable content like reading passages or audio materials can be created and tailored to students’
varied proficiencies and needs. Tools like ChatCPT and Articoolo support these functions well and are
available for free at the time being (Lim et al., 2023).
However, just like everyone else, language scholars seem to be concerned that AI-powered tools
could end up as a double-edged sword in the context of language teaching and learning. These concerns
revolve around the transformative impact of AI on education and its implications for students, educators,
and society as a whole. The first concern relates to the increasing personalization in education using new

152

What Are Students Saying About AI as an Academic Tool

technologies; Chen et al. (2020) shared an alarming prediction where AI-powered tools could end up
further dividing students from their peers, teachers and the society as students may become dependent
on AI for tutoring. This overreliance on AI could result in the fragmentation of the learning experience,
isolating students from the rich social and collaborative aspects of education. Secondly, Carvalho et al.
(2022) also highlighted their concern on how practitioners may still not have figured out the ways to
support the young generation of learners to develop the skills that they will need to adapt to and innovate
with AI. This includes prompting skills (Mackenzie, 2023) and academic integrity of using AI-generated
knowledge and information (Lim et al., 2023). It is a great fear that when students use AI tools with
inadequate awareness, it may lead to a generation of learners who are highly proficient in navigating
AI-driven educational environments but lack essential interpersonal and critical thinking skills.
Therefore, there is a pressing need to gather a comprehensive understanding of university students’
lived experiences and perceptions when utilizing AI-powered tools in English language learning based
on qualitative data. As urged by researchers Bilquise and Shaalan (2022), this would greatly help to shed
light on the potential benefits and challenges students encounter, with a particular emphasis on how these
tools may enhance or hinder students’ language skills. These insights are particularly vital in informing
educators and tertiary level institutions about the best practices in integrating AI into language educa-
tion. Insights from qualitative data may provide more substantial evidence and support for AI-related
policies in the education sector.

The Theory Behind It All: Quick Dive Into the Theory of Planned Behavior (TPB)

In order to explore how students perceive and use the existing AI, this chapter aims to capture students’
viewpoints towards the emergence of AI in education and the ways to go forward. To provide a more
meaningful analysis of students’ perspectives and expectations of AI-powered tools in day-to-day
language learning activities, the authors have decided to explore the data using the Theory of Planned
Behavior (TPB).
TPB is a psychological theory that provides insights into how individuals’ attitudes, subjective
norms, and perceived behavioral control influence their intentions and behaviors (Ajzen, 1991). It posits
that individuals’ intentions to engage in a specific behavior are influenced by three main constructs:
attitudinal behavior (AB), subjective norms (SN), and perceived behavioral control (PBC). These three
constructs collectively shape an individual’s behavioral intentions. Higher positive attitudes, perceived
social support (subjective norms), and a stronger belief in their ability to control the behavior led to a
greater intention to engage in that behavior. TPB advocates that behavioral intentions are the immedi-
ate antecedents of actual behavior. In other words, stronger intentions are more likely to result in the
desired behavior. TPB has been applied across various domains, including health psychology, marketing,
environmental behavior, and social sciences, to explain and predict human actions. It has proven to be a
useful framework of reference for behavioral related studies such those related to intervention for desir-
able behaviors. In his study, Ajzen (1991) utilized TPB to examine how beliefs and attitudes influence
the adoption of environmentally friendly behaviors. The findings revealed that individuals with more
favorable attitudes and subjective norms were more likely to engage in performing the intended actions.
Similarly, in exploring the students’ intention toward the inclusion of AI in their academic work pro-
cess, it will be important to understand if the students’ attitudinal behavior (AB), subjective norms (SN),
and perceived behavioral control (PBC) affect their perceptions and usage of AI in attending to their
academic tasks. As shown in the study of Chai et al. (2023), TPB is also helpful to understand students’

153

What Are Students Saying About AI as an Academic Tool

intentions to use AI as academic support, and this in turn, sheds light on their decision-making process.
In the context of the current study, TPB can be applied in the ways shown in Figure 2.

Figure 2. Theory of planned behavior in context

In summary, the TPB framework is well-suited to analyze university-level students’ usage of AI-
powered tools for academic support because it provides a comprehensive model that incorporates in-
tentions, attitudes, subjective norms, and perceived behavioral control. Its well-established predictive
power and practical applications make it a valuable tool for understanding the factors influencing AI
tool adoption in educational contexts.

THE STUDY: UNVEILING STUDENT PERSPECTIVES

Methodology of the Current Study

This research uses a qualitative approach that involves conducting semi-structured interviews with
participants who had experienced using AI in attending to their academic work. 8 students enrolled in
2 different tertiary learning institutions in Malaysia were selected based on convenience-based non-
probability sampling method. 4 students were diploma level students at a private university while another
4 were postgraduate level students at a public university. All students were well briefed about the study
in prior to engaging them in individual semi-structured interview sessions.

154

What Are Students Saying About AI as an Academic Tool

The interviews were recorded using audio recording devices and later on be transcribed. The qualitative
approach offers an in-depth understanding of complex phenomena by exploring nuances, contexts, and
subjective experiences. Whilst semi-structured interviews, a key qualitative tool, enabled the researchers
to ensure that the interview questions posed during the interviews address the key dimensions of TPB,
as well as foster rich insights and accommodate individual perspectives. Table 2 presents a validated
semi-structured interview protocol used in the current investigation.

Table 2. Proposed semi-structured interview protocol

Perceived Behavior
Domain Attitude Subjective Norms Others
Control
h. Based on your previous
c. Have you observed e. Have you already used experiences, how satisfied are
a. What are your initial other students using AI AI tools such as ChatGPT you with the performance and
thoughts or feelings tools for their studies? or Google Bard for results of AI tools?
about using AI tools for How has that impacted academic purposes? i. In your experience, what
academic assistance? your perception of these f. If yes, how often and for are the weaknesses of AI
Questions*
b. What specific tools? what tasks? tools for academic support?
academic tasks do you d. Have you discussed g. What factors might j. Are there any specific
believe AI tools could AI tools with your peers influence your decision features or improvements
help you with? or lecturers? If yes, what to continue or discontinue you would like to see in AI
were their opinions? using AI tools? tools to better support your
academic needs?
*Questions developed based on literature on AI tools for education and the Theory of Planned Behavior. Questions have been loosely
adapted from the qualitative instruments and findings from the studies of Sumakul et al. (2022) and (Burkhard, 2022).

In terms of data analysis, the analysis of the transcribed interview data basically involved the use of
content and thematic analysis. Content analysis plays a key role in enabling a systematic examination of
data. It involves the labeling of condensed meaning units by formulating codes and then grouping these
codes into categories (Erlingsson & Brysiewicz, 2017).
Thematic analysis, on the other hand, focuses on identifying, analyzing, and reporting patterns
(themes) within the interview data. As stated by Braun & Clarke (2006), themes capture a prominent
aspect of the data in a patterned way. Not only thematic analysis offers flexibility in terms identifying
trends, it also promotes interpretive depth and helps to uncover complex interrelationships between
themes (Braun et al., 2020). Both methods provide rigor for uncovering insights and understanding the
underlying meanings and nuances.

Background of Study Participants’ Usage of AI in Language Classrooms

According to Xuan et al. (2023), a majority of tertiary level learners in Malaysia have started using AI-
powered tools in their classrooms in 2023. To exemplify, in a Malaysian private university, diploma level
students from various faculties are allowed to use AI-powered tools such as ChatGPT for one of their
coursework for the language course, Academic English. The coursework is referred to as a ‘Grammar
Project’ which constitutes 30% of their overall coursework grade. The instruction for the coursework is
as follows:

155

What Are Students Saying About AI as an Academic Tool

Box 1.

Coursework 3: Grammar Project (30%) Week 6

Description
This is a group project consisting between 3 and 4 students. Students are tasked to prepare an activity in presenting a grammatical item
assigned to them. Subsequently, students have to present the grammar activity in the class. Each group is given 20-30 minutes to present.
Students may use online materials or AI-powered tools approved by their tutor at all stages of this activity.

Assessment Criteria
Students will be assessed on the following:
• The ability to write a feasible plan outlining the materials, timelines and description of the grammar project.
• The ability to contribute to the grammar activities
• The ability to present appropriate grammatical item in a creative way
• The ability to cooperate in group activities
• The ability to answer questions about the grammar activities presented

Marking Criteria
• Outline: 5 marks
• Language: 30 marks
• Content: 30 marks
• Delivery: 30 marks
• Q & A: 5 marks

Total: 100 marks

This coursework supports Quality Education under the 17 groups of the Sustainable Development Goals.

For this project, students are required to prepare an activity which allows the whole class to revise
various grammatical items using interesting activities such as games, quizzes and more. At the planning
stage, tutors allow students to utilize search engines and AI-powered tools such as ChatGPT, Bing or
Bard to gather ideas on the kinds of classroom activities they can do for topics such as tenses, sentence
structures, active-passive sentences, direct and indirect speeches, prepositions and adjectives and adverbs.
A sample query performed on ChatGPT by one of the groups is presented in Figure 3 along with
response. The grammar topic assigned to them was Adjectives and Adverbs.
Using this guide, the students then adapted this activity with some changes and submitted an outline
to the tutor to be approved. The tutor also provides some feedback to the students. A sample is shown
in Table 3.
Using this example, it can be understood that while students may turn to AI-powered tools to help
them with their language assignments, they also have the opportunities to infuse their own creativity and
ideas into the suggestions provided by the AI tools. Unfortunately, some tutors have reported whereby
students were found to copy-paste Chat-GPT’s suggestion of activities directly into the outline of gram-
mar project and submit as their own. The tutors found themselves in a tricky situation to award marks
for outline in this case as nowhere in the coursework brief it was mentioned that students cannot copy
directly from AI sources. The course coordinator of Academic English subject at this particular university
has been alerted to update the coursework brief to reflect ethical use of AI-powered tools.
To further expand on this phenomenon, this study has conducted interviews with selected diploma
and postgraduate students from two universities in Malaysia. Findings are presented in the next section.

156

What Are Students Saying About AI as an Academic Tool

Figure 3. Sample response from ChatGPT for a query from students

L a st ret r i e ve d o n 3 1 / 1 2 / 2 0 2 3 a t h t t ps :/ / cha t .o p en a i. co m /c / 32 2 26 7 18 - e3 1 f- 4 c5 d -b d 43 - 95 7 f1 4 7 bf 6
7b

Table 3. Sample grammar project outline submitted for tutor’s approval

Topic Adjectives and Adverbs

Members in the
3
group
First, we will introduce different types of adjectives and their uses using a short presentation on Canva.
Next, we will divide the class into 3 groups and each of us will be in charge for a group. We will then provide each
group with some photos that we have taken from around the campus. Photos will be taken from canteen, indoor
and outdoor events and general outings of our classmates.
Activity
They then need to create as many sentences as they can based on the theme given. The themes we have selected
Description
for the groups are “feelings”, “colors” and “numbers”. They are given only 10 minutes for this. The group with the
most number of sentences that match the theme given, wins the game.
To show our own understanding of adjectives, once the groups have completed, the three of us will explain the
types and uses of the adjectives found in their sentences.
Materials Canva presentation, printed photos on A4 papers, more papers, candies as rewards
Other Remarks This activity has been improvised from a Chat-GPT suggestion on 20th December 2023.
Good plan! Please make sure they do not take more than 10 minutes to write sentences, or else you will not be able
to complete this activity within 20 minutes. Secondly, since you have already explained different types of adjectives
and uses in the introduction, it may be redundant to do that again with the students’ sentences. I would suggest you
Tutor’s Feedback
to try change the adjectives identified into adverbs (if possible) to demonstrate the relationship between adjectives
and adverbs. This may give you better roles to play for this activity, and I will have more substance to grant you
marks out of 95.
Marks given for
4/5 marks
this outline

157

What Are Students Saying About AI as an Academic Tool

FINDINGS AND DISCUSSION

To maintain anonymity of the students for ethical purposes, in the presentation of findings, the diploma
level students are identified as S1, S2, S3 and S4 while the postgraduate students are R1, R2, R3 and
R4. This section presents the findings upon thematically categorizing the main ideas detected from the
interview responses of all the students. Selected excerpts are also shown for illustration purposes. It is
to be noted while section 2.2 shows how students have specifically used ChatGPT for the preparation
of Grammar Project, this section presents findings from their general and overall usage of AI-powered
tools throughout their semester.

The Role of Intention in Perceiving AI as a Companion

From the lens of TPB, to understand students’ intention to use AI for language learning, it is important
to first understand their initial thoughts on AI. Responses for the question on initial reaction show that
students perceived AI as a tool for improvement and enhancement in various academic tasks, as an
advanced and amazing technology, and also as a tool worth cautioning.

Using AI as a Tool for Enhancement of Academic Work

As simplified in Table 4, all the postgraduate participants were found to use various AI tools to improve
their academic work in terms of rephrasing, replacing words, double rephrasing, summarizing, and
researching.

AI Is Viewed as an Advanced and Amazing Technology

Students such as S2 expressed a sense of wonder and amazement about the rapid and sudden advanced
nature of AI tools, suggesting that university students may be impressed by the capabilities of AI tech-
nology, possibly implying a willingness to explore it.
Similarly, R2 seemed to be impressed with AI’s capabilities as well when she said:

“My classmates’ use of AI tools actually made me look highly of AI tools, because I found that they
would ask AI tools about some very basic questions like what was definition of ‘foregrounding’, and the
AI tools could provide some straightforward explanations.” (R2)

On the other hand, some participants perceive AI in a less favourable manner, whereby the students
felt that it’s not all about AI is “hunky-dory” in nature. The next section depicts some of the students’
views on the hidden risks of AI.

AI Is a Tool That Should Be Used With Caution

S3’s response reflects a more cautious perspective, influenced by depictions of AI in movies as potentially
harmful or destructive to humanity. This alludes that some students may approach AI with caution for
its potentially negative consequences. He stated:

158

What Are Students Saying About AI as an Academic Tool

Table 4. Academic tasks participants performed using AI tools

Task Description Excerpt From Interviews

AI tools can use advanced natural language processing
algorithms to generate alternative versions of a given
“…I feel that AI is an exceedingly valuable tool to
sentence while preserving the original meaning. This can
Rephrasing be used as an academic assistance, specifically in
be particularly useful when trying to rephrase information
sentence paraphrasing” (R3)
from existing sources or when attempting to avoid repetitive
language in academic writing.
“…mostly for proofreading and give me
It is also understood that AI tools can provide suggestions for
suggestions on how to improve my writing and
synonyms or alternative word choices that are contextually
make my writing more “academic”. (R4)
Replacing Words appropriate for academic writing. This feature can help
The same participant also stated that: “It can give
students improve the variety and precision of their vocabulary,
me advice from various perspectives like clarity,
making their writing more sophisticated and effective.
consistency, grammar, transitions, etc.”
“Double paraphrasing (i.e., using ChatGPT to
Double paraphrasing involves using AI tools to generate a generate a paraphrased academic sentence or
paraphrased version of a sentence or paragraph and then paragraph from past studies, and use Quillbot
Double
applying another AI tool for further paraphrasing. This to paraphrase the same sentence/paragraph the
Paraphrasing
iterative process can help refine and enhance the clarity, second time). AI tools can also help with widening
coherence, and originality of the written content. one’s academic vocabulary and aid in filtering
relevance studies for academic use…” (R3)
AI tools can automatically extract key information and
main points from lengthy journal articles, providing concise
“…I have used AI tools such as ChatPDF to
Summarizing summaries that capture the essence of the original content.
efficiently summarize relevance journal articles”
journal articles This enables researchers to quickly grasp the main findings
(R3)
and implications of a study without having to read the entire
article, as pointed out by one of the participants.
Students seem to use ChatGPT to gather information on topics
“I try to search on Google for some information,
easily. Instead of browsing multiple websites or articles, they
Researching which I can’t get, so then I use ChatGPT to get the
seem to appreciate that they can find concise information at a
information instead.” (S1)
one-stop ChatGPT.
“I now use it as a starting point for my
For Daily use Some students seemed to have familiarized themselves with assignments, but I also already AI tools like
outside of AI-powered tools in daily life activities outside of academic SIRI with my daily activities such as to wake
Academic Work work way long before they started using it in classrooms. up on time. For the easy things, such as calling
somebody or setting alarm” (S4)

“I think, before the AI thing really came out, I thought it is something that could destroy humanity, based
on the movies that we have watched before. So, we should be careful with it.” (S2)

It’s important to note that while AI tools can be valuable for these specific tasks, some postgraduate
students also mentioned that they should be used judiciously and in conjunction with human judgment.
Students and researchers should critically evaluate the output generated by AI tools, verify the accuracy
of information, and exercise caution to avoid potential issues such as plagiarism or overreliance on
automated processes. As pointed out by a participant (R1):

“It might lead to overreliance and hinder genuine academic progress. This concern is particularly
relevant for non-native English speakers, as GPT’s direct translation feature could make one lazy and
impede real academic improvement.”

159

What Are Students Saying About AI as an Academic Tool

Emphasizing on the enabling factors, the students generally demonstrated a positive attitude towards
using AI tools for various academic tasks. A majority of them mentioned using AI, like ChatGPT, to assist
with paraphrasing, editing and proofreading, locating appropriate research articles and summarization.
This suggests that they see AI as a helpful and effective tool for improving their academic work. Their
intention to use AI for these tasks is influenced by their positive attitude towards its potential benefits.
In fact, S4 mentions using AI tools like Siri for daily tasks, which indicates a general acceptance of AI
technology.
S2, S3 and R1, on the other hand, did not express a positive attitude towards using AI for academic
tasks; which implies a lack of interest or enthusiasm. This can be attributed as a cautionary factor among
the students interviewed.
In summary, the students’ responses reflect varying attitudes and perceived behavioral control when
it comes to using AI for academic tasks. Attitude, as demonstrated by their views on the usefulness of
AI, plays a significant role in shaping their intentions.

Social and Contextual Factors Shaping Student Perceptions

2 questions were formulated to dive into the various social or contextual factors that affect how students
perceive AI in language learning. The first is, have you observed other students using AI tools for their
studies and the second is, have you discussed AI tools with your peers or lecturers? If yes, what were
their opinions?
In short, the responses to Question 3 and Question 4 highlight the significant role of subjective norms,
including peer behavior and opinions of authority figures (teachers/lecturers), in shaping students’ per-
ceptions and intentions related to AI tools for academic purposes. Mostly students’ decision to use AI
to a certain extent is influenced by the individuals such as friends, classmates.

Friends and Lecturers Use AI Tools Openly

S1 observed other students using AI tools and saw it as a positive influence. The student noticed that
others were benefiting from AI, which encouraged him to try it himself. In another similar situation, S4
saw most of his classmates using AI tools and felt left out because he thought that he was not thinking
as creatively. He admitted to have started using AI for academic tasks in order to appear to be more cre-
ative. On the other hand, S2 also observed his classmates using AI tools but had a negative perception
of it. He mentioned that the answers generated by AI felt artificial and not genuine.
When asked if they discussed AI with their peers or lecturers, S1 answered that peer discussion likely
reinforced his positive perception of AI tools and his intention to use them for academic purposes. S2
mentioned that some lecturers allow the use of AI tools in classrooms. This suggests that there is some
level of acceptance by authority figures (lecturers), which can positively influence students’ perceptions
and intentions to use AI in academic settings.
In another interesting instance, R3 also noted about peers who used AI-powered tools openly for
classwork:

“A friend of mine used AI tools for double paraphrasing purposes. The AI tools have helped her to complete
tasks efficiently and produce quality academic writeups. This completely changed my perception towards
AI tools and since then, I have started using them as academic support for my PhD thesis writeup.”

160

What Are Students Saying About AI as an Academic Tool

Some Parties Are Not in Favor of AI Tools

S4, on the other hand, mentioned that using AI in university is discouraged, and lecturers deem students
as lazy when they use it. This negative view expressed by lecturers likely had a discouraging effect on
students’ intentions to openly discuss and use AI. S4 confessed that he still uses AI, but without declar-
ing it to anyone around him, especially to his lecturers.
R1 also shared similar views whereby she said:

“I have discussed it with my peers. Most of them are not good at using it. One of my peers told me that
she doesn’t think GPT is very useful, perhaps GPT plugins are more useful.” (R1)

Thus, one can conclude that due to the influence of individuals in their social circles, some of these
students do think of AI in a less favourable manner.

Social Factors Shaping Student Perceptions

It can be concluded that positive peer behavior and support from teachers can encourage the use of AI,
while negative peer perceptions and discouragement from lecturers can deter its adoption. These find-
ings align with the principles of the Theory of Planned Behavior, where subjective norms play a crucial
role in shaping intentions and behaviors.
It is important to note that subjective norms refer to the perceived social pressure to perform or not
perform a behavior. If students’ peers or professors have a strong opinion against using AI for academic
tasks, this could potentially influence their intention not to use AI.

Students’ Perceived Control Matters When Dealing With AI

Based on the interview data, due to the varying experience in incorporating AI as a tool when attending
to their academic tasks, whereby a number of students even admitted that they only begun to explore
the use of AI in aiding their academic work, the data that relates to students’ view on how much control
they feel they possess in terms of integrating data was very limited. Therefore, the findings that relates
to the perceived behavioral control are presented in a single paragraph.
In general, when the participants were asked to share what factors would help them decide if they
would continue or discontinue using AI tools for academic purposes. Some students expressed the in-
tention to continue using AI, citing the busy schedule and the need for efficiency in completing tasks.
This response seems to align with a perception of high control, as AI is seen as a practical tool that helps
manage time and workload effectively. It is to be noted that participants like S1 and R1 were consistent
in expressing a positive attitude toward AI, viewing it as a tool for improvement. Similarly, S2 mentioned
turning to AI for help when struggling with assignments, especially when his friends are not helpful or
do not contribute to the generation of ideas. This indicates a perceived level of control over the decision
to use AI in specific situations where personal resources (ideas from friends) are limited. On the con-
trary, S3 mentioned a condition under which he would discontinue using AI if it becomes too smart and
scares him. This indicates a perception of potential risks associated with AI becoming too advanced. It
appeared to be that his decision was influenced by perceived risks and a lack of control over potential
negative outcomes. In short, students’ perceptions of control may be influenced by factors such as the

161

What Are Students Saying About AI as an Academic Tool

perceived efficiency and time-saving benefits of AI, the availability of alternative resources (like friends
for ideas), concerns about potential risks, and considerations about the impact on cognitive processes.
As stated by Gado et. al (2022), the results in their study showed that apart from perceived useful-
ness of AI, attitude towards AI, perceived social norm regarding AI; student’s perceived knowledge of
AI turned out to be important predictors of individuals’ intention to use AI. In the context of the present
study, many of these students seem to have very limited experience in using AI when dealing with the
various learning tasks, thus it is not surprising that many of them did not revealed much about their
views regarding how much behavioural control they possess when dealing with AI.
Incidentally, based on the interviews carried out with the diploma level students, the findings revealed
that the students’ English language proficiency does play a role in shaping their views regarding the
roles and usefulness of AI.

Perception Shaped by Language Proficiency of Students

Interestingly, the participants responses to questions related to perception also differed based on their ESL
proficiency levels. It is to be noted that S1, S2, S3 and all postgraduate participants were intermediate
to advanced users of ESL while S4 was a beginner level user.
S1, who had an intermediate to advanced level of ESL proficiency, did not mention any weaknesses
other than the potential issue of plagiarism. This response indicates a generally positive view of AI
tools, with a specific concern related to academic integrity. S2, with intermediate to advanced ESL
proficiency, identified a weakness related to the artificial sound of some answers. Similarly, S3, with
intermediate to advanced ESL proficiency, highlighted a weakness related to the depth of information
provided by AI. He said:

“Sometimes, the information provided is too deep for our knowledge. Some assignments just want simple
and basic answers but the AI’s answers are too deep for me to understand. So, even if we use it in as-
signment, it won’t be useful for us.” (S3)

Some students’ proficiency level likely contributes to recognizing the challenge of aligning AI-
generated content with their own comprehension levels. On the contrary, S4, who is a beginner level
ESL user, mentioned a weakness related to students becoming lazier and dependent on AI. His response
suggests a broader concern about the impact of AI on student behavior and work ethic.
In general, students with higher ESL proficiency levels might be more attuned to language-related
weaknesses, such as the artificiality of responses or the complexity of information provided by AI. On
the other hand, students with lower ESL proficiency levels might focus on broader concerns about the
impact of AI on learning habits rather than specific linguistic aspects. This can be seen in the differences
of responses of the diploma level students who were more general in their responses and the postgraduate
students who mentioned very specific linguistic aspects. One main takeaway from this finding is that
the language proficiency of students can shape how they utilize AI and in their daily academic tasks
understand the strengths and weaknesses of AI tools. This insight can be valuable for educators and re-
searchers aiming to implement or study the impact of AI tools in diverse language learning environments.

162

What Are Students Saying About AI as an Academic Tool

AI USAGE AMONG STUDENTS FROM THE LENS

OF THEORY OF PLANNED BEHAVIOUR

Based on the findings presented, it is very clear that intentions matter, perceptions are complex, and
student voices are crucial. One of the major findings from this study is that, intention does matter in
the context of students’ usage of AI-powered tools for academic support. As agreed by Choi and Suh
(2022), intention acts as a crucial factor to consider when analyzing students’ behavior and attitudes for
learning. The Theory of Planned Behavior (TPB) emphasizes the significance of intention in predicting
and understanding behavior (Niepel et al., 2018).
Intention should be part of needs assessment moving forward for adds predictive power. Ajzen (1991)
asserts that intention serves as a strong predictor of actual behavior. In the TPB, intention is a key deter-
minant of whether an individual will engage in a specific behavior, such as using AI-powered tools for
academic support. Students’ intentions to use or not use these tools can provide insights into their likely
behavior. Also relating the current findings to studies by Prasad and Jaheer (2023) and Tuomi (2018),
students’ intentions may be influenced by their attitudes (whether they see AI tools as beneficial), sub-
jective norms (what their peers and professors think), and perceived behavioral control (how easy they
perceive it to use AI tools) as well.
Acknowledging that individuals’ attitudes and beliefs are multifaceted is vital in accepting the complex
views presented by students. As supported by Soomro et al. (2015) students performing academic tasks
in English may come from diverse backgrounds and have unique educational experiences. Due to this,
their prior exposure to AI, technology, and academic environments can vary significantly. This diversity
leads to a wide range of perceptions about AI tools. Some students may be highly familiar with AI and
embrace it, while others may be less experienced and more apprehensive. Furthermore, perceptions are
also influenced by subjective norms, which according to Ajzen (1991), represent the perceived social
pressure or expectations of others. Students may be influenced by the attitudes and behaviors of their peers,
instructors, and the wider academic community. As proven in a similar study by Ramirez-Anormaliza
et al. (2015), these external influences can contribute to the complexity of students’ perceptions about
their learning environments.
This is related to the final point, where students’ voices are crucial in understanding their changing
views and multi-faceted concerns regarding AI’s influence in the education sector. According to Ajit
et al. (2022), student voices can be instrumental in tailoring support services and interventions. In the
context of the current study, if the students express concerns about AI making them lazier, institutions
can use their voices to design interventions that promote responsible and effective AI use. This is to
ascertain that as students’ perceptions evolve, their feedback can drive ongoing enhancements to AI
tools, ensuring that the tools remain relevant and effective over time.
In line with what has been proposed by Ajit et al. (2022) regarding the significance of student voices
or opinions in the endeavour to enhance the usefulness of AI, the present investigation also asked these
students for suggestions pertaining to the weaknesses of AI tools for academic support, as well as if
there any specific features or improvements AI tools that they opine will better support their academic
needs. The suggestions given are presented in the next section.

163

What Are Students Saying About AI as an Academic Tool

WHAT STUDENTS WANT: SUGGESTIONS FOR THE FUTURE

Pertaining to the last question of the interview protocol, “Are there any specific features or improvements
you would like to see in AI tools to better support your academic needs?”. Overall, the diploma-level
students’ responses indicate a mix of contentment, recognition of limitations in suggesting improvements,
and specific requests for features that align with their individual preferences and needs.

AI Tools Are Good as They Are

S1 expresses satisfaction with the current state of AI tools, indicating that he does not have any specific
features or improvements in mind. This might suggest contentment with the existing functionalities,
possibly reflecting a positive overall experience with AI tools. S2 too perceives the current tools as ef-
fective and sufficient for his needs.

Adding Voice Features to AI Tools

S3 and S4 actually offered some useful suggestions. S3 suggested the addition of voice features to AI
tools. He mentioned that listening would be preferable to reading, indicating a preference for auditory
learning. This request for voice features aligns with a specific learning preference, possibly influenced
by his personal learning style. S3 was interviewed in September 2023, and perhaps he was not aware of
the voice command features that were being integrated into many popular AI tools. However, by October
2023, many AI tools have published guides in activating voice commands to generate response.

Figure 4. Bing’s voice command feature published in June 2023

164

What Are Students Saying About AI as an Academic Tool

More Self-Learning Support From AI Tools

In another interesting sharing, S4 expressed a desire for AI tools to facilitate studying at home without
the need to come to school. He specifically mentioned the wish for classes, mini lessons, or tutorials from
AI tools. This request implies a desire for more comprehensive educational support beyond information
retrieval, possibly reflecting a preference for a more structured and guided learning experience. Rec-
ognizing individual learning preferences is crucial when designing or improving AI tools for academic
support. Features such as voice support or structured learning modules might enhance the overall user
experience for some students.

FINAL THOUGHTS

Learning Together in the Age of AI

Whether individuals such as students or instructors embrace AI or not, AI and AI-related tools are already
a part the academic life and are here to stay. Henceforth, it is the responsibility of learners and instructors
alike to learn what they are and how to harness AI potentials (Esplugas, 2023).
An ideal AI-powered language learning tool, based on the students’ input for the current study and
aligned with the Theory of Planned Behavior (TPB), should prioritize positive attitudes, social influence,
perceived behavioral control, and seamless integration with academic tasks. Customization options,
feedback mechanisms, and features addressing specific concerns contribute to a well-rounded language
learning experience that caters to the diverse needs and preferences of students. In visualizing an AI-
powered tool that can support language learners, attention should be given to adaptive learning paths
(Kularbphettong et al., 2015), feedback (Butow & Hoque, 2020), cultural context integration (Tuomi,
2018), interactive conversations (Ligorio, 2022), offline learning support (Radha et al., 2020) and mul-
tilingual support (Tamim, 2021).
At this juncture, it is important to encouraging ongoing dialogue between students, educators, and
developers as it is pivotal for the effective and inclusive integration of AI in educational settings. As
suggested by Reiss (2021), the authors of this chapter too strongly believe that continuous dialogue
among stakeholders ensures that AI tools are developed in a user-centered manner. By actively engaging
students, educators, and developers in discussions, the tools can be tailored to meet the diverse needs
and preferences of the users, resulting in more effective and relevant solutions for 21st century education
and beyond.

REFERENCES

Ajit, G., Lucas, T., & Kanyan, R. (2022). Design and Technology in Malaysian Secondary Schools:
A Perspective on Challenges. Malaysian Journal of Social Sciences and Humanities, 7(1), 335–351.
doi:10.47405/mjssh.v7i1.1219
Ajzen, I. (1991). The theory of planned behavior. Organizational Behavior and Human Decision Pro-
cesses, 50(2), 179–211. doi:10.1016/0749-5978(91)90020-T

165

What Are Students Saying About AI as an Academic Tool

Bilquise, G., & Shaalan, K. (2022). AI-based Academic Advising Framework: A Knowledge Management
Perspective. International Journal of Advanced Computer Science and Applications, 13(8), 193–203.
doi:10.14569/IJACSA.2022.0130823
Birdsell, B. (2022). Student Writings with DeepL: Teacher Evaluations and Implications for Teaching.
JALT Postconference Publication, 2021(1), 117. doi:10.37546/JALTPCP2021-14
Braun, V., Clarke, V., Boulton, E., Davey, L., & McEvoy, C. (2020). The online survey as a qualitative
research tool. International Journal of Social Research Methodology, 00(00), 1–14. doi:10.1080/1364
5579.2020.1805550
Burkhard, M. (2022). Student Perceptions of Ai-Powered Writing Tools: Towards Individualized Teaching
Strategies. Proceedings of the 19th International Conference on Cognition and Exploratory Learning in
the Digital Age, CELDA 2022, Celda, 73–81. 10.33965/CELDA2022_202207L010
Carvalho, L., Martinez-maldonado, R., Tsai, Y., & Markauskaite, L. (2022). Computers and Education :
Artificial Intelligence How can we design for learning in an AI world ? Computers and Education:
Artificial Intelligence, 3(July), 100053. doi:10.1016/j.caeai.2022.100053
Chen, X., Xie, H., & Hwang, G. J. (2020). A multi-perspective study on Artificial Intelligence in Educa-
tion: Grants, conferences, journals, software tools, institutions, and researchers. Computers and Educa-
tion: Artificial Intelligence, 1(October), 100005. doi:10.1016/j.caeai.2020.100005
Choi, Y., & Suh, K. H. (2022). Verifying the usefulness of the theory of planned behavior model for
predicting illegal use of online content: The role of outcome expectancies and social loafing. BMC
Psychology, 10(1), 1–12. doi:10.1186/s40359-022-00978-3 PMID:36371253
Esplugas, M. (2023). The use of artificial intelligence (AI) to enhance academic communica-
tion, education and research: A balanced approach. The Journal of Hand Surgery, 48(8), 819–822.
doi:10.1177/17531934231185746 PMID:37417005
Gado, S., Kempen, R., Lingelbach, K., & Bipp, T. (2022). Artificial intelligence in Psychology: How
can we enable psychology students to accept and use artificial intelligence? Psychology Learning &
Teaching, 21(1), 37–56. doi:10.1177/14757257211037149
Haleem, A., Javaid, M., & Pratap, R. (2023). BenchCouncil Transactions on Benchmarks, Standards and
Evaluations An era of ChatGPT as a significant futuristic support tool : A study on features, abilities,
and challenges. BenchCouncil Transactions on Benchmarks. Standards and Evaluations, 2(4), 100089.
doi:10.1016/j.tbench.2023.100089
Lakkala, M., Toom, A., Kangasharju, A., & Ilom, L. (2022). Computers and Education : Artificial In-
telligence Lower secondary students ’ poetry writing with the AI-based Poetry Machine. doi:10.1016/j.
caeai.2022.100048
Lim, W. M., Gunasekara, A., Pallant, J. L., Pallant, J. I., & Pechenkina, E. (2023). Generative AI and
the future of education: Ragnarök or reformation? A paradoxical perspective from management educa-
tors. International Journal of Management Education, 21(2), 100790. doi:10.1016/j.ijme.2023.100790

166

What Are Students Saying About AI as an Academic Tool

Mackenzie, D. (2023). Surprising Advances in Generative Artificial Intelligence Prompt Amazement

— And Worries. Engineering (Beijing), xxxx, 4–6. doi:10.1016/j.eng.2023.04.004
Maria, G., Sousa, B. De, Cardoso, L., & Toassi, P. (2018). Duolingo As a Tool to Improve Vocabulary
Writing in English as a No Inglês Como Língua Estrangeira. Academic Press.
Niepel, C., Burrus, J., Greiff, S., Lipnevich, A. A., Brenneman, M. W., & Roberts, R. D. (2018). Stu-
dents’ beliefs and attitudes toward mathematics across time: A longitudinal examination of the theory of
planned behavior. Learning and Individual Differences, 63(June), 24–33. doi:10.1016/j.lindif.2018.02.010
Prasad, B. N., & Jaheer, B. (2023). The Use of AI (artificial Intelligence) in English Learning Among
Engineering Students: A Case Study. International Journal of English Learning & Teaching Skills, 5(4),
3500–3508. doi:10.15864/ijelts.5410
Puspitasari, E., & Tsara, E. (2022). Learning Tools for EFL Writing: What and How based on Upper
Secondary School Students’ Perspectives. VELES: Voices of English Language Education Society, 6(2),
488–499. doi:10.29408/veles.v6i2.5878
Ramirez-Anormaliza, R., Sabaté, F., & Guevara-Viejo, F. (2015). Evaluating Student Acceptance Level
of E-Learning Systems. 8th Annual International Conference of Education, Research and Innovation,
2393–2399. https://library.iated.org/view/RAMIREZANORMALIZA2015EVA
Ray, P. P. (2023). ChatGPT: A comprehensive review on background, applications, key challenges, bias,
ethics, limitations and future scope. Internet of Things and Cyber-Physical Systems, 3(March), 121–154.
doi:10.1016/j.iotcps.2023.04.003
Reiss, M. J. (2021). The use of AI in education: Practicalities and ethical considerations. London Review
of Education, 19(1). doi:10.14324/LRE.19.1.05
Soomro, S. A., Kazemian, B., & Mahar, I. H. (2015). The Importance of Culture in Second and Foreign
Language Learning. SSRN Electronic Journal, 15(1), 1–10. doi:10.2139/ssrn.2656713
Su, J., Tsz, D., Ng, K., Kai, S., & Chu, W. (2023). Computers and Education : Artificial Intelligence
Artificial Intelligence (AI) Literacy in Early Childhood Education : The Challenges and Opportunities.
Computers and Education: Artificial Intelligence, 4(January), 100124. doi:10.1016/j.caeai.2023.100124
Tuomi, I. (2018). The Impact of Artificial Intelligence on Learning, Teaching, and Education Policies.
Science for Policy. doi:10.2760/12297

KEY TERMS AND DEFINITIONS

21st Century Education: 21st-century education is an adaptive, technology-driven approach (Turi-

man et al., 2012). In this chapter, this term mainly refers to the adoption of digital literacy into English
language-based courses that prepares students for an ever-evolving global landscape.
Academic Integrity: Academic integrity refers to the ethical foundation of honesty, responsibility,
and trustworthiness in scholarly pursuits (Lim et al., 2023). In this chapter, this term is referred to the

167

What Are Students Saying About AI as an Academic Tool

values of originality, proper citation, and the avoidance of plagiarism or cheating in classroom activities
and assignments.
Artificial Intelligence (AI): Artificial intelligence in education refers to the utilization of technology
and algorithms to enhance and personalize learning experiences (Haleem et al., 2023). In this chapter,
AI is explored from the angles of content creation, student assessment, and personalized tutoring.
Attitude: Attitude in this chapter refers to the disposition, mindset, and emotional stance a student
holds towards their learning process, encompassing their beliefs, motivations, perseverance, and recep-
tiveness towards existing and new knowledge (Gu & Wu, 2019).
Behavior: Behavior refers to the actions, conduct, and responses exhibited by an individual or a
group in various situations (Boguszewicz-Kreft et al., 2020). In this chapter, this term encompasses how
students engage, participate, and react within the learning environment.
Language Education: Language education involves the structured teaching and learning of a lan-
guage, encompassing its grammar, vocabulary, pronunciation, and cultural context (Kazakov, 2021).
In this chapter, language education specifically refers to language courses that are taught in English,
focusing on reading, writing, listening, speaking skills and grammar acquisition.
Machine Learning: In the context of language education, machine learning refers to the application
of artificial intelligence techniques and algorithms to enhance language learning experiences (Godwin-
Jones, 2022). This chapter briefly visits the development of systems that optimize and customize the
language learning process for students.
Perception: Perception encompasses the way students receive, process, and understand knowledge,
influenced by their prior experiences, beliefs, attitudes, and cognitive abilities (Chai et al., 2023). In this
chapter, this term refers to how students engage with AI-powered tools to construct their understanding
of academic content.
Plagiarism: Plagiarism is the act of using someone else’s ideas, words, or work without proper ac-
knowledgment or attribution, presenting them as one’s own (Khan, 2016). In this chapter, this term is
referred to students’ actions of copying or closely imitating content from AI-powered sources.

168
What Are Students Saying About AI as an Academic Tool

APPENDIX: CASE SUPPORT MATERIALS

Questions and Answers

1. What is the overall problem presented in this case?

The overarching problem presented in this case is the lack of understanding and exploration regard-
ing how learners intend to use AI in their academic tasks, particularly in the context of language
education.

2. How does this case help to address the gap in the problem presented?
The study aims to address this gap by investigating how students’ intentions to use AI impact their
language learning behaviour and by identifying the factors influencing their perceptions of AI’s
usefulness as an academic support tool. This lack of exploration in the current literature hinders
the optimization of AI integration in language education and may limit its effective utilization in
enhancing academic tasks for students.

3. What are the factors affecting the problem(s) related to this case?
The factors are: perceived usefulness of AI, ease of use, social influence, attitudes towards AI and
subjective norms. These factors collectively influence students’ intentions and perceptions regard-
ing the utilization of AI in language education, ultimately impacting their adoption and integration
of these technologies into their academic pursuits.

4. Discuss managerial, organizational, and technological issues and resources related to this case.
Managerial issues addressed are: Effective guidance on AI integration, training for educators, and
policies ensuring responsible AI use. Next, the main organizational issue addressed is, establishing
support structures for students. Finally, in terms of technological issues, infrastructure for seamless
integration, and continuous technological advancements for educational purposes are explored.

5. What is the final solution that can be recommended to the management of the organization described
in the case? Provide your arguments in support of the recommended solution.
It is suggested for relevant education stakeholders to offer educator training, ensure accessible AI
tools, and develop guidelines for responsible AI use. This holistic approach fosters responsible
adoption, empowers educators, and optimizes AI’s academic benefits, enhancing student learning
experiences and outcomes in language education.

Epilogue and Lessons Learned

Tailoring learning experiences to individual students’ interests, abilities, knowledge levels, and talents
fosters greater engagement, thereby enhancing motivation and success while also amplifying their voices
and choices. This makes personalized learning a prominent trend in education. Thanks to artificial
intelligence, students now could benefit from customized learning process that align with their unique
experiences and preferences. Additionally, individuals can receive enhanced support through personalized
AI-based recommendations, surpassing the attention teachers can provide. The personalized integration

169
What Are Students Saying About AI as an Academic Tool

of AI stands also out as a major milestone in education, making learning more seamless, comfortable,
and adaptable to individual knowledge levels.
From this case study, we, the researchers have developed a better understanding of what AI is and
what roles it plays in the Malaysian teaching and learning context. Hereby, this section is presented to
encapsulate the key insights garnered from this study, offering a concise overview of the lessons learned
and their implications for the field of AI in language education, particularly within the Malaysian context.

Lesson 1: Students’ Conservative Use of AI Tools

Contrary to prevalent assumptions, our study uncovered a surprising trend: students demonstrated a
judicious approach towards AI integration in their academic endeavours. Despite initial concerns among
educators regarding potential overreliance, the reality reflected a cautious and selective utilization of AI-
powered tools. Students appeared to harness these resources as supplementary aids rather than primary
solutions, showcasing a balanced integration into their academic workflow. This unexpected revelation
challenges conventional presumptions, highlighting the need for a nuanced understanding of students’
actual usage patterns and the dynamic roles AI plays in their learning journey.

Lesson 2: Collaborative Development for Targeted AI Solutions

The study underscored the necessity for interdisciplinary collaboration between AI developers and
social science researchers. Bridging these domains becomes imperative to tailor AI tools effectively
for educational contexts. Our findings emphasized that developers must engage with insights from
social sciences, incorporating pedagogical theories and methodologies into the design and refinement
of AI-based educational tools. This synergy holds the potential to yield more targeted, impactful, and
contextually relevant solutions, aligning technological advancements with the intricate nuances of learn-
ing and teaching processes.

Lesson 3: Strengthening Expertise and Global Competitiveness

The study illuminated an area demanding greater attention within the Malaysian academic landscape: the
cultivation of expertise in AI integration for educational purposes. Recognizing the pivotal role AI plays
in shaping the future of education, there arises an urgency to bolster local expertise. Building a robust
knowledge base and skill set within this domain not only enriches the quality of educational practices but
also positions Malaysian researchers competitively on the global stage. This imperative emphasizes the
significance of investing in specialized training, research initiatives, and collaborative efforts to fortify
Malaysia’s standing in the rapidly evolving landscape of AI-driven education.
While we are excited to further explore this topic using various other theories, we also hope that more
researchers from around the world can work with AI-developers to personalize teaching and learning
for the 21st century. We are looking forward to the interesting developments that AI could bring to the
education landscape in 2024 and beyond!

170
What Are Students Saying About AI as an Academic Tool

List of Additional Sources

Ministry of Science, T. & I. (MOSTI). (2021). Malaysia National Artificial Intelligence Roadmap 2021-
2025 (Ai-Rmap). https://airmap.my/apps
Dewan Rakyat Malaysia. (2019). Penyata Rasmi Parlimen: Kamar Khas Parlimen ke-14, penggal
ke-2, mesyuarat ke-2. 8. https://www.parlimen.gov.my/files/hindex/pdf/KKDR-15072019.p
df

171
Section 3
Practice:
Use of AI in Language Education
173

Chapter 9
Integrating ChatGPT Into
a Culture-Focused Flipped
Curriculum for Chinese
as a Foreign Language:
Experiments and Implications

Jianfen Wang
https://orcid.org/0000-0003-0890-5253
Berea College, USA

ABSTRACT
This chapter explores ChatGPT’s potential for assisting in a culture-focused flipped curriculum to fa-
cilitate the development of intercultural communicative competence, a core value of foreign language
education in the 21st century. Three experiments assess ChatGPT’s performance in generating scenarios
and performance scripts for practicing intercultural communication in Chinese-speaking contexts. While
ChatGPT demonstrates remarkable linguistic accuracy and comprehension abilities, it struggles to
generate scripts that reflect communicative strategies specific to Chinese-speaking contexts, especially
when the prompt lacks explicit instructions about Chinese cultural expectations. The limitation can be
rooted in ChatGPT’s training and the user’s ineffective prompting. The findings suggest that ChatGPT
is better suited as a reference tool than a primary learning resource in the curriculum. The implications
for foreign language education and the integration of AI are also discussed.

A core value of foreign language education in the 21st century is the development of intercultural com-
municative competence (ICC), the ability to interact effectively and appropriately with people from other
linguistic and cultural backgrounds (American Council on the Teaching of Foreign Languages [ACTFL],
2017). Compared with “communicative competence,” ICC adds an emphasis on the ability to take up
the perspectives of the listener or reader in intercultural communication (Byram, 2020). This emphasis
necessitates a more effective integration of language and culture in foreign language instruction. To
DOI: 10.4018/979-8-3693-0872-1.ch009

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

meet this challenge, proponents of the Performed Culture Approach (PCA) (Walker, 2010; Wang &Jia,
2023; Yu, 2021) propose a shift to a culture-focused framework characterized by performance-based
instruction and assessment. For example, by enacting various scenarios that simulate interactions be-
tween individuals of different social hierarchies in Chinese-speaking contexts and receiving feedback
from a Chinese perspective, students develop a concrete understanding of how hierarchy plays out in
Chinese-speaking contexts while developing proficiency in the language. Such experiential knowledge
is more easily registered and more readily accessible than what is gleaned merely from cultural notes. It
equips students with the flexibility to effectively navigate similar situations, whether in life or in reading.
In lower-level foreign language courses, the development of ICC can be greatly facilitated by a
culture-focused flipped curriculum, which dedicates classroom instruction to enactments of intercultural
scenarios. Effective implementation of the curriculum requires students to teach themselves the language
before class and demonstrate their knowledge in class to receive feedback. The instructor’s preparation
for class centers on creating a range of meaningful scenarios that enhance cultural understanding while
facilitating language practice. Both the students and the instructor may benefit greatly from the assistance
of ChatGPT, a remarkable achievement in the realm of artificial intelligence (AI). Equipped with a trans-
former architecture and trained on extensive datasets, ChatGPT has demonstrated excellence in swiftly
generating realistic texts of various forms and providing detailed responses to factual and conceptual
queries (Hong, 2023; Kasneci et al., 2023). This chapter explores ChatGPT’s potential for assisting in
a culture-focused flipped curriculum.
In the forthcoming sections, I first offer a brief description of the culture-focused flipped curriculum,
highlighting how it may incorporate ChatGPT while upholding academic integrity and depth of learn-
ing. I then review current discussions among educators about ChatGPT’s capabilities and limitations
for language education. Furthermore, I report findings from three experiments that I conducted with
ChatGPT3.5, assessing its performance in one of the most demanding lesson-planning tasks faced by
human instructors implementing the culture-focused flipped curriculum, namely, generating a variety of
context-specific performance scripts for practicing intercultural communication. The chapter concludes
with implications for language educators aspiring to harness ChatGPT’s potential to enhance the ef-
fectiveness of language education for cultivating ICC.

THE CULTURE-FOCUSED FLIPPED CURRICULUM

The culture-focused flipped curriculum is an application of the Performed Culture Approach (PCA)
(Walker, 2010), specially developed to help learners participate effectively in cultures that are funda-
mentally different from their own. PCA, informed by sociocultural theories and recent developments in
cognitive science, pioneers a culture-focused framework, where the goal of foreign language education
is to enable learners to function effectively in the target culture (Wang & Jia, 2023). It emphasizes the
learning of behavioral culture in all levels of language classes for long-term benefits. Behavioral culture is
the tacit knowledge of effective (re)actions in specific contexts. It is embodied in the dynamic processes
that frame the behavior of its members and give them the means to recognize the behaviors of their own
and others in specific contexts (Walker, 2021). The emphasis on behavioral culture is achieved by using
performance as a unifying framework for language and culture.
Performance, in this context, refers to a situated communicative event specified by five basic elements
of human behavior, namely time, place, roles, audience, and script (Noda, 2007; Walker, 2010; Walker

174

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

& Noda, 2010). The script, specifying both verbal and nonverbal communicative behavior, is always
specific to the sociocultural context. Therefore, in the culture-focused curriculum, learners’ language use
is evaluated primarily for effectiveness and appropriateness within the specific target-culture context,
rather than solely for linguistic accuracy and fluency. For example, a student’s creative use of “Wŏ xǐhuan
nǐde màozi (I like your hat)” to compliment a Chinese friend’s new hat will be corrected because, in a
Chinese-speaking context, such a comment is often interpreted as an implication of wanting the hat. As
part of the correction, the instructor would typically model appropriate compliments, such as, “Nǐde
màozi hěn hǎokàn (Your hat looks nice)” or “Màozi hěn shihe nǐ (The hat fits you well).”
By consistently emphasizing performance as the basic unit of instruction and assessment, the curriculum
allows students to study language and culture as an integrated whole. It does not only respect the holistic
nature of human behavior (Pike, 1967) but also emphasizes effective and appropriate interaction with
people from other cultural backgrounds – the essence of ICC. Enacting intercultural scenarios in class
allows students to expose their misconceptions about the target culture and receive immediate feedback,
facilitating the learning of target-culture perspectives. Furthermore, practicing the language in realistic
intercultural scenarios helps students develop visions of their Chinese-speaking selves, a crucial factor in
maintaining long-term motivation to learn the language (Dörnyei & Ushioda, 2009; Wang & Jia, 2023).
The flipped aspect of the curriculum promotes autonomous learning and a sense of ownership in the
achievements. It requires students to study substantially before class and be ready to enact simulated real-
life scenarios in class. Classroom instruction is dedicated to rehearsing sociocultural scenarios, offering
students ample opportunities to experiment with language usage in target-culture contexts. In the scenarios,
the teacher plays various roles of Chinese speakers, providing feedback primarily as an interlocutor and
offering explicit correction or modeling when needed. The flipped curriculum combines self-directed
independent learning with in-class experiential learning. Such hybrid learning environments align well
with the preferences of Gen-Z learners, who value personalized and on-demand experiences and benefit
from opportunities for independent learning before joining other learners (Seemiller & Grace, 2019).
Moreover, with ChatGPT being “a free and more efficient alternative to human tutors” (Hong, 2023,
p.40), flipped classrooms emerge as a natural direction for educational innovation, taking full advantage
of ChatGPT for pre-class learning and allowing more hands-on collaborative activities during class.
The curriculum, respecting language’s nature as being “primarily oral” (Hammerley, 1986, p.34),
uses conversation as a primary assessment tool. Here, the term “conversation” broadly refers to any spon-
taneous interaction involving two or more participants collaborating toward a shared goal in a specific
context, with or without the assistance of external media (such as a writing system) (Wang, 2016). A
conversation may be as simple and brief as mutual nods to acknowledge one another in the elevator, or
as sophisticated and extensive as discussing a novel to gain a deeper understanding of the themes. The
essence lies in an awareness of and genuine respect for the perspectives of the other participant(s) in the
specific context. Since both the pronunciation and the writing system of the Chinese language are highly
challenging for learners, the beginning-level curriculum distinguishes speaking-focused and reading-
focused classes to focus on one challenge at a time without breaking the unity of language and culture.
The two types of classes use different prompting strategies to elicit conversations. The prompts in
speaking-focused classes only assume aural-oral knowledge of the assigned script, whereas those in the
subsequent reading-focused classes will require knowledge of the assigned character text. For example,
if a speaking-focused class engages students in performing various scenarios involving discussions
about one’s schedule for an appointment. One activity in the subsequent reading-focused class may put
students in a scenario where they receive an email about the cancellation of an appointment and need to

175

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

relay it to another person who is also impacted by the cancellation. Their comprehension of the email
is demonstrated by the simulated conversation. Since the roles of the email sender, the reader (i.e., the
student), and the other person (acted either by the teacher or another student) are specified, the way the
students talk during the conversation reflects their sociocultural knowledge.
In this curriculum, students are required to demonstrate their learning in person, so they must per-
sonalize and internalize the content. However, they may employ ChatGPT as an accessible and versatile
learning companion during self-directed learning. At the beginning level, where pre-class learning
involves mostly basic and physical tasks, such as repeating aloud after audio samples and manually
tracing characters, students may only occasionally turn to ChatGPT to satisfy their curiosity about the
language and the culture. However, as they progress, their pre-class learning tasks will gradually align
with what the teacher does for lower-level learners, such as brainstorming intercultural scenarios and
creating conversation or narrative scripts for class performance. ChatGPT’s assistance in these tasks will
benefit both the learners and the teacher, further enhancing the curriculum’s effectiveness.

CHATGPT AS A TOOL FOR LANGUAGE TEACHING AND LEARNING: A REVIEW

Numerous educators have explored ChatGPT’s capabilities and limitations for language teaching and
learning. Some share their speculations about ChatGPT’s potential for language education based on
its advanced technology (e.g., Baskara & Mukarto, 2023; Hong, 2023), while others test the tool with
concrete language learning tasks (e.g., Kohnke, Moorhouse &Zou, 2023). They generally acknowledge
ChatGPT’s potential as an efficient tool for language teaching and learning, albeit with a notable need
for human oversight to counter biases and inaccuracies. This section focuses on reviewing ChatGPT’s
performance in language-learning tasks reported in the existing literature to understand the tool’s po-
tential for serving in the culture-focused curriculum.
Most of the experiments with ChatGPT have focused on how language learners may use it. Their
results confirm the tool’s versatile capabilities while revealing its inconsistent performance. For instance,
Pasden (2023) demonstrates ChatGPT’s capability of performing a variety of Chinese language learning
tasks, including translating between English and Chinese, providing vocabulary lists, generating Chinese
texts, and responding to chat prompts in Chinese, but it tends to make factual errors. For example, when
asked about the Chinese novelist Ba Jin’s most famous work, ChatGPT initially mistakenly presented
the novel’s name as “The Family (Jiājiào, 家教)” while the Chinese title should actually be “Jiā, 家.”
ChatGPT self-corrects the mistake when asked, “Are you sure that’s the correct Chinese name of Ba
Jin’s novel ‘Family’?” The self-correction is unusual because, in Wang’s (2023a) experiment, where
ChatGPT wrongly states that the verb occurs before the 把ba particle, a similar rhetorical question fails
to trigger a self-correction. When asked, “Are you sure that in a 把 sentence, the verb is placed before the
把 particle?” ChatGPT ignores the implication and continues to assert that “the verbs indeed precede the
把 particle (italics added).” Such factual errors, especially when presented with a self-asserted tone, can
be confusing and misleading for learners who are not proficient enough in the target language to discern
the errors. Therefore, learners would be running a risk if they relied on ChatGPT to gain new knowledge.
Some educators have explored ways that ChatGPT can assist language teachers, using tasks typi-
cally associated with language-focused approaches (Buchanan-Shrader, 2023; Kohnke, Moorhouse &
Zou, 2023). For example, Kohnke, Moorhouse, and Zou (2023) demonstrate how ChatGPT can sup-
port English language teachers in various capacities, such as explaining difficult terms and providing

176

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

sample sentences, generating texts of various genres (e.g., dialogs, emails, stories) relating to a single
topic, rewriting a text in another language, adjusting the complexity of the dialog, preparing vocabulary
notes, and generating comprehension or expansion questions to accompany reading tasks. However, the
authors’ evaluation of ChatGPT’s performance focuses on linguistic and factual accuracy, neglecting
sociocultural appropriateness. They point out the wordiness and inaccuracies in ChatGPT’s explanations
of grammatical errors but not its poor context-awareness in the dialog creation task.
In the dialog creation task, Kohnke, Moorhouse, and Zou (2023) instruct ChatGPT to “write a dia-
log between Amy and Jane about rising electricity prices.” Despite not knowing who Amy and Jane
are, ChatGPT immediately produces a dialog script instead of requesting more information about the
context. While the script is content-rich and linguistically accurate, it suffers from lengthy and overly
formal sentences that do not sound conversational. The longest line in the script starts with a complex
preposition phrase (“with the hot weather coming up”) and ends with a subordinate clause (“which will
probably drive the bill even higher”). When further prompted to adjust the complexity for beginner or
advanced learners, ChatGPT maintains the length of the initial version and the complex sentences, merely
replacing words or phrases. This results in dialog versions that, despite differing in vocabulary, maintain
similar levels of complexity and formality, failing to reflect the intended simplicity for beginners and
the sophistication for advanced learners. In fact, all three versions resemble the decontextualized dialogs
often found in traditional textbooks for English language learners.
The decontextualized dialog script is most likely due to the generic prompt. ChatGPT does not ask
follow-up questions despite its seemingly powerful comprehension and synthesis abilities. What it does
is comparing existing data “to draw the most likely (e.g., the most frequent and relevant) responses”
(Hong, 2023, p.28), functioning more like a smart search tool. According to prompt-engineering guides,
the precision of ChatGPT’s responses can be significantly enhanced by being specific, descriptive, and
detailed about the context, expected outcome, length, format, style, or providing examples (Mittal, 2023;
Schulhoff, Khan & Yanni, 2023). Therefore, prompts that specify the sociocultural context are more likely
to yield realistic conversation scripts, and this is evident in Zeng’s (2023) experiment, which instructed
ChatGPT to generate conversation scripts for an elevator scenario in a Chinese-speaking context.
In Zeng’s (2023) experiment, the prompt provides a detailed scenario description in English, specify-
ing the roles (i.e., a new employee comes across the company’s HR manager Mr. Zhang whom she met
during the job interview), the place and time of the interaction (i.e., in the elevator on the new employee’s
first day of work) and the new employee’s intention (i.e., to take the opportunity to thank the HR manager
for the interview). ChatGPT’s immediate response appropriately addresses the social context, providing
a seven-line exchange in Chinese suitable for an elevator conversation. Throughout the script, the new
employee sounds polite and grateful while the manager sounds friendly and encouraging. Although some
of the expressions bear traces of English influence, the overall script serves as a decent starting point
for thoughtful language learners and teachers.
ChatGPT’s impressive performance in Zeng’s (2023) experiment is a result of effective prompting
and can be expected even when instructions are provided in Chinese, showcasing its excellent compre-
hension ability in Chinese. Figure 1 is a screenshot of Wang’s (2023b) interaction with ChatGPT, where
ChatGPT responds to a prompt provided in Chinese. The prompt translates as follows:
Please create a dialog script for beginner learners based on the following description: It’s a little
after eight in the evening. An American student and his friend have finished dinner at a restaurant near
campus. They walk out of the restaurant and are about to leave.

177

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

Figure 1. Conversation script generated by ChatGPT

The script ChatGPT generates in response is highly usable. Although the first four lines carry a subtle
hint of English influence, the last four lines sound surprisingly natural for a parting scene in Chinese:
one person announces his departure and bids goodbye, the other person echoes it and reminds him to stay
safe on the way, the first speaker bids goodbye again using a different phrase, and the second speaker
echoes it. The script serves as a reminder that real-life partings between friends involve a more elaborate
and varied exchange than the simplistic phrase “Zàijiàn (See you again)” commonly found in textbooks.
Zeng’s (2023) and Wang’s (2023b) experiments demonstrate ChatGPT’s ability to consider social
contexts and create realistic scripts when prompted effectively. Integrating such realistic scripts into the
curriculum can allow students to see a more diverse range of performance scripts. However, the tasks
that Zeng and Wang use do not require strategies specific to Chinese-speaking contexts, so ChatGPT’s
performance on these tasks may not reflect its grasp of cultural nuances. Moreover, these tasks only require
ChatGPT to generate scripts for predefined scenarios, whereas generating intercultural scenarios is a more
demanding part of developing and implementing a culture-focused curriculum. Therefore, ChatGPT’s
potential for culture-focused curriculums remains to be assessed through more culture-focused tasks.

ASSESSING CHATGPT’S INTERCULTURAL SKILLS: THREE EXPERIMENTS

In communication, a shared understanding of the cultural context is primary because more information
comes from the cultural context than the linguistic codes, whose meaning is subject to the users’ inter-
pretation of the context. When the users are from different cultural backgrounds, a shared understanding
of the context may not always be assumed. For instance, in Chinese culture, it is perfectly acceptable to
decline an offer with a simple “Bú yòng (No need)” without saying “Xièxie (Thanks),” but in an Eng-
lish context, such brevity is often perceived as rude. Similarly, responding to an offer with “I’m fine”
in English can be confusing for a Chinese speaker as it does not clearly indicate acceptance or refusal.

178

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

Miscommunications are common in intercultural scenarios but often remain unnoticed until relation-
ships between parties begin to deteriorate. Therefore, a culture-focused curriculum strives to acquaint
students with situations and expected reactions specific to the target culture and help them practice useful
scripts to improve effectiveness when communicating with people from the target culture. The range of
intercultural scenarios an individual instructor can conceive is inherently constrained by their experi-
ence. Here, ChatGPT’s extensive knowledge base and remarkable search capabilities offer a potential
solution. In this section, I detail three experiments that I conducted with ChatGPT3.5 in the summer
of 2023 to explore the free AI tool’s capability of brainstorming intercultural scenarios and generating
performance scripts for practicing intercultural strategies in Chinese-speaking contexts.
Each experiment employs a different prompting strategy inspired by PCA’s model of cultural knowledge
compilation. In this model, personal memories of performances constitute categories of “cases” (memories
related to tasks and functions), “sagas” (memories related to specific people or places), and “themes”
(memories related to a culture-specific concept that underlies a wide range of behaviors) (Noda, 2007;
Walker & Noda, 2000). These categories are interconnected. For example, performances about meeting
new friends at parties and those about meeting potential business partners at professional conferences may
all fall into a “first encounter” case or an “introduction” case, while the former will be part of a “friend”
or a “party” saga and the latter a “business partner” or a “professional conference” saga. Depending on
how the performances unfold, they may relate to other memories by the “face-saving” or “hierarchy”
theme. Each of the three categories serves as the objective for the scenario-brainstorming tasks.
While a culture-focused curriculum encompasses various types of performances, the experiments will
focus on generating conversational scripts because performing conversations is the most fundamental
and productive for learners’ literacy development (Keating & Egbert, 2004; Schieffelin & Ochs, 1986;
Wang, 2016). Conversations engage the learner’s entire body and allow them to gain concrete experiences
of the target culture. Personal stories accumulated from the conversational performances will facilitate
comprehension and performance of narrative texts, which constitute most of the higher-level courses.
The ChatGPT-generated scenarios and scripts are analyzed for linguistic accuracy and suitability for
teaching intercultural strategies in Chinese-speaking contexts.

Experiment 1. Creating Materials for Teaching the Case of Complimenting

The first experiment tests ChatGPT’s ability to brainstorm scenarios and scripts that illustrate how
cultural differences influence expected reactions in specific situations. I use the case of complimenting
in the United States versus in China as an example. Table 1 shows the interaction. While the response
contains mostly relevant information free of linguistic errors, its explanations about the differences in
each situation tend to be overly general, and some are ambiguous or even nonsensical. For instance, Situ-
ation 8 suggests that one should avoid sounding insincere or overly familiar when giving compliments
to elders; however, this advice, especially the sounding overly familiar part, will not apply if the elders
are family members. Situation 4 states that the Chinese might offer small gifts in return for compli-
ments but does not mention the types of compliments that may prompt such a reaction. Situations 2 and
5 contain incorrect statements, which I have marked with strikethroughs. These statements mistakenly
attribute the Chinese indirectness in expressing compliments to the cultural value of modesty, whereas
in fact, openly praising individual achievements, while less common than in the United States, is not
considered immodest in China.

179

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

Table 1. Interaction with ChatGPT about compliments (Part 1)

Can you brainstorm situations where cultural context might lead to different reactions to compliments in the USA versus
Prompt:
in China?
Certainly! Cultural context can indeed lead to different reactions to compliments in the USA and China. Here are some
situations where compliments might be perceived differently due to cultural nuances:
1. Accepting Compliments: USA: In the USA, it’s generally expected that individuals accept compliments graciously
with a simple “Thank you” or a positive acknowledgment of the compliment. China: In China, it’s common for
individuals to downplay compliments to demonstrate humility and modesty. A response might involve a polite refusal or a
self-effacing comment.
2. Personal Achievements: USA: Praising individual achievements, even in public settings, is common and encouraged.
It’s a way to acknowledge personal success and hard work. China: Praising individual achievements too openly might be
seen as immodest. In China, a more collective-oriented approach might involve attributing success to the support of others
or the circumstances.
3. Appearance Compliments: USA: Complimenting someone’s appearance, clothing, or hairstyle is often seen as a
friendly gesture in the USA. China: Compliments about personal appearance might be received with more reserve in
China, as humility and not drawing attention to oneself are valued.
4. Gift-Giving and Reciprocation: USA: In the USA, receiving compliments might be met with a smile or a thank you.
Gift-giving might not always be a direct response to compliments. China: In China, receiving compliments might prompt
ChatGPT: the individual to offer a small gift or token of appreciation in return, as a way to show gratitude and maintain harmony.
5. Compliments in Professional Settings: USA: In professional settings in the USA, compliments about someone’s
work, presentation, or accomplishments are encouraged as a form of recognition. China: In professional settings in China,
compliments might be more reserved and expressed indirectly to maintain a level of modesty and not appear boastful.
6. Compliments in Social Gatherings: USA: Compliments about the event, food, or arrangements at a social gathering
are common in the USA and contribute to the overall positive atmosphere. China: In China, compliments about the host’s
efforts might be expected, but they might be given more subtly, as openly expressing praise could be seen as excessive.
7. Cultural Differences in Language and Expressions: USA: Expressing compliments using direct and positive
language is typical in the USA. China: In China, expressions might be more indirect and nuanced, involving the use of
comparative phrases or metaphors to convey compliments.
8. Giving Compliments to Elders: USA: Complimenting elders is generally well-received and a sign of respect in the
USA. China: In China, while showing respect to elders is crucial, compliments might be offered more cautiously to avoid
sounding insincere or overly familiar.
These examples illustrate how cultural differences can lead to variations in the reception and expression of compliments
in the USA and China. Understanding these differences can help foster effective communication and relationships in
cross-cultural interactions.

Imperfection aside, the response provides useful information and serves as a strong starting point for
exploring the cultural differences associated with the case of complimenting. Firstly, the response aptly
captures the Chinese tendency toward reservation and indirect expressions when giving compliments. It
also highlights how they tend to downgrade or attribute success to collective efforts when responding to
compliments. Secondly, the explanations show how the acts of expressing and responding to compliments
align with the cultural values of modesty, sincerity, and social harmony. ChatGPT also makes useful
connections to other cases where the cultural context may significantly influence expected reactions.
For example, Situation 4 connects complimenting with the case of gift-giving. Situation 8 suggests that
respect for elders is expressed in different ways in China than in the USA. These connections inspire
the user to brainstorm additional intercultural scenarios.
Among the situations provided by ChatGPT, the sixth one, labeled as “Compliments in Social Gath-
ering,” potentially encompasses a variety of role relationships and occasions. To delve deeper into this,
I instruct ChatGPT to provide scripts that illustrate the cultural differences in social gatherings. Table 2
shows this interaction. ChatGPT uses the scenario of a guest complimenting the host’s cooking at a din-
ner party as an example and provides a two-line exchange for this scenario in both the United States and
China. While the guest’s message remains the same in both languages, the hosts’ responses appropriately
differ. In the Chinese context, the host modestly downplays their cooking skills by saying, “只是一些

180

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

家常小菜而已zhīshì yìxiē jiācháng xiǎocài éryǐ (These are just some simple home-cooking),” but such
modesty is not featured in the American context. In the subsequent comment, ChatGPT attributes this
difference to the value of humility in Chinese culture, which is insightful.

Table 2. Interaction with ChatGPT about compliments (Part 2)

Can you provide scripts to illustrate how different reactions to compliments in social gathering might play out in
Prompt
conversations in the USA and in China?
Certainly! Let’s explore how different reactions to compliments in the context of social gatherings might play out in
conversations in both the USA and China.
Situation: Compliments in Social Gatherings
USA:
Context: A guest compliments the host’s cooking at a dinner party.
Guest: “The food is absolutely delicious! You’re an amazing cook.” Host: “Thank you so much! I’m glad you’re enjoying
it.”
ChatGPT
China:
Context: A guest compliments the host’s cooking at a dinner party.
Guest: “这些菜真好吃!您的厨艺真厉害。” Host: “谢谢夸奖,只是一些家常小菜而已。”
In the USA, the host responds with appreciation for the compliment. In China, the host responds modestly, attributing the
quality of the food to simple home-cooking skills, in line with the value of humility.
These scripts highlight how cultural norms influence the way compliments are received and acknowledged in the context
of social gatherings. Keep in mind that individual personalities and relationships can also impact these conversations.

ChatGPT thoughtfully concludes the response by emphasizing the impact of individual personalities
and relationships, so my follow-up prompt requests ChatGPT to provide scripts that illustrate how dif-
ferent relationships may impact the conversations. Table 3 shows the interaction. This time, the response
contains three different scenarios, featuring conversations between close friends, acquaintances, and
family members with generational differences. Each scenario is furnished with a two-line exchange,
featuring the same compliment in both cultural contexts but different response strategies, followed by a
brief comment about the differences.
The sample scripts and comments for the first two scenarios are coherent, but those for Scenario 3 are
problematic. The comment marked with a strikethrough in Scenario 3 is nonsensical because the elder
in the Chinese script does not “respond with appreciation” and “the cultural value of showing respect to
elders” does not apply in this context. The scripts for the Chinese context are unnatural because elders do
not typically respond humbly to a younger person’s compliment, although such humility may be expected
if the younger person were an international guest and the elder intended to indicate her pride in Chinese
cuisine. Usually, the elder might simply encourage the younger to eat more or promise to cook the food
again in the future, saying something like “xǐhuan chī jiù duō chī yìdiǎn (If you like it, then eat more)”
or “xiàhuí hái gěi nǐ zuò (I’ll make it for you again).” The unexpected modest response of the Chinese
elder in Scenario 3 may reflect ChatGPT’s tendency to overgeneralize. Nonetheless, ChatGPT rightly
reminds us at the end of the response that “personal dynamics, familiarity, and cultural norms all play
a role in shaping the interactions.” Discerning such nuances, however, requires thorough immersion in
social life, which is beyond ChatGPT’s capacity and will thus rely on human instructors.

181

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

Table 3. Interaction with ChatGPT about compliments (Part 3)

Can you provide scripts to illustrate how different relationships between the speakers may impact reactions to
Prompt
compliments in social gatherings in the USA and in China?
Certainly! The nature of the relationship between speakers can have a significant impact on how compliments are given
and received in social gatherings. Let’s explore how different relationships might influence reactions to compliments in
both the USA and China.
Situation: Compliments in Social Gatherings
Scenario 1: Close Friends
USA:
Context: Close friends at a gathering.
Friend A: “Your new hairstyle looks fantastic!” Friend B: “Thank you! I’m so glad you like it.”
China:
Context: Close friends at a gathering.
Friend A: “你的新发型很棒!” Friend B: “哈哈,谢谢,我觉得还行吧。”
In both cultures, close friends might respond more openly and lightheartedly to compliments, but in the Chinese context,
there might be a bit of playful modesty.
Scenario 2: Acquaintances
USA:
Context: Acquaintances at a gathering.
Acquaintance A: “You have a great sense of humor!” Acquaintance B: “Thank you! That’s really kind of you to say.”
ChatGPT
China:
Context: Acquaintances at a gathering.
Acquaintance A: “你的幽默感真不错!” Acquaintance B: “哪里哪里,其实还好啦。”
In both cultures, acquaintances might respond with gratitude, but in the Chinese context, there might be a touch of
modesty even in the response to a compliment.
Scenario 3: Generational Difference
USA:
Context: A younger person compliments an elder at a family gathering.
Younger Person: “Grandma, you always make the best pies!” Elder: “Thank you, dear. I’m glad you enjoy them.”
China:
Context: A younger person compliments an elder at a family gathering.
Younger Person: “奶奶,您做的派真好吃!” Elder: “哪里哪里,我这点手艺还差得远呢。”
In both cultures, the elder responds with appreciation for the compliment, but in the Chinese context, there might be more
humility expressed due to the cultural value of showing respect to elders.
These scripts demonstrate how different relationships can influence the way compliments are given and received, even
within the same cultural context. Personal dynamics, familiarity, and cultural norms all play a role in shaping these
interactions.

To assess the consistency of ChatGPT’s performance in brainstorming scenarios, I used the prompt “Can
you provide more scenarios?” four times, yielding 12 more scenarios. The first six scenarios are mostly
sensible with feasible scripts and relevant comments. These scenarios feature colleagues at an office party,
siblings at a family gathering, boss and employee at a company celebration, childhood friends at a reunion,
teacher and student at a school event, and in-laws at a family gathering, However, when the prompt is used
the third time, ChatGPT begins to reveal inconsistencies in its work. The Chinese script starts to include
literal translations from English that make little sense in Chinese, such as “你真是有绿手指Nǐ zhēn shì
yǒu lǜ shǒu zhǐ,” which is a literal translation of “You really have a green thumb.” Moreover, the comment
starts to mention differences that are not reflected in the corresponding scripts. Without pointing out the
mistakes, I used the prompt one more time. In the final response, all three scenarios – “Mentors and men-
tees,” “Extended family members,” and “Service providers and customers” – have Chinese scripts that are
equivalents to the English ones and reflect no difference in the complimenting and responding strategies
in the Chinese-speaking context. While the same strategies do apply to both contexts, ChatGPT still states
a fabricated difference in the Chinese context. These irrelevant comments confirm ChatGPT’s tendency
to overgeneralize when prompted to compare cultural differences.

182

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

This experiment shows that ChatGPT can gather useful information about cultural differences,
brainstorm scenarios, and, to some extent, generate feasible performance scripts. However, it tends to
overgeneralize the differences and rely on translating from English scripts. While the overgeneralization
or fabrication of cultural differences may be triggered by the words “different reactions” in the initial
prompt, the reliance on translation is likely innate. ChatGPT is trained on English-language sources, and
its multilingual capability derives from a translation mechanism (Rettberg, 2022). Another observation
from this experiment is that ChatGPT does not always remember the context provided in earlier prompts,
and once its response starts to go off track, it tends to go further off if the mistake is not corrected in
time. Therefore, ChatGPT’s performance is highly dependent on timely, effective feedback.

Experiment 2: Creating Performance Scripts for

Practicing Face-Saving Strategies

The second experiment explores ChatGPT’s ability to generate scenarios that illustrate a value unique to
Chinese culture. I first ask ChatGPT about the Chinese cultural themes or values that a foreign person
needs to be aware of to communicate effectively with Chinese speakers. In response, ChatGPT provides
a list of 15 Chinese cultural themes in bullet points, each accompanied by a brief explanation of why
or how the value should be observed. Figure 2 is a screenshot of the first part of ChatGPT’s response,
showing the first four bullet points.

Figure 2. Screenshot of part of a ChatGPT-generated text

All fifteen themes are pertinent, with accurate explanations and valuable advice. Notably, the concept
of “face” appears twice – first by itself and then in “Face saving,” emphasizing the importance of avoiding
direct refusals or negative responses. Curious about ChatGPT’s practical knowledge in this area, I request
it to create scenarios and performance scripts for beginner learners of the Chinese language to practice

183

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

face-saving strategies in Chinese-speaking contexts. In response, ChatGPT provides five scenarios with
scripts, collected in Table 4. However, the quality of the scenarios is inconsistent.

Table 4. ChatGPT-generated scenarios and scripts illustrating face-saving strategies

Scenario 1: Receiving an Invitation

Context: You’ve been invited to a social event, but you’re not sure if you can attend due to a prior commitment.
Script:
Host (in Chinese): 你能来参加我的生日聚会吗?(Nǐ néng lái cānjiā wǒ de shēngrì jùhuì ma?) - “Can you come to my birthday party?”
You (in Chinese): 嗯,我会尽量安排时间的。(Ēn, wǒ huì jìnliàng ānpái shíjiān de.) - “Well, I’ll try to arrange my schedule.”
Scenario 2: Declining a Gift Politely
Context: Someone is offering you a gift, but you’re unsure if you should accept it.
Script:
Gift Giver (in Chinese): 这是一份小礼物,送给你的。(Zhè shì yī fèn xiǎo lǐwù, sòng gěi nǐ de.) - “This is a small gift for you.”
You (in Chinese): 太客气了,真不好意思。(Tài kèqì le, zhēn bù hǎoyìsi.) - “You’re too kind, I’m really embarrassed.”
Scenario 3: Responding to a Compliment
Context: You’ve received a compliment on your Chinese language skills.
Script:
Complimenter (in Chinese): 你的中文说得真好!(Nǐ de zhōngwén shuō de zhēn hǎo!) - “You speak Chinese really well!”
You (in Chinese): 哪里,还差得远呢。(Nǎlǐ, hái chà de yuǎn ne.) - “Not at all, I still have a long way to go.”
Scenario 4: Being Offered More Food at a Meal
Context: You’re full at a dinner party, but your host offers you more food.
Script:
Host (in Chinese): 再来一些吧,这是我的招待。(Zài lái yīxiē ba, zhè shì wǒ de zhāodài.) - “Have some more; it’s my treat.”
You (in Chinese): 太客气了,我真的吃不下了。(Tài kèqì le, wǒ zhēn de chī bùxià le.) - “You’re too kind, I really can’t eat anymore.”
Scenario 5: Politely Declining an Invitation
Context: You’ve been invited to an event, but you genuinely cannot attend.
Script:
Friend (in Chinese): 下个周末我们去爬山,你要一起来吗?(Xià ge zhōumò wǒmen qù páshān, nǐ yào yīqǐ lái ma?) - “Next weekend,
we’re going hiking. Do you want to come?”
You (in Chinese): 我真的想去,可是下周末我有别的安排了。(Wǒ zhēn de xiǎng qù, kěshì xià zhōumò wǒ yǒu bié de ānpái le.) - “I
really want to go, but I have other plans next weekend.”

Scenarios 2 and 4 contain glaring mistakes, which are marked with strikethroughs in Table 4. Sce-
nario 2 should be labeled “Accepting” instead of “Declining” a gift politely because “Tài kèqì le, zhēn
bù hǎoyìsi (You’re too kind. I’m really embarrassed)” is typically used when accepting a gift. To politely
decline a gift, one might say something like “Nǐ de xīnyì wǒ lǐng le, dàn lǐwù wǒ zhēnde bùnéng shōu
(I appreciate your kindness, but I really can’t accept the gift).” Scenario 4 features the typical Chinese
hosting practice of offering more food to the guest, and the suggested response is acceptable. The prob-
lem lies with “zhè shì wǒde zhāodài” in the host’s line, which is a direct translation from the English
expression “It’s my treat.” Although it makes sense, it sounds uncomfortable to the Chinese. To encour-
age someone to have more food, the Chinese would typically say something to emphasize how special
the food is or how much more they have.
Besides the glaring mistakes, a closer examination of the scripts for teaching Chinese behavioral
culture reveals subtler issues in Scenarios 1 and 5. Scenario 1 presents “wǒ huì jìnliàng ānpái shíjiān
de (I’ll try to make time for it)” as a way to respond to an invitation with uncertainty. However, in the
Chinese-speaking context, such ambiguity is usually intended to decline the invitation. While Scenario
5 appears to be perfect, the scenario and the strategy are not unique to Chinese-speaking contexts and
are thus less valuable for teaching Chinese behavioral culture.

184

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

Scenario 3 stands out as perfect in terms of accuracy and relevance, presenting a strategy unique to
Chinese culture, namely, responding to compliments with modesty. While this might not immediately
seem related to face-saving, in Chinese culture where modesty is highly valued and outright acceptance
of compliments is discouraged, the responding line here effectively avoids accepting the compliment
without direct refusal, saving the face of both parties. Unsurprisingly, this strategy is featured in three
of the ten scenarios generated by ChatGPT in response to my subsequent requests for more scenarios.
In the remaining seven scenarios generated in the subsequent interactions, all but one feature gener-
ally applicable situations and strategies that resemble those in Scenario 5. For example, there is a sce-
nario labeled “Politely declining an offer to pay for your transportation,” and ChatGPT rightly suggests
“Fēicháng gǎnxiè, dàn wǒ háishì zìjǐ fù ba (Thank you very much, but I’d prefer to pay for it myself).”
The one scenario that stands out to be distinctively Chinese involves the common Chinese practice of
offering to pay at the restaurant. Figure 3 is a screenshot of the scenario. Although this scenario also
involves responding to an offer to pay, ChatGPT aptly suggests a different strategy, “Tài kèqì le, wǒmen
xià cì lún dào wǒ qǐng (You’re too kind; it’s my turn to treat next time),” which indicates acceptance.
This strategy is expected here but not necessarily in the previous scenario because, in Chinese culture,
taking turns to pay for meals is commonly used as a way to nurture relationships. The linguistic structures
in the script, while not perfect, are acceptable for the conversational context. The major flaw lies with
the scenario label. ChatGPT repeats the same mistake it made in Scenario 2 by mislabeling an indirect
acceptance as declining, which reveals its inability to discern this cultural nuance.

Figure 3. ChatGPT-generated script for a restaurant scenario

Focusing on the concepts specific to Chinese culture may have helped prime ChatGPT for produc-
ing more scenarios and scripts specific to Chinese-speaking contexts. Scenarios 2, 3, 4, and the one
featuring an offer to pay at a restaurant are more likely to be observed in Chinese-speaking contexts
than in English-speaking ones. However, the inaccurate scenario labels that confuse “declining” with
“accepting” reveal ChatGPT’s weakness in grasping the cultural nuances. Furthermore, the inaccurate
labeling and unnatural expressions confirm its reliance on translation. The acceptability of most scripts
in this experiment likely reflects ChatGPT’s improved translation accuracy, as most of the situations

185

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

and strategies apply to both English and Chinese contexts, and the few Chinese-specific scenarios have
labels that indicate misinterpreted intention.

Experiment 3: Creating a Guest-at-a-Chinese-Home Saga

The third experiment assesses ChatGPT’s ability to generate a series of scenarios and scripts for learners
to practice acting appropriately in a particular role in Chinese-speaking contexts, in this case, the role
of a guest at a Chinese home. This saga is selected because the Chinese have unique expectations for a
good guest, particularly the expectation that “the guest should allow the host to make decisions” (Jian
et al., 2016, p. 94), which contrasts with the expectations of most English speakers who often prefer to
assert their own preferences.
The prompt goes, “Can you create a series of scenarios and performance scripts for beginner learners of
the Chinese language to practice acting in the role of a guest at a Chinese home?” ChatGPT immediately
provides five scenarios with scripts in Chinese characters, pinyin, and English. These scenarios constitute
a simplified but coherent story of visiting a Chinese home, including greeting the host, complementing
the home, offering to help with preparation, discussing food preferences, and expressing gratitude and
enjoyment. When asked for more scenarios, ChatGPT provides five more scenarios that complement
the initial ones. These include complimenting the host’s cooking, bringing a small gift, engaging in
conversation, offering to help with cleanup, and saying goodbye.
While the scenarios align well with the intended saga, and the scripts are linguistically accurate, not
all of them are useful for enhancing ICC because they do not consistently reflect typical Chinese cultural
expectations. The scripts of Scenarios 4, 7, and 10 stand out as the least useful for Chinese-speaking
contexts. Figure 4 is a screenshot of Scenario 4. In the script, the guest’s line, Wǒ bù chī làde shíwù, bù
zhīdào jīntiān yǒu shénme càiyáo (I don’t eat spicy food. I wonder what dishes you have today), sounds
quite blunt in a Chinese context. In Chinese culture, it is generally considered impolite for a guest to
directly inquire about what dishes the host has prepared. Even when the host asks about food prefer-
ences, a polite response should convey a willingness to defer to the host’s choices, saying something
like “Wǒ bù tiāoshí, zhīshì bútài néng chī làde (I’m not picky about food; I just can’t handle spicy food
very well).” Also, both the underlined words shíwù (food) and càiyáo (dishes) are too formal and un-
necessary for a casual conversation.
Figure 5 is a screenshot of Scenarios 6 and 7. Both scenarios involve the host readily accepting the
guest’s offer, a compliment in the former and a gift in the latter. Readily accepting compliments on the
cooking is non-traditional but increasingly accepted in Chinese culture, especially among the younger
generations influenced by Western cultures. However, such an accepting approach is less common when
the offer is a gift. Practicing such scripts misleads learners to expect the Chinese to accept gifts as readily
as Westerners and feel confused or even offended when their Chinese friend in real life does not do so. A
more useful script should feature the host saying something to indicate their reluctance or embarrassment
about accepting it, such as “Zěnme hái dài dōngxi lái? Zhè ràng wǒmen duō bù hǎo yìsī ā (You shouldn’t
have brought anything. This is really embarrassing for us).” The guest should then encourage the host
to accept the gift by saying something like “Zhè shì wǒde yìdiǎn xīnyì, nín yídìng yào shōuxià (This is
a token of my appreciation. Please accept it).” A Chinese person’s polite reaction to the gift may appear
as a complaint to someone unfamiliar with the culture, so it is important for learners to understand the
host’s real intention and practice the strategies for insisting on the offer.

186

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

Figure 4. ChatGPT-generated scenario for discussing food preferences

Figure 5. GhatGPT-generated scripts for complimenting the food and presenting a gift

187

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

The script of Scenario 10 “Saying Goodbye,” despite being accurate, misses unique Chinese practices
that lack counterparts in English-speaking contexts. Figure 6 is a screenshot of the script. In Chinese
culture, it is customary for a hospitable host to escort the guest to the door, and a polite guest would
decline the offer by saying “Qǐng liú bù (Please save your steps).” As they part ways, the host would
say “Màn zǒu (Walk slowly),” which means “Take care.” These interactions are commonly observed in
Chinese-speaking contexts when a host sees their guest off. Therefore, understanding these customary
practices is crucial for learners to appear polite as a guest in Chinese-speaking contexts.

Figure 6. ChatGPT-generated scenario for departing a Chinese home

The scripts generated in this experiment miss crucial teaching points associated with host-guest
practice specific to Chinese-speaking contexts, suggesting they might be meant for general use. To test
whether ChatGPT considered the Chinese cultural context when creating the scripts, I request ChatGPT
to “create a series of scenarios and performance scripts for beginner learners of the English language to
practice acting in the role of a guest at an American home.” Disappointingly, it immediately provides
the same ten scenarios in the exact same sequence, merely replacing the Chinese characters and pinyin
with English. Consequently, each exchange in the conversation features the same English sentence twice.
It is evident that ChatGPT does not account for the distinct expectations in the specific cultural context
when producing the scenarios and scripts.
Given ChatGPT’s demonstrated knowledge of situations and strategies unique to Chinese culture in
the previous two experiments, the failure here is likely due to ineffective prompting. The prompt does
not explicitly instruct ChatGPT to generate interactions unique to Chinese-speaking contexts. However,
to provide such instructions and evaluate ChatGPT’s response, one must have clear ideas of the Chinese-
specific cultural practices to be included in the script. Therefore, ChatGPT is good for concretizing or
elaborating on the ideas that human instructors conceptualize but cannot substitute for their creative
thinking and cultural expertise.

188

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

CHATGPT’S PERFORMANCE AND LIMITATIONS IN

A CULTURE-FOCUSED CURRICULUM

In all three experiments, ChatGPT exhibited remarkable linguistic accuracy and comprehension abilities.
Its responses were highly relevant to the given prompts, demonstrating its prowess in comprehending
and translating content between English and Chinese. While linguistic accuracy is valuable, it alone
does not suffice to meet the culture-focused curriculum’s goal of fostering ICC, which emphasizes the
ability to take up target-culture perspectives. While ChatGPT generated scenarios that are inspirational,
a closer examination revealed that only a few of the Chinese scripts contained communicative strategies
typical of Chinese-speaking contexts. This limitation arises because ChatGPT’s dataset lacks situations
and strategies that are unique to Chinese culture. ChatGPT has been trained to align with the values of
its initial trainers who are all English speakers (Lowe & Leike, 2022), so even when Chinese-specific
scenarios and scripts are generated in Experiments 1 and 2, they often lack an accurate grasp of cultural
nuances and sometimes misinterpret the speaker’s real intentions. The user needs to know the Chinese
culture enough to discern useful content.
ChatGPT’s performance in grasping the cultural context may be dependent on explicit instruction.
In Experiments 1 and 2, where ChatGPT received explicit instructions to compare communicative
strategies in different cultural contexts or was primed by Chinese cultural values, it generated a few
Chinese-specific scenarios and scripts. However, in Experiment 3, where such explicit instructions were
absent, ChatGPT’s responses lacked Chinese-specific interactions. Moreover, while all three experiments
produced scenarios and scripts that feature receiving compliments or gifts, only those in the first two
experiments had the receiver respond modestly to compliments and embarrassedly to the gift, which are
expected reactions in Chinese cultural contexts. In Experiment 3, such scenarios featured the receiver
readily accepting the compliment and the gift, a practice more likely to be observed in English-speaking
contexts. These findings highlight the significance of prompt design when using AI tools like ChatGPT
to generate content for teaching intercultural communication.
To yield the most cost-effective, accurate, useful, and safe outputs, the prompt must contain explicit,
precise, and detailed instructions. Creating such prompts requires (a) an understanding of how ChatGPT
interprets input; (b) adequate knowledge of the inquired domain; and (c) a tedious trial-error process (Mit-
tal, 2023). Designing a prompt to produce a script for practicing intercultural communicative strategies
would require knowledge of both the learner’s base culture and the target culture. Therefore, ChatGPT’s
capability in responding to inquiries does not readily translate into convenience for language teachers
and students in the culture-focused curriculum. Teachers and students need substantial training to be
able to really harness ChatGPT’s power.
ChatGPT’s responses in all three experiments consisted of generic scenarios and brief two-turn scripts,
many of which were not readily usable as they contained expressions that were accurate but unnatural
for Chinese conversational contexts. The brevity of scripts was likely due to ineffective prompting. In-
structing ChatGPT to brainstorm scenarios and scripts might have made it focus more on the number of
scenarios than the details of the scripts. To generate more elaborate performance scripts, ChatGPT may
need prompts that resemble those used in Zeng’s (2023) and Wang’s (2023b) queries, providing specific
descriptions of the roles and their intentions. Yet, creating such prompts requires much imagination and
creativity. Therefore, ChatGPT’s creative capabilities appear limited for culture-focused tasks, often
requiring human instructors to carry out the real creative work.

189

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

In sum, ChatGPT’s prowess in comprehension and translation makes it a valuable tool for various
language learning tasks, but its performance in the context of a culture-focused curriculum reveals no-
table limitations. While ChatGPT can generate relevant and linguistically accurate content for reference,
the scenarios and scripts often need much scrutiny for cultural representativeness and appropriateness.
Therefore, human instructors remain essential in selecting useful scenarios and creating culturally rich
scripts to help learners develop effective strategies for intercultural communication.

THE IMPLICATIONS FOR FOREIGN LANGUAGE

EDUCATION AND THE INTEGRATION OF AI

Foreign language education in the AI era can thrive by harnessing ChatGPT’s remarkable linguistic
abilities and complementing their weaknesses in intercultural awareness and skills. Compared with
human instructors, ChatGPT can offer cheaper, more accessible, and more personalized instruction for
enhancing linguistic accuracy and fluency, threatening the sustainability of foreign language classes that
are solely driven by language-focused goals. However, it cannot teach learners practical strategies for
negotiating expectations and intentions with members of the target culture. Therefore, foreign language
instruction should shift its focus toward the more practical and cultural aspects of language learning to
maintain its vigor in the AI era.
Culture-focused, flipped curricula like the one described at the beginning of this chapter prove to
integrate AI while preserving academic integrity and the depth of learning. Such curricula are char-
acterized by the enactment of scenarios where non-native speakers may inadvertently misrepresent or
misinterpret intentions. This performance-based approach integrates culture into language application.
It compels students to personally demonstrate their language knowledge in real-life situations, exposing
their misconceptions about target-culture expectations and receiving feedback from the instructor. To
succeed in such curricula, students must go beyond mere memorization or translation and develop the
ability to assess the situation and adjust their communicative strategies on the fly, leaving little room
for students to have ChatGPT do their work. In such culture-focused curricula, ChatGPT’s role becomes
one of a reference tool rather than a primary learning resource. It can facilitate learning and teaching,
but not substitute for them.
While incorporating ChatGPT into language education can benefit teachers and learners in many
ways, it is not without its challenges and consequences. Using ChatGPT in a cost-effective way requires
us to learn to play its language-game, which is very different from the one we play daily with fellow
beings. In our daily language-game, “the meaning of a word is in its use in the language” (Wittgenstein,
1958, p.20), so words can take on different meanings depending on the activity that employs them. When
playing the game, we focus on the communal activity rather than the words. By contrast, in ChatGPT’s
language-game, a word’s meaning is prescribed and finite, so specific keywords or sequences are neces-
sary to trigger certain responses. When playing the game, one must focus on the words and ensure their
use aligns with the large language model (LLM) that powers the AI tool. Playing AI’s language-game
restrains the creativity of human language and stifles human culture, the process of meaning-making
that frames our actions and our conceptions of ourselves (Hall, 1996; Street, 1993). Overreliance on
ChatGPT runs the risk of eroding our proficiency in playing the human language-game and leading to
social challenges and hardships.

190

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

Finally, foreign language instructors and learners must understand that achieving ICC primarily in-
volves creative and culturally responsive work, for which ChatGPT’s capabilities may not align. While
AI tools can provide valuable support, the true development of ICC requires the guidance of human
instructors. Therefore, foreign language educators should place increased emphasis on broadening their
intercultural experiences and enhancing their sensitivity to cultural differences to complement AI tools
and keep enriching the human language-game.

REFERENCES

American Council on the Teaching of Foreign Languages (ACTFL). (2017). NCSSFL-ACTFL Can-Do
Statements. Retrieved from https://www.actfl.org/resources/ncssfl-actfl-can-do-statements
Baskara, R., & Mukarto, M. (2023). Exploring the implications of ChatGPT for language learning in
higher education. Indonesian Journal of English Language Teaching and Applied Linguistics, 7(2),
343–358. doi:10.21093/ijeltal.v7i2.1387
Buchanan-Shrader, H. (2023). Top 8 Ways Chinese Teachers Can Use ChatGPT to Create Lesson Plans.
https://www.thechairmansbao.com/blog/chatgpt-teach-chinese/
Byram, M. (2020). Teaching and assessing intercultural communicative competence: Revisited. Multi-
lingual Matters. doi:10.21832/BYRAM0244
Dörnyei, Z., & Ushioda, E. (Eds.). (2009). Motivation, language identity and the L2 self. Multilingual
Matters. doi:10.21832/9781847691293
Hall, S. (1996). Introduction: Who needs “identity”? In S. Hall & P. Du Gay (Eds.), Questions of Cul-
tural Identity (pp. 1–17). Sage.
Hammerly, H. (1986). Synthesis in language teaching: An introduction to languistics. Second Language
Publications.
Hong, W. (2023). The impact of ChatGPT on foreign language teaching and learning: Opportunities in
education and research. Journal of Educational Technology and Innovation, 5(1), 37–45.
Jian, X., Wang, J., Jia, J., & Feng, C. (2016). Perform Suzhou: A course in intermediate to advanced
spoken Mandarin. Soochow University Press.
Kasneci, E., Sessler, K., Küchemann, S., Bannert, M., Dementieva, D., Fischer, F., Gasser, U., Groh, G.,
Günnemann, S., Hüllermeier, E., Krusche, S., Kutyniok, G., Michaeli, T., Nerdel, C., Pfeffer, J., Poquet,
O., Sailer, M., Schmidt, A., Seidel, T., ... Kasneci, G. (2023). ChatGPT for good? On opportunities
and challenges of large language models for education. Learning and Individual Differences, 103, 1–9.
doi:10.1016/j.lindif.2023.102274
Keating, E., & Egbert, M. (2004). Conversation as a cultural activity. In A. Duranti (Ed.), A companion
to linguistic anthropology (pp. 169–188). Blackwell Publishing Ltd.
Kohnke, L., Moorhouse, B. L., & Zou, D. (2023). ChatGPT for Language Teaching and Learning. RELC
Journal, 0(0), 537–550. Advance online publication. doi:10.1177/00336882231162868

191

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

Lowe, R., & Leike, J. (2022). Aligning language models to follow instructions. OpenAI. https://openai.
com/research/instruction-following
Mittal, A. (2023, July 26). The essential guide to prompt engineering in ChatGPT [Blog post] Retrieved
from https://www.unite.ai/prompt-engineering-in-chatgpt/
Noda, M. (2007). Performed culture: Cataloguing culture gains during study abroad. Japanese Language
and Literature, 41(2), 297–314.
Pasden, J. (2023). Using ChatGPT to learn Chinese [Blog post]. Retrieved from https://www.sinosplice.
com/life/archives/2023/02/03/using-chatgpt-to-learn-chinese
Pike, K. L. (1967). Language in relation to a unified theory of the structure of human behavior (2nd,
revised edition). Mouton & Co., Publishers.
Rettberg, J. W. (2022, December 6). ChatGPT is multilingual but monocultural, and it’s learning your
values [Blog post]. https://jilltxt.net/right-now-chatgpt-is-multilingual-but-monocultural-but-its-learning-
your-values/
Schieffelin, B. B., & Ochs, E. (Eds.) (1986). Language socialization across cultures: Studies in the social
and cultural foundations of language. Cambridge University Press.
Schulhoff, S., Khan, A., & Yanni, F. (2023). Your guide to communicating with artificial intelligence.
Retrieved from https://learnprompting.org/
Seemiller, C., & Grace, M. (2019). Generation Z: A century in the making. Routledge.
Street, B. V. (1993). Culture is a verb: Anthropological aspects of language and cultural process. In D.
Graddol, L. Thompson, & M. Byran (Eds.), Language and Culture (pp. 23–44). BAAL and Multiple
Matters.
Walker, G. (2010). Performed culture: Learning to participate in another culture. In G. Walker (Ed.),
The pedagogy of performing a culture (pp. 1–21). National East Asian Languages Resource Center.
Walker, G. (2021). Why we perform. In X. Zhang & X. Jian (Eds.), The third space and Chinese lan-
guage pedagogy: Negotiating intentions and expectations in another culture (pp. 139–158). Routledge.
Walker, G., & Noda, M. (2010). Remembering the future: Compiling knowledge of another culture. In
G. Walker (Ed.), The pedagogy of performing a culture (pp. 22–48). National East Asian Languages
Resource Center.
Wang, J. (2016). Ecology of literacy: A context-based inter-disciplinary curriculum for Chinese as
a foreign language (Doctoral dissertation). Retrieved from https://rave.ohiolink.edu/etdc/view?acc_
num=osu1461251633
Wang, J. (2023a, March 25). Xiang ChatGPT qingjiao “ba” zi ju – xisijikong de liangge quehan向
ChatGPT请教“把”字句——细思极恐的两个缺憾 [Consulting ChatGPT on the “ba” sentence – Two
terrifying deficiencies upon careful reflection] [Blog post]. Retrieved from https://mp.weixin.qq.com/s/
dXvedrVHrdtJKJ9Yda6qpQ

192

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

Wang, J. (2023b, March 18). ChatGPT neng fou zhuli tiyan wenhua chuji xuecai zhizuo? ChatGPT能
否助力体演文化初级学材制作? [Can ChatGPT assist in creating beginner-level learning materials for
performing the culture?] [Blog post]. Retrieved from https://mp.weixin.qq.com/s/rY4GkQYw7umEqR-
fEQVepmQ
Wang, J., & Jia, J. (Eds.). (2022). Performed Culture in action to teach Chinese as a FL: Integrating
PCA in curriculum, pedagogy, and assessment. Routledge.
Wittgenstein, L. (1958). Philosophical investigations (3rd ed.; G. E. M. Anscombe, Trans.). Prentice
Hall. (Original work published 1953)
Yu, L. (2021). The Performed Culture Approach. In Z. Ye (Ed.), New trends in teaching Chinese as a
foreign language (pp.1–34). Singapore: Palgrave Macmillan. doi:10.1007/978-981-13-6844-8_7-1
Zeng, Z. (2023, February 25). Yu ChatGPT zuo pengyou!与ChatGPT做朋友! [Befriending ChatGPT]
[Blog post]. Retrieved from https://mp.weixin.qq.com/s/LLruwI7bWpSuCkAUx5BkiA

KEY TERMS AND DEFINITIONS

Behavioral Culture: The tacit knowledge of effective (re)actions in specific contexts. It is embodied
in the dynamic processes that frame the behavior of its members and give them the means to recognize
the behaviors of their own and others in specific contexts.
Conversation: Any spontaneous interaction involving two or more participants collaborating toward
a shared goal in a specific context, with or without the assistance of external media (such as a writ-
ing system). The essence lies in an awareness of and genuine respect for the perspectives of the other
participant(s) in the specific context.
Cultural Knowledge Compilation: The conceptualization of memory processes in the Performed
Cultural Approach. In this conceptualization, personal memories of performances constitute categories of
“cases” (memories related to tasks and functions), “sagas” (memories related to specific people or places),
and “themes” (memories related to a culture-specific concept that underlies a wide range of behaviors).
Culture-Focused: A framework for developing and implementing foreign language curricula where
the goal is to enable learners to function effectively in the target culture. Within a culture-focused
framework, linguistic codes are both a product and an integral part of communicative behavior. Their
significance relies on individual speakers’ interpretation of communicative intentions, which are deter-
mined by communicative situations. Personal perception of situations is constrained by one’s cultural
experiences. Hence, the primary goal of language learning within a culture-focused framework is to
accumulate experiences in communication within the target culture and acquire the ability to accurately
identify one’s own and others’ behavioral intentions in specific situations.
Flipped Curriculum: A curriculum designed for implementing the flipped classroom strategy. It
combines self-directed independent pre-class learning with in-class experiential learning to enhance the
effectiveness of language acquisition.

193

Integrating ChatGPT Into a Culture-Focused Flipped Curriculum

Intercultural Communicative Competence (ICC): The ability to interact effectively and appro-
priately with people from other linguistic and cultural backgrounds. Compared with “communicative
competence,” this concept emphasizes the ability to take up the perspectives of the listener or reader in
intercultural communication.
Performance: A situated communicative event specified by five basic elements of human behavior,
namely time, place, roles, audience, and script. It is the basic unit of culture-focused foreign language
instruction and assessment.
Performed Culture Approach (PCA): An innovative approach to foreign language education founded
by Dr. Galal Walker and his colleagues at The Ohio State University. It is rooted in the Confucian con-
cept of “Zhixing heyi (Knowing and doing as one and the same process)” and informed by sociocultural
theories and the latest developments in cognitive science. This language-teaching approach pioneers a
culture-focused framework characterized by performance-based instruction and assessment.
Prompting Strategies: Deliberate approaches or techniques employed by users to elicit specific,
desired responses from large language models (LLMs). Users may structure their input, question word-
ing, or context in a way that guides the model to generate information, ideas, or answers aligned with
their preferences or objectives. These strategies aim to influence the output by shaping the conversation
through thoughtful prompts.

194
195

Chapter 10
Redefining Traditional
Pedagogy:
The Integration of Machine
Learning in the Contemporary
Language Education Classroom

Géraldine Bengsch
University of York, UK

ABSTRACT
The digital transformation of education, accelerated by unforeseen global events like the COVID-19
pandemic, has ushered in a new era in pedagogy, including in language instruction. While the shift to
online platforms has been swift, the evolution of content from static digital forms to dynamic, interac-
tive experiences driven by artificial intelligence (AI) is still emerging. This chapter explores the trans-
formative potential of machine learning (ML) in redefining traditional language learning materials
into adaptive, responsive, and personalised educational experiences. The chapter outlines theoretical
applications and presents a prototype app, “TalkToMe,” designed to boost speaking practice in the
target language. Additionally, it addresses ethical concerns surrounding ML integration in education,
ensuring the preservation of academic integrity. This chapter aims to bridge the gap between traditional
methodologies and cutting-edge technology, offering a roadmap for the future of language instruction
through collaboration between pedagogy and technology.

INTRODUCTION

The onset of the 21st century has begun to integrate an unparalleled fusion of technology and education.
Never before have educators had access to such a broad array of tools, designed not just to inform, but to
reshape instruction (Dalton‐Puffer, 2011; Hussherr & Hussherr, 2017; Warschauer & Healey, 1998). The
use of technology in the classroom was accelerated to an unforeseen pace through the advent of global
events, especially the Covid-19 pandemic, forcing education to adapt, reinvent, and move predominantly

DOI: 10.4018/979-8-3693-0872-1.ch010

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

Redefining Traditional Pedagogy

to online platforms in the provision of emergency teaching (Hodges et al., 2020; Klimova, 2021; W. Li
et al., 2021). This digital transformation, while swift, carried with it remnants of traditional pedagogy,
often translating physical materials directly into their digital counterparts without harnessing the full
potential of the digital medium (Radić et al., 2021). However, now that the pandemic and emergency
teaching provisions have become a thing of the past, educators may be considered to contemplate new
ways of utilising technology in their everyday practice (Korkmaz & Toraman, 2020).
In the realm of language education, this dynamic is particularly salient. The rich concept of language,
with its nuances, cultural contexts, and multifaceted layers of comprehension, presents both challenges
and opportunities when integrated with technology (Arnó-Macià & Barés, 2015; Misiejuk et al., 2023).
Traditional methods, ranging from vocabulary lists to static grammar exercises, while effective to an
extent, often lack the adaptability and responsiveness that the digital age promises (Arnó-Macià & Barés,
2015). It is here, at the intersection of traditional language instruction and cutting-edge technological
potential, that Machine Learning (ML) emerges as a potential tool of transformation and extension of
traditional methods (Briggs, 2018).
The subsequent sections aim to show some of the ways in which ML, particularly through tools
like Large Language Models (LLMs), can redefine the landscape of language education (Jeon & Lee,
2023). By transferring static resources into dynamic, responsive, and tailored experiences, ML is set to
change how educators can approach and leverage language instruction and how learners engage with
(Bonner et al., 2023). This chapter will address both the potential of this connection between pedagogy
and technology, as well as the challenges and ethical considerations it brings forth.
It is important to note that the main argument of this chapter is on utilising machine learning as a
tool to enhance traditional teaching methods. It is argued that the future of language instruction is not
about replacing the human touch, but about amplifying it (Selwyn, 2019). It is about harnessing the
power of ML to complement, enrich, and diversify the learning experience, ensuring that every student
not only learns a language but has an opportunity to immerse themselves in it (Kharb & Singh, 2021;
Zou et al., 2018).

BACKGROUND

In the heart of every classroom lies a microcosm of the world outside – one that reflects broader trends,
attitudes, and shifts. Over the last decade, educators have observed the ebb and flow of students’ engage-
ment with language learning, their aspirations mingling with their apprehensions, crafting a complex
landscape of challenges and potential (Asiksoy, 2018).

Static Digital Forms vs. Dynamic ML-Powered Experiences

Traditionally, language instruction has been rooted in fixed formats. Be it textbooks, flashcards, or
worksheets, these static methods have been the bedrock of foundational language learning (Preis et al.,
2023). While effective to a certain extent, they come with inherent limitations. This chapter is inspired
by the author’s decade long experiences of teaching German at a university in England. Recollecting
an instance from the classroom, a group of beginner-level students grappled with the intricacies of the
German language. Their primary struggle? Engaging authentically with the language. Static tools offered
them limited, often repetitive experiences, which, over time, diminished their enthusiasm. However, for

196

Redefining Traditional Pedagogy

beginners to pre-intermediate learners of a language, it often remains difficult to find material that is
suitable for their level (Gilmore, 2007; Nikitina, 2011; Shadiev et al., 2020).
Enter the world of Machine Learning. What if these students had access to dynamic platforms that
adjusted in real-time to their responses? Tools that could simulate real-world interactions, adapt to their
learning curve, and offer personalised feedback. Such tools would allow even beginners to engage mean-
ingfully with their target language, without the steep learning curve that traditionally exists to interact-
ing with authentic material or native speakers. The transition from static digital forms to ML-powered
experiences is not just about innovation; instead, it invites practitioners to consider reimagining the very
essence of language engagement (Preis et al., 2023).

The Gap Between Traditional Pedagogies and Technological Potential

The divide between what traditional pedagogies offer and what technology promises is vast. As an educa-
tor, some of the most poignant feedback received revolves around the limitations of conventional tools.
Over the years, the author noticed that students become frustrated with the lack of scalable resources
that can adjust to their unique pace. Others expressed apprehension about communicating with native
speakers, fearing the loss of face due to potential mistakes (Ryan & Viete, 2009; Shumin, 2002).
Moreover, the challenges extend beyond the classroom. Many students seek immersive experiences
outside formal instruction, attempting to engage with authentic material like newspapers or movies.
But here lies the dilemma: the absence of real-time feedback and guidance often leaves them feeling
overwhelmed and lost (Lochtman, 2002; Sari & Aminatun, 2021). However, post the Covid-19 era, there
appears to be a change in students’ attitude towards language learning and the use of technology within
it. The behavioural patterns of learners have undergone a noticeable shift. Digital platforms, once viewed
with scepticism and a burden, are now embraced with a somewhat more open mindset (Toquero, 2020).
The remote working culture further accentuates this, leading to a dispersed learner base, more inclined
to experiment with digital tools (Moser et al., 2021).

Navigating the New Normal

The world post-Covid has evolved in ways beyond what could have been imagined at the beginning
stages of the pandemic. For language education, this meant a drastic transformation in how students
perceive and interact with digital tools (Son et al., 2020). Returning to the classroom then, makes the
use of static grammar exercises from often outdated textbooks seem even more jarring (Dooly, 2023).
Today’s learner seeks engagement, real-time feedback, and, most importantly, a touch of fun (Pujiani et
al., 2022). The lack in engagement that once was so dominant in digital interactions appears to gradually
be giving way to a more open, experimental mindset, showing the readiness of a new era in language
instruction (Ironsi, 2022; Pujiani et al., 2022).
The current landscape of language education is witnessing a shift from static digital forms to dynamic
ML-powered experiences. Traditional pedagogies are being challenged by the potential of technology,
and educators are recognising the need to bridge the gap between the two.. It is noted that learners have
become used to the ever increasing availability of dedicated apps and websites that promote language
learning outside of the classroom (Heil et al., 2016; Pikhart, 2020). This is not a particularly new no-
tion (Gilakjani, 2012), but the current direction of the use of technology in language learning that is

197

Redefining Traditional Pedagogy

not restrained to the classroom can be potentially utilised to increase grit and learner motivation in the
classroom as well (Hejazi & Sadoughi, 2023; Lai et al., 2022).

MACHINE LEARNING AND LANGUAGE LEARNING

Introduction to Machine Learning and Its Significance

Machine Learning (ML) – a phrase that has echoed across various industries, has shaped most of ev-
erything in day-to-day activities, from e-commerce to medical diagnostics. At its core, ML enables
computers to learn from and make decisions based on data. Unlike traditional algorithms that operate
under explicitly programmed instructions, ML systems can fine-tune their operations based on patterns
they identify. However, what sets ML apart from traditional computer programs is its ability to learn and
adapt without being explicitly programmed with step-by-step instructions (Hopkins, 2022).
In the realm of language education, Machine Learning has found various applications that have
shaped the field. Early iterations of ML in language learning focused on basic pattern recognition in
linguistic data, laying the foundation for more sophisticated tools that combine language acquisition
with computational algorithms These tools leverage ML’s ability to learn from data and make decisions
based on identified patterns (Sutton & Barto, 1998). Reinforcement learning, a subfield of ML, has been
applied to language education to improve the quality of language literacy. By using ML algorithms, the
effectiveness and readability of teaching materials can be enhanced, leading to better interactions in the
classroom (Jatzlau et al., 2019). These applications highlight the potential of ML to improve language
instruction and create more personalised and effective learning experiences which will be discussed in
future sections.

The Gamification Wave: Duolingo and Its Kin

Duolingo stands out as a prominent example of Machine Learning’s impact on language education, char-
acterised by its innovative integration of gamification elements into language instruction. The platform’s
appeal lies in its ability to transform language learning from a passive endeavour into an interactive and
engaging journey. Duolingo’s gamified approach presents learners with bite-sized lessons, encouraging
them to maintain streaks, and offering rewards for consistent progress. This approach capitalizes on the
principles of active engagement and motivation, aligning with contemporary educational theories that
emphasize learner involvement (Shortt et al., 2023). The gamification features employed by Duolingo,
such as points, leaderboards, and achievements, foster competition and motivation among learners. This
engagement is particularly beneficial for self-paced learners who require intrinsic motivation to stay
committed to their language learning journey. Duolingo’s approach not only caters to diverse learning
styles but also resonates with learners after a pandemic, who are accustomed to interactive and reward-
ing online experiences (Ünal & Güngör, 2021).
One noteworthy critique revolves around Duolingo’s treatment of grammar. The platform’s implicit
approach to grammar instruction, although effective for certain learners, can pose challenges when
merging with traditional classroom instruction, where explicit grammar teaching remains an important
concept, not only for ensuring learning progress, but also to ensure a common language for teachers
to talk to students to about their target language (Jiang et al., 2021). Striking a balance between the

198

Redefining Traditional Pedagogy

advantages of gamified language learning and the necessity of explicit grammar instruction remains an
ongoing challenge in the field. In this chapter, some suggestions are made to create apps that embrace
technology but are targeted to complement existing teaching practices in the language classroom.

The Google Translate Conundrum

Google Translate stands as an important tool in breaking down language barriers in real-time, offering a
lifeline to many learners navigating unfamiliar linguistic terrains. Its convenience and accessibility make
it an indispensable resource for quick translations, especially in today’s globalised world.
One of the primary limitations of Google Translate in the context of language education is its tendency
to overlook granular details such as grammar, nuances, and context. Learner dictionaries, which are pivotal
in language acquisition, excel in providing these finer points (Lew, 2004). While Google Translate excels
in bridging communication gaps, its reliance on machine-driven translation algorithms can occasionally
result in translations that lack cultural sensitivity or context appropriateness. This limitation can hinder
learners striving for cultural and contextual fluency in addition to linguistic competence (Tumbal et al.,
2021). Language educators and learners need to be mindful of these constraints and consider supplemen-
tary resources to achieve a more holistic language learning experience. The suggestions in this chapter
aim to use technology in a manner that is meaningful to language learners and provides them with an
option to obtain useful feedback that they can implement into their learning goals.

The Evolution: Transformers, Generative AI, and LLMs

The rapid advancement of Machine Learning (ML), including the advent of the transformer architecture,
reshaped the landscape of natural language processing (NLP) and have since become instrumental in
enhancing language instruction.
Transformers, as architectural innovations, stand as a testament to the power of deep learning. They
introduced a novel way of processing sequential data, allowing for more efficient and context-aware
language modelling (Vaswani et al., 2017). Their ability to capture long-range dependencies within text
highly improved the quality of machine-generated text, enabling applications ranging from chatbots
to language translation systems. This breakthrough has had a profound impact on language education,
enhancing the development of more advanced and contextually aware language learning tools (Kim
et al., 2023; Suresh et al., 2021). For instance, it has enabled the development of chatbots and virtual
language tutors capable of engaging in natural language conversations with learners, thereby providing
them with a realistic language practice environment (Baidoo-Anu & Ansah, 2023; Baskara, 2023; Su
& Yang, 2023). In this strand of ML fall Large Language Models (LLMs) and Generative AI. These
models, such as GPT-3 and 4 (Generative Pre-trained Transformer 3 and 4), exhibit an unprecedented
capacity to comprehend and generate human language with remarkable accuracy. LLMs have shown
great impact on many areas of society and are more than likely to shape a future where language instruc-
tion is not just tailored to individual learners but is deeply personalised, contextual, and dynamically
adaptive (Bozkurt, 2023; Pérez-Núñez, 2023). LLMs have the capability to make language instruction
more effective and accessible to learners of all backgrounds, especially with limited contact hours in
the classroom (Baidoo-Anu & Ansah, 2023; Pérez-Núñez, 2023).
However, it is imperative to keep mindful while exploring this promising yet evolving landscape. Chal-
lenges related to privacy, bias in training data, and the ethical use of AI in education must be addressed

199

Redefining Traditional Pedagogy

as we harness the potential of LLMs for language learning (Lee, 2018). Furthermore, the integration of
LLMs into educational environments requires thoughtful pedagogical considerations to ensure that they
enhance, rather than replace, the vital role of human educators.

TRANSFORMATIONAL CAPACITY OF ML IN LANGUAGE INSTRUCTION

The very essence of language learning is transformative. It is not just mere acquisition of vocabulary and
grammar rules, but a personal journey that encompasses culture, cognition, and communication. With
the infusion of Machine Learning (ML) into this intricate landscape, the process of transformation takes
on an even more profound resonance. The potential of ML within language instruction is extensive, and
while this chapter will delve into pivotal aspects such as vocabulary acquisition, pronunciation improve-
ment, reading comprehension enhancement, cultural immersion, and speaking proficiency, it is crucial
to recognise that these represent just the tip of the iceberg (Su & Yang, 2023).
However, it is important to emphasise that while ML offers immense potential, it should complement,
not replace, the role of human educators. Cultural insights, and nuanced guidance provided by teachers
remain indispensable in language instruction. The following sections discuss some of the areas in which
ML can offer avenues into personalised learner journeys.

Vocabulary Acquisition: Unlocking the Power of Personalisation

Vocabulary acquisition is undeniably central to language learning. In traditional language instruction,

the emphasis has often been on memorisation and repetition, where learners are tasked with committing
an extensive list of words to memory through sheer repetition and static activities (Paribakht & Wesche,
1997). Rather than subjecting all learners to the same list of words and the same pace, ML systems tailor
the vocabulary learning experience to the individual.
Consider a student who is grappling with certain words in the language they are learning. In a tra-
ditional setting, these challenging words might be presented once, and the student is left to memorize
them through repetition. ML changes this paradigm. When a learner struggles with specific words, ML
algorithms ensure that these words are revisited in subsequent exercises, ensuring consistent reinforce-
ment until mastery is achieved. This approach is akin to a personal language coach who identifies the
learner’s areas of difficulty and provides targeted support, thereby optimising the learning trajectory.
Rather than presenting words in isolation, these systems can introduce vocabulary within the context of
sentences or real-world scenarios. This contextual learning not only aids in better comprehension but
also facilitates the application of newly acquired vocabulary in practical situations, which is essential
for language proficiency (Ehara, 2023; Ginn et al., 2021).

Pronunciation: Precision Through ML-Powered Feedback

Pronunciation serves as the vital bridge that connects the knowledge of words to their effective use in
communication. Traditional methods for improving pronunciation, such as listening to model record-
ings or relying on textbook guidelines, have played essential roles in language learning. However, these
approaches have inherent limitations in providing real-time, personalised feedback and analysis. This

200

Redefining Traditional Pedagogy

is where Machine Learning (ML)-powered tools can step in, ushering in a new era of precision and ef-
ficiency in pronunciation enhancement.
ML-driven pronunciation tools offer a dynamic and responsive learning experience. Instead of merely
listening to model recordings, learners can engage in real-time speech exercises with ML-powered sys-
tems. As learners speak, the ML algorithms instantly evaluate their pronunciation against native or ideal
speech patterns. This immediate feedback is invaluable as it allows learners to make corrections and
improvements on the spot, helping them develop an authentic and fluent speaking style (Liu & Quan,
2022; Piotrowska et al., 2021).

Reading Comprehension: Interactive Mastery With ML

Reading comprehension stands as a vital test for language proficiency, representing the ability to not just
recognise words but to understand their context and meaning within sentences and passages. Traditional
methods for enhancing reading comprehension often involve static exercises where learners read predefined
passages followed by a set of questions. However, the advent of Machine Learning has opened exciting
possibilities to transform this conventional approach into a dynamic and interactive learning experience.
ML-powered reading comprehension tools excel in making the process of understanding and ab-
sorbing written content highly engaging and informative. One of the most significant transformations
is the ability to click on any word within the text to instantly access a wealth of information. ML also
enhances reading comprehension by offering context-rich content. Traditional exercises often involve
isolated passages, lacking the real-world context that learners encounter in their everyday language us-
age. ML-powered tools can provide learners with articles, news stories, or literary excerpts that mirror
real-life situations and offer a deeper understanding of the language in its natural context. This exposure
not only improves comprehension but also cultivates cultural awareness and contextual fluency (Chen
et al., 2021; Hassan Taj et al., 2017).

Cultural Immersion: Enriching Language Learning

Through ML-Enhanced Experiences

Language is not merely a collection of words and grammar rules; it is interwoven with culture, history,
and societal nuances. Traditional language learning methods have often attempted to provide glimpses
into cultural contexts through supplementary notes or additional readings. Rather than presenting learn-
ers with static descriptions or explanations of cultural elements, ML can enable them to step into these
cultural contexts, fostering a truly immersive and enriching experience. ML can provide learners with
insights into cultural nuances and comparisons between their native culture and the culture associated
with the language they are learning. This transformational approach to cultural immersion not only en-
hances language learning but also cultivates a deeper appreciation and respect for the cultural diversity
that language embodies. ML can analyse a learner’s native cultural context and draw parallels or con-
trasts with the culture of the target language. Such comparative insights help in developing a nuanced
understanding of cultural differences and similarities. This perspective is vital in cultivating empathy and
respect for diversity, an essential component of global citizenship. It enables learners to understand the
cultural contexts in which languages thrive, fostering a more profound connection with the language and
the communities that speak it. They do not just learn to communicate; they learn to connect, appreciate,
and engage with a different culture on a profound level. This not only enhances their language skills

201

Redefining Traditional Pedagogy

but also broadens their worldview, preparing them to navigate and contribute positively in a globally
interconnected world. (Kolovou, 2021).

Speaking: Unlocking Fluency Through ML-Enhanced Interactions

Speaking is one of the most challenging and crucial facets of language learning. It represents the junc-
ture where knowledge meets real-world application, where learners transform their understanding of
words and grammar into effective communication. Traditional language classrooms, while essential,
often provide limited opportunities for speaking practice, and learners may not feel ready to speak in
front of their peers. However, Machine Learning has emerged as a potential bridge to overcome these
limitations, offering innovative solutions that enable learners to enhance their speaking skills and achieve
fluency more effectively. ML’s speech recognition capabilities are continually evolving, enabling sys-
tems to understand various accents, dialects, and speaking styles. This adaptability ensures that learners
from diverse linguistic backgrounds receive accurate feedback and can practice speaking in a way that
aligns with their target language’s native speakers. ML leverages Natural Language Processing (NLP)
to understand and respond to learners’ spoken language. This technology allows learners to engage in
open-ended conversations, ask questions, and receive detailed responses, simulating real-life interactions
(Brena et al., 2021).

CONCEPTUAL EXPLORATION: FROM STATIC TO DYNAMIC

So far, it has been discussed that in the ever-evolving landscape of the digital age, the conventional methods
of language learning often fall short of meeting the dynamic demands and aspirations of modern learn-
ers. These traditional tools and approaches, while valuable in their own right, frequently leave learners
desiring more engaging and personalised experiences. In this section, various aspects of a potential the
fusion of pedagogy and technology, through the lens of ML, are explored with more specific examples
of how ML could be incorporated into applications useful to enhance traditional language learning.
The concepts introduced earlier are revisited and imagined as apps that could be incorporated into the
traditional language learning classroom.

Adaptive Vocabulary Quizzes: Personalised Reinforcement Through ML

Traditional vocabulary learning methods, often centred around static vocabulary lists or flashcards,
have long been employed in language education. However, these conventional approaches tend to adopt
a one-size-fits-all strategy, where all learners are presented with the same set of words and exercises,
regardless of their individual proficiency levels or learning paces. In contrast, Machine Learning can
introduce the concept of adaptive vocabulary quizzes to optimise vocabulary acquisition. Let’s delve
into the potential of this ML-driven approach and outline an example app for language learning, both
inside and outside the classroom.

App Concept Outline: DynamicVocaLearn

Features and Functionality of an app to increase the interactivity of vocabulary are outlined below.

202

Redefining Traditional Pedagogy

• Adaptive Quizzes: The core feature of DynamicVocaLearn is its adaptive quizzes. Learners begin
with a quick assessment to gauge their current vocabulary proficiency level. Based on this initial
evaluation, the app tailors vocabulary quizzes to each learner’s unique needs and performance.
• Progress Tracking: The app provides real-time feedback and tracks learners’ progress. It offers
insights into areas of improvement, words frequently missed, and overall vocabulary growth.
• Personalised Vocabulary Sets: DynamicVocaLearn utilises ML algorithms to curate vocabu-
lary sets for each learner. The system considers the learner’s strengths and weaknesses, ensuring
that challenging words are revisited for reinforcement, while familiar words are introduced less
frequently.
• Difficulty Adjustment: The app dynamically adjusts the difficulty of quizzes based on the learner’s
performance. Learners are consistently challenged without feeling overwhelmed.
• Real-Life Context: Vocabulary is presented in context, with sentences and examples that mimic
real-life language use. This contextual learning aids comprehension and retention.
• Spaced Repetition: ML-driven spaced repetition techniques are employed to optimise long-term
retention. Words are reintroduced at strategic intervals to reinforce memory.

Pronunciation Corrector

While traditional methods rely on model audio recordings, ML provides real-time feedback. By analysing
the learner’s pitch, stress, and pronunciation against a vast database, instant corrections can be suggested,
aiding in quicker and more accurate mastery.

App Concept Outline: PronunCheck

Features and Functionality of an app to increase the interactivity of pronunciation improvement are
outlined below.

• Real-Time Pronunciation Assessment: PronunCheck’s core feature is its real-time pronunciation

assessment tool. Learners can speak into the app, and ML algorithms instantly evaluate their pro-
nunciation against native or ideal speech patterns.
• Pitch and Stress Analysis: The app meticulously analyses aspects such as pitch, stress, intona-
tion, and phonetic accuracy. It provides learners with feedback on these crucial elements of
pronunciation.
• Immediate Corrections: Learners receive instant feedback and suggested corrections. If a learner
mispronounces a word or phrase, the app offers guidance on how to improve.
• Adaptive Exercises: PronunCheck offers adaptive exercises to target specific pronunciation
challenges. Learners can focus on vowel sounds, consonant clusters, or other areas requiring
improvement.
• Voice Recognition: The app employs advanced voice recognition technology to accurately assess
spoken language. It adapts to various accents and speaking styles.
• Personalisation: The app personalises pronunciation exercises based on the learner’s individual
needs, accent, and progress, offering a tailored learning experience.
• Real Life Context: Pronunciation exercises and examples are presented in real-life contexts, such
as conversations and speeches, enhancing practical language skills.

203

Redefining Traditional Pedagogy

Grammar Checker

Beyond fill-in-the-blanks or sentence correction exercises, ML offers a more in-depth approach. Students
can input sentences, receiving feedback not only on errors but also suggestions and hints, moving from
mere correction to true understanding.

App Concept Outline: GrammaWise

Features and Functionality of an app to increase the interactivity of practising grammar are outlined below.

• Contextual Grammar Analysis: GrammaWise goes beyond traditional sentence correction exer-
cises. Learners can input sentences or passages, and the app provides detailed feedback on errors,
suggestions for improvements, and hints on grammar rules.
• Grammar Proficiency Assessment: The app assesses learners’ current grammar proficiency levels
through an initial assessment. It then customizes grammar exercises and feedback based on indi-
vidual needs.
• Hints and Explanations: GrammaWise offers hints and explanations alongside error corrections,
fostering a deeper understanding of grammar rules and usage.
• Interactive Exercises: Interactive exercises allow learners to practice applying grammar rules in
real-world sentences. These exercises adapt in difficulty as learners progress.
• Adaptive Learning Paths: The app adjusts the complexity of grammar exercises based on learners’
performance, ensuring continuous challenge and growth.
• Real Life Context: Grammar exercises are framed within real-life scenarios and contexts, such as
emails, conversations, and articles, providing practical language usage.

Reading Comprehension Enhancer

Traditional reading passages are complemented with questions. ML tools elevate this process: students
can interact with texts, receiving definitions, context, and even quizzes on-demand, enhancing depth
and breadth of understanding. Moreover, ML can facilitate interactive exercises within the reading ma-
terial. For instance, learners can answer comprehension questions, engage in discussions, or participate
in quizzes directly within the text. These interactive elements promote active engagement, reinforce
understanding, and enhance the overall learning experience.

App Concept Outline: ReadSmart

Features and Functionality of an app to increase the interactivity of reading comprehension are outlined
below.

• Interactive Reading Materials: ReadSmart offers a library of interactive reading materials en-
riched with ML-driven features. Learners can engage with texts in a dynamic and immersive way.
• On-Demand Definitions and Context: ML algorithms provide on-demand definitions and contex-
tual explanations. Learners can simply tap on a word or phrase to access its meaning and usage
in context.

204

Redefining Traditional Pedagogy

• Comprehension Quizzes: Within the text, learners can access comprehension quizzes tailored to
the content they are reading. These quizzes reinforce understanding and measure comprehension.
• Personalisation: ReadSmart personalises the reading experience by recommending texts and quiz-
zes based on the learner’s interests and reading level, facilitating a more engaging and effective
learning process.
• Real Life Application: Texts and reading materials include real-life scenarios, news articles, and
practical dialogues to help learners apply their comprehension skills in everyday situations.

Writing Assistant

Instead of waiting for teacher feedback on essays, ML provides an interactive platform for real-time
feedback on vocabulary, grammar, and coherence, refining the writing process as it unfolds.

App Concept Outline: WriteWise

Features and Functionality of an app to increase the interactivity of written mastery are outlined below.

• Real-Time Interactive Writing Platform: WriteWise offers a dynamic writing platform where
learners can compose essays, articles, and compositions. ML algorithms provide real-time feed-
back on vocabulary, grammar, coherence, and other writing aspects.
• Instant Feedback: As learners write, WriteWise offers instant feedback on vocabulary usage,
grammar errors, sentence structure, and coherence. Suggestions for improvements are provided
as they type.
• Grammar and Vocabulary Suggestions: ML algorithms identify and highlight grammar mistakes
and suggest alternative vocabulary choices to enhance writing quality.
• Coherence and Structure Analysis: WriteWise assesses the coherence and overall structure of the
text, offering suggestions for improving the flow and organization of ideas.
• Real-Time Editing Assistance: Learners can edit and revise their writing within the app, imple-
menting suggested changes with a simple click.
• Personalisation: WriteWise personaliwes feedback and suggestions based on the learner’s writing
style, skill level, and progress, offering a tailored writing improvement experience.
• Real Life Context: Writing prompts and exercises are based on real-life scenarios and contexts,
helping learners to apply their writing skills in practical situations.

Cultural Contextualiser

Moving beyond mere notes on cultural contexts, ML and Augmented Reality (AR) provide immersive
experiences. As learners engage with content, they can visualise and interact with cultural phenomena,
with ML offering real-time insights.

App Concept Outline: CultureConnect

Features and Functionality of an app to increase the interactivity of engaging with cultural concepts are
outlined below.

205

Redefining Traditional Pedagogy

• Immersive Cultural Experiences: CultureConnect provides learners with immersive experiences

that allow them to explore and interact with cultural phenomena associated with the language they
are studying.
• Augmented Reality Integration: The app integrates Augmented Reality to bring cultural elements
to life. Learners can use their device’s camera to visualize and interact with cultural objects, land-
marks, and events.
• Real-Time Cultural Insights: ML algorithms provide real-time insights and information about
the cultural elements learners encounter. This includes historical facts, cultural significance, and
contemporary relevance. By integrating real-life cultural scenarios, learners can better grasp the
practical application of cultural knowledge in real-world situations, enhancing their ability to
navigate and appreciate different cultures.
• Interactive Cultural Exercises: Within the cultural experiences, learners can engage in interactive
exercises such as quizzes, challenges, and discussions to deepen their cultural understanding.
• Personalisation: CultureConnect personalises the cultural learning experience by recommending
content and activities based on the learner’s interests, prior knowledge, and learning goals. This
feature ensures that each learner receives a customised experience that caters to their unique cul-
tural interests and educational needs.

These are merely some starting ideas on what could be created using ML to feature in the contemporary
language education classroom. As becomes evident, the examples all follow a similar formula, routed in
traditional activities featured in language learning. They aim to not fundamentally change what research
has shown to be conducive to a learner’s journey towards fluency. Instead, they extend static concepts
to incorporate modern tools, so that they can serve today’s learner better, both inside and outside the
classroom. The human educator stays at the forefront of connecting the learner with their target language.
The following section presents a high-level walkthrough of how a ML-powered app can be created.

FROM CONCEPT TO CREATION: CRAFTING ML-POWERED APPS

So, how might one convert these conceptual tools into tangible applications? It begins with ideation—
identifying gaps in traditional tools and envisioning how ML can bridge these. Once the concept is clear,
considerations of tools to use and data collection becomes pivotal; ML thrives on data. With a robust
dataset or adjacent technology in place, such as existing APIs, the design phase begins, considering user
experience and interface. Then comes the development phase, where ML algorithms are integrated.
Iterative testing ensures the app’s efficacy and user-friendliness. Throughout this process, feedback
loops are essential: from educators, learners, and tech experts. Lastly, once deployed, constant updates
and refinements ensure the tool’s relevance and impact. While technology is changing and evolving
quickly, the basic steps remain the same. Here, the chapter will use the example of an app the author
had built previously.

206

Redefining Traditional Pedagogy

TalkToMe: A Prototype Case Study

Recognising the ubiquitous issue of speaking in the classroom and the inherent limitations of traditional
classroom conversation dynamics, the author created a working prototype for a dedicated app, titled
“TalkToMe”1. The app was entered into the 2023 Streamlit hackathon and was one of the winners in its
technology category.

Problem Statement

Students, especially those new or returning to learning a language, frequently exhibit reluctance to vo-
calise their thoughts in the classroom. This hesitation is further accentuated by the traditional pedagogic
approach, where instructors, though well-intentioned, frequently interrupt students to provide immediate
feedback on their speech. While this technique has its merits, it does quite emulate real-world conversa-
tions where constant interruption is not only uncommon but often deemed rude (Kasper, 2006; Wong &
Waring, 2020). The need, therefore, was to devise an instrument where learners could simulate realistic
conversational scenarios and have control over the feedback they receive. This is not only related to the
level of corrections they obtain, but also related to how the bot response to them. In a purely auditory
context, it can often be challenging to not only understand what is being said, but to also learn new
vocabulary from the interaction. Creating an opportunity for students to add a form of subtitles to the
output to aid with comprehension and learning (Danan, 2004; Kanellopoulou, 2019).

Introducing TalkToMe

“TalkToMe” is a proposed language learning app designed to bridge the gap between classroom instruction
and real-world application. It embodies the principles of Dynamic Learning, offers Holistic Feedback,
and champions a Goal-Oriented approach. At its core, “TalkToMe” recognises the diverse needs of its
users, offering them the autonomy to tailor their learning experience.

Features of the App

Dynamic Learning: Instead of static revision modules, students have the option to integrate vocabulary
they are keen to practice, making their learning journey interactive and personal. This feature can help
students prepare for exams. In addition, it can aid learners in practicing for specific interactional concepts,
such as ordering in a restaurant, before they proceed with the conversation either in the classroom or in
a real-world environment (Van Dijk, 1977).
Figure 1 shows a screenshot of the app’s interface and highlights its features. These are further de-
scribed below. Note that the individual features are based on existing language learning pedagogy and
accompanying research.

• Holistic Feedback: Recognising the varied comfort levels among learners, “TalkToMe” offers a
unique feature that lets users select their desired feedback intensity. Whether they seek constant
guidance or periodic pointers, the choice is theirs (S. Li, 2010).

207

Redefining Traditional Pedagogy

Figure 1. Screenshot of TalkToMe’s user interface

208

Redefining Traditional Pedagogy

• Goal-Oriented Approach: With a focus on real-world applications, students can incorporate texts
or subjects they wish to discuss. Be it prepping for an academic presentation or an upcoming
exam, “TalkToMe” caters to these targeted needs. The implementation is deliberately flexible
to cater for students with diverse needs and language learning goals. While a similar concept to
choosing specific vocabulary to practice, being able to provide a target text as input allows stu-
dents to test their comprehension of the material and to anticipate questions when discussing the
text in the classroom (O’Malley et al., 1989).
• Visualisations: The app contains visual feedback for the learner. This includes a bar that counts
the words they have spoken during their session. It also visualises the individual turn length of
the utterances a learner produces. This can be an important part for students to move from simple
yes/no responses to confident and longer utterances (Seedhouse, 2004). Additional feedback is
provided on the most common words a learner is using to help them diversify their vocabulary
(Huttenlocher et al., 1991). It also provides visual feedback on how often a learner has used their
set vocabulary, so that they can keep track of how often they have practiced a word in context
(Sternberg, 2014; Webb, 2007).

Direct Application in a Classroom Setting

The versatility of “TalkToMe” ensures it is not just a tool for individual learners but also an asset in the
classroom. Educators can utilise it to complement their teaching methods, allowing students to practice
outside of class hours and come prepared, thus maximising classroom interactions. Students can upload
class materials to the app to practice and revise it. This allows students to create a learning environment
suitable for their own personal interests and aims. One feature that has not been mentioned so far is the
integration of general speaking tips and specific ideas for novel ways to utilise the app and to diversify
the user’s learning experience.

Building TalkToMe: Behind the Scenes

Constructing an app that seamlessly integrates language learning with AI might seem like a daunting
endeavour. But, with the right tools and a clear vision, it becomes a journey of connecting the dots.
Below, the author outlines the building blocks of “TalkToMe”, in creating an ML-powered app.

1. Choosing the Right Language: Python

“TalkToMe” was programmed in Python. Its extensive libraries for various aspects, including machine
learning and the supportive community make it a good choice for developing applications, especially
when working with AI.

2. Crafting the User Interface: Streamlit

One of the significant challenges when building an app is designing an intuitive and responsive user
interface. Streamlit is a free and open-source app framework based on React, but specifically crafted for
Python. It allowed to transform the Python scripts into interactive web applications without the added
complexities of web development.

209

Redefining Traditional Pedagogy

3. Conversing with the Machine: Integrating APIs

APIs, or Application Programming Interfaces, are like bridges connecting the app to vast reservoirs
of functionalities. For “TalkToMe”, several APIs were used to harness pre-built ML tools:

• AssemblyAI: Once a student records their speech, AssemblyAI translates this audio into text.
This “speech-to-text” capability is crucial as it translates human speech, with all its nuances, into
a format that machines can understand.
• OpenAI: To make the app conversational, OpenAI’s GPT-3.5 model is utilised. By sending cus-
tom prompts to OpenAI, the platform crafts coherent and contextually relevant responses. Think
of it like feeding a sentence to a knowledgeable assistant and receiving an insightful reply. The
model used is likely to be known to readers in OpenAI’s ChatGPT tool.
• Google’s TTS (Text-to-Speech): The conversation comes full circle with Google’s TTS. It trans-
lates the machine’s text response back into human-like speech, providing an auditory feedback to
the learner.

4. Budgetary Considerations: Building an app, especially one that relies on state-of-the-art technolo-
gies, might raise concerns regarding costs. While many tools and libraries available are free, some
specialised services, like certain APIs, come with associated costs. It’s essential to be mindful of
these expenses, especially when relying on third-party tools. Fortunately, many providers offer
tiered pricing or usage-based costs, allowing developers to scale their expenses based on actual
usage. While the app itself has been built keeping future scaling in mind, some of the functionalities
could be improved further by making more dedicated calls to the APIs at hand, or the integration
of other APIs. However, given that this project has not been further funded, a balance had to be
found to ensure that the app would be useable, while keeping costs down.

In essence, creating “TalkToMe” combines various technologies. But at its core, it is about sim-
plifying complex AI processes into an easy-to-use tool, making language learning more engaging and
effective for all.

Ethical Considerations in ML-Powered Education

The integration of machine learning (ML) into education, particularly in language learning, promises
significant benefits. However, with the great potential of ML also come profound ethical dilemmas that
must be carefully addressed. It is crucial that we approach this fusion of technology and education with
caution, responsibility, and ethical discernment (Paschal & Melly, 2023).
Figure 3 demonstrates the connection between value creation and constraints, including some of the
central ethical concerns. So far, the chapter has focused on the benefits that implementing ML applica-
tions into the classroom might bring. The following sections will focus on the constraints of the new
technology and provide some suggestions of how to navigate them.

210

Redefining Traditional Pedagogy

Figure 2. Technical flow of information through TalkToMe

Figure 3. Value and constraints of ML applications

211

Redefining Traditional Pedagogy

Data Privacy and Security

One of the foremost ethical concerns in ML-powered education is data privacy and security. As learners
engage with ML-driven language learning apps and platforms, their data, including personal informa-
tion and learning progress, is collected and processed. Protecting this data from breaches and ensuring
learners’ privacy is paramount (Kamarinou et al., 2017).
Suggestions:

Transparency: Educational institutions and app developers should be transparent about the data they
collect, how it is used, and who has access to it. Learners should have a clear understanding of
their data’s journey.
Consent: Learners should provide informed consent before their data is collected and processed. Consent
forms should be easily accessible and understandable.
Secure Storage: Data should be securely stored, encrypted, and protected from unauthorised access.
Regular security audits should be conducted to identify and rectify vulnerabilities.

Bias and Fairness

ML algorithms can inadvertently perpetuate biases present in training data. This bias can manifest in
the content, examples, or assessments provided to learners, affecting their language learning experience
and reinforcing stereotypes (Leavy et al., 2020; Lee, 2018).
Suggestions:

Diverse Training Data: Ensure that ML models are trained on diverse and representative datasets that
encompass various cultures, languages, and backgrounds to mitigate bias.
Bias Audits: Regularly assess ML algorithms for bias and take measures to correct it. Employ fairness-
aware techniques to reduce bias in recommendations and content.
Ethical Review Boards: Establish ethical review boards or committees to scrutinise the content and
recommendations provided by ML-powered systems for potential bias.

Accessibility

While ML can enhance language learning experiences, it may inadvertently create barriers for learners
with disabilities if not designed with accessibility in mind (Sahami, 1999).
Suggestions:

Universal Design: Ensure that ML-powered educational tools are designed with universal accessibility in
mind, incorporating features like screen readers, text-to-speech, and alternative navigation methods.
Accessibility Testing: Regularly test educational apps and platforms for accessibility with input from
users with disabilities to identify and address any shortcomings.

212

Redefining Traditional Pedagogy

Equity and Inclusivity

ML-powered language learning tools should not exacerbate existing disparities in education. There is
a risk that learners without access to advanced technology or high-speed internet may be left behind
(Lobel, 2022; Stephenson & Harvey, 2022).
Suggestions:

Equity Initiatives: Implement initiatives to provide access to ML-powered language learning tools for
underserved communities, including schools and learners in remote or low-income areas.
Low-Tech Alternatives: Develop low-tech or offline versions of ML-powered tools to ensure that learners
without high-speed internet can still benefit from technology-assisted language learning.

Ethical Use of AI Tutors

The use of AI-powered tutors in language learning raises ethical questions about the potential for learners
to become emotionally detached from the learning process or for AI tutors to replace human educators
entirely (Ifelebuegu et al., 2023).
Suggestions:

Complementing Human Teachers: Emphasise that AI tutors should complement human teachers, not
replace them. Human educators play a vital role in providing emotional support and personalized
guidance.
Ethical Guidelines: Develop and adhere to ethical guidelines for the use of AI tutors, including limita-
tions on the emotional involvement of learners with AI entities.

In conclusion, the integration of ML in language education is a double-edged sword. While it holds

immense promise, it also presents ethical challenges that require careful consideration. To harness the
full potential of ML while upholding ethical standards, educators, developers, policymakers, and learners
must work together to establish clear guidelines, promote transparency, and prioritise the well-being,
privacy, and inclusivity of all learners. By doing so, it can be ensured that the fusion of technology and
education serves as a force for positive transformation in language learning.

SOLUTIONS AND RECOMMENDATIONS

The digital age brings with it boundless potential to redefine the landscape of language education. Edu-
cators, technologists, and lifelong learners, stand at the crossroads of pedagogy and technology, seeking
the best way to bridge the two realms. This chapter has underscored the transformative potential that
machine learning brings to language education. From adaptive learning experiences to real-time feed-
back, the promise is undeniable. But with great potential comes the imperative to exercise caution and
educators should remain mindful of the challenges and navigate them with foresight.
The main recommendation for this chapter is the encouragement of collaborations between educators
and ML experts. The integration of ML into language education goes beyond algorithms and datasets; it
embodies a shared vision where technologists appreciate the nuances of language pedagogy, and educators

213

Redefining Traditional Pedagogy

comprehend the capabilities and limitations of ML. Collaborative workshops, joint research endeavours
and interdisciplinary projects serve as vehicles for fostering this inclusive approach, ensuring that ML-
powered language learning solutions genuinely meet educational needs while avoiding potential pitfalls.

FUTURE DIRECTIONS

This chapter has shown some of the potential for integrating technology, especially ML into the tradi-
tional language learning classroom to present one possible vision of a technologically enhanced language
learning future:

• Personalised Learning Journeys: The idea that language learners can embark on a journey tailored
specifically to their needs, where learning pace, content, and feedback adapt in real-time based on
learner inputs and performance has been a central point in this chapter.
• Bridging the Gap: With the confluence of pedagogy and technology, the divide between tradition-
al teaching methods and the technological potential diminishes. Future classrooms might seam-
lessly blend face-to-face interactions with digital experiences, ensuring learners get the best of
both worlds.
• Embracing the Global Village: As technology breaks down barriers, language learners can engage
in authentic, culturally rich experiences, virtually traveling to distant lands, interacting with native
speakers, and immersing themselves in foreign cultures, all from the comfort of their classrooms
or homes.

In conclusion, while the path to integrating ML into language education comes with challenges, the
potential should guide the development. By fostering collaborations, maintaining an ethical stance, and
keeping the learners’ needs at the centre of future pedagogies, practitioners and researchers can craft a
future where technology and pedagogy harmoniously work together, creating opportunities for language
learning experiences fit for the twenty-first century.

CONCLUSION

This chapter has aimed to show the profound transformative potential of machine learning. It explored
just some of the myriad ways in which this dynamic technology can augment traditional teaching meth-
ods, making learning more adaptive, interactive, and engaging.
It was shown that a potential evolution of language education is not just about integrating the latest
technological advancements; it is about reshaping our pedagogical approaches to fully leverage these
tools. Machine learning, with its capability to process vast amounts of data and provide personalised
experiences, promises a future where every learner can have a tailored educational journey. However,
with great power comes great responsibility. The integration of ML into classrooms needs to ensure that
it enhances rather than hampers the learning experience. It is vital to consider the ethical implications,
the challenges of maintaining academic integrity, and the importance of ensuring that technology serves
as an aid, not a crutch.

214

Redefining Traditional Pedagogy

Thus, this chapter concludes with a call to action for educators, technologists, policymakers, and
learners alike. The future of language education is not preordained. It is ready for a holistic evolution,
where pedagogical methods and technological innovations converge harmoniously. The aim is to strive
for a future where technology not only complements but elevates the human touch, making language
learning more meaningful, accessible, and effective for all. In the end, the goal remains unchanged: to
equip learners with the tools and skills they need to navigate our interconnected world confidently.

REFERENCES

Arnó-Macià, E., & Barés, G. M. (2015). The Role of Content and Language in Content and Language
Integrated Learning (CLIL) at University: Challenges and Implications for ESP. English for Specific
Purposes, 37, 63–73. Advance online publication. doi:10.1016/j.esp.2014.06.007
Asiksoy, G. (2018). ELT students’ attitudes and awareness towards the use of Web 2.0 technologies for
language learning. Journal of Language and Linguistic Studies, 14(2), 240–251.
Baidoo-Anu, D., & Ansah, L. O. (2023). Education in the era of generative artificial intelligence (AI):
Understanding the potential benefits of ChatGPT in promoting teaching and learning. Journal of AI,
7(1), 52–62. doi:10.61969/jai.1337500
Baskara, R. (2023). Exploring the implications of ChatGPT for language learning in higher education.
Indonesian Journal of English Language Teaching and Applied Linguistics, 7(2), 343–358.
Bonner, E., Lege, R., & Frazier, E. (2023). Large language model-based artificial intelligence in the
language classroom: Practical ideas for teaching. Teaching English with Technology, 23(1).
Bozkurt, A. (2023). Generative artificial intelligence (AI) powered conversational educational agents:
The inevitable paradigm shift. Asian Journal of Distance Education, 18(1).
Brena, R. F., Zuvirie, E., Preciado, A., Valdiviezo, A., Gonzalez-Mendoza, M., & Zozaya-Gorostiza, C.
(2021). Automated evaluation of foreign language speaking performance with machine learning. [IJI-
DeM]. International Journal on Interactive Design and Manufacturing, 15(2–3), 317–331. doi:10.1007/
s12008-021-00759-z
Briggs, N. (2018). Neural Machine Translation Tools in the Language Learning Classroom: Students’
Use, Perceptions, and Analyses. The JALT CALL Journal, 14(1), 3–24. Advance online publication.
doi:10.29140/jaltcall.v14n1.221
Chen, X., Zou, D., Xie, H., & Cheng, G. (2021). Twenty years of personalized language learning. Journal
of Educational Technology & Society, 24(1), 205–222.
Dalton‐Puffer, C. (2011). Content-and-Language Integrated Learning: From Practice to Principles? Annual
Review of Applied Linguistics, 31, 182–204. Advance online publication. doi:10.1017/S0267190511000092
Danan, M. (2004). Captioning and subtitling: Undervalued language learning strategies. Meta, 49(1),
67–77. doi:10.7202/009021ar

215

Redefining Traditional Pedagogy

Dooly, M. (2023). Moving Back into the Classroom while Moving beyond Current Paradigms: Lessons
for Post-Covid Language Education. Technology-Enhanced Language Teaching and Learning: Lessons
from the Covid-19 Pandemic, 213.
Ehara, Y. (2023). Innovative Software to Efficiently Learn English Through Extensive Reading and
Personalized Vocabulary Acquisition. Academic Press.
Gilakjani, A. P. (2012). The significant role of multimedia in motivating EFL learners’ interest in Eng-
lish language learning. International Journal of Modern Education and Computer Science, 4(4), 57–66.
doi:10.5815/ijmecs.2012.04.08
Gilmore, A. (2007). Authentic materials and authenticity in foreign language learning. Language Teach-
ing, 40(2), 97–118. doi:10.1017/S0261444807004144
Ginn, J., Salas, C. B., Barlowe, S., & Lehman, W. (2021). A novel framework for integrating mobile ma-
chine learning and L2 vocabulary acquisition. Journal of Computing Sciences in Colleges, 36(5), 47–56.
Hassan Taj, I., Ali, F., Sipra, M., & Ahmad, W. (2017). Effect of technology enhanced language learning
on EFL reading comprehension at tertiary level. Arab World English Journal, 8.
Heil, C. R., Wu, J. S., Lee, J. J., & Schmidt, T. (2016). A review of mobile language learning applica-
tions: Trends, challenges, and opportunities. The EuroCALL Review, 24(2), 32–50. doi:10.4995/euro-
call.2016.6402
Hejazi, S. Y., & Sadoughi, M. (2023). How does teacher support contribute to learners’ grit? The role
of learning enjoyment. Innovation in Language Learning and Teaching, 17(3), 593–606. doi:10.1080/
17501229.2022.2098961
Hodges, C. B., Moore, S., Lockee, B. B., Trust, T., & Bond, M. A. (2020). The difference between
emergency remote teaching and online learning. Academic Press.
Hopkins, E. (2022). Machine learning tools, algorithms, and techniques. Journal of Self-Governance
and Management Economics, 10(1), 43–55.
Hussherr, F.-X., & Hussherr, C. (2017). Construire le modèle éducatif du 21e siècle-Les promesses de
la digitalisation et les nouveaux modes d’apprentissage. FYP éditions.
Huttenlocher, J., Haight, W., Bryk, A., Seltzer, M., & Lyons, T. (1991). Early vocabulary growth: Relation
to language input and gender. Developmental Psychology, 27(2), 236–248. doi:10.1037/0012-1649.27.2.236
Ifelebuegu, A. O., Kulume, P., & Cherukut, P. (2023). Chatbots and AI in Education (AIEd) tools: The
good, the bad, and the ugly. Journal of Applied Learning and Teaching, 6(2).
Ironsi, C. S. (2022). Navigating learners towards technology-enhanced learning during post COV-
ID-19 semesters. Trends in Neuroscience and Education, 29, 100189. doi:10.1016/j.tine.2022.100189
PMID:36470617
Jatzlau, S., Michaeli, T., Seegerer, S., & Romeike, R. (2019). It’s not magic after all–machine learning
in snap! Using reinforcement learning. Academic Press.

216

Redefining Traditional Pedagogy

Jeon, J., & Lee, S. (2023). Large language models in education: A focus on the complementary relation-
ship between human teachers and ChatGPT. Education and Information Technologies, 28(12), 1–20.
doi:10.1007/s10639-023-11834-1 PMID:37361830
Jiang, X., Rollinson, J., Plonsky, L., Gustafson, E., & Pajak, B. (2021). Evaluating the reading and
listening outcomes of beginning‐level Duolingo courses. Foreign Language Annals, 54(4), 974–1002.
doi:10.1111/flan.12600
Kamarinou, D., Millard, C., Singh, J., & Leenes, R. (2017). Machine learning with personal data. In
Data protection and privacy: The age of intelligent machines. Hart Publishing.
Kanellopoulou, C. (2019). Film subtitles as a successful vocabulary learning tool. Open Journal of
Modern Linguistics, 9(02), 145–152. doi:10.4236/ojml.2019.92014
Kasper, G. (2006). Beyond Repair: Conversation Analysis as an Approach to SLA. AILA Review, 19,
83–99. doi:10.1075/aila.19.07kas
Kharb, L., & Singh, P. (2021). Role of machine learning in modern education and teaching. In Impact of
AI Technologies on Teaching, Learning, and Research in Higher Education (pp. 99–123). IGI Global.
doi:10.4018/978-1-7998-4763-2.ch006
Kim, D.-E., Hong, C., & Kim, W. H. (2023). Efficient Transformer-based Knowledge Tracing for a
Personalized Language Education Application. Academic Press.
Klimova, B. (2021). An insight into online foreign language learning and teaching in the era of CO-
VID-19 pandemic. Procedia Computer Science, 192, 1787–1794. doi:10.1016/j.procs.2021.08.183
PMID:34630743
Kolovou, T. A. (2021). Recreating Cultural Immersion in an Online Environment. Journal of Teaching
and Learning with Technology, 10, 408–413.
Korkmaz, G., & Toraman, Ç. (2020). Are we ready for the post-COVID-19 educational practice? An
investigation into what educators think as to online learning. International Journal of Technology in
Education and Science, 4(4), 293–309. doi:10.46328/ijtes.v4i4.110
Lai, Y., Saab, N., & Admiraal, W. (2022). University students’ use of mobile technology in self-directed
language learning: Using the integrative model of behavior prediction. Computers & Education, 179,
104413. doi:10.1016/j.compedu.2021.104413
Leavy, S., Meaney, G., Wade, K., & Greene, D. (2020). Mitigating gender bias in machine learning data
sets. Bias and Social Aspects in Search and Recommendation: First International Workshop, BIAS 2020,
Lisbon, Portugal, April 14. Proceedings, 1, 12–26.
Lee, N. T. (2018). Detecting racial bias in algorithms and machine learning. Journal of Information.
Communication and Ethics in Society, 16(3), 252–260. doi:10.1108/JICES-06-2018-0056
Lew, R. (2004). Which dictionary for whom? Receptive use of bilingual, monolingual and semi-bilingual
dictionaries by Polish learners of English. Robert Lew.

217

Redefining Traditional Pedagogy

Li, S. (2010). The effectiveness of corrective feedback in SLA: A meta‐analysis. Language Learning,
60(2), 309–365. doi:10.1111/j.1467-9922.2010.00561.x
Li, W., Zhang, H., Zhang, C., Luo, J., Wang, H., Wang, H., Zhu, Y., Cui, H., Wang, J., Li, H., Zhu, Z.,
Xu, Y., & Li, C. (2021). The Prevalence of Psychological Status During the COVID-19 Epidemic in
China: A Systemic Review and Meta-Analysis. Frontiers in Psychology, 12, 614964. Advance online
publication. doi:10.3389/fpsyg.2021.614964 PMID:34017278
Liu, Y., & Quan, Q. (2022). AI recognition method of pronunciation errors in oral English speech with
the help of big data for personalized learning. Journal of Information & Knowledge Management,
21(Supp02), 2240028. doi:10.1142/S0219649222400287
Lobel, O. (2022). The equality machine: Harnessing digital technology for a brighter, more inclusive
future. Hachette UK.
Lochtman, K. (2002). Oral corrective feedback in the foreign language classroom: How it affects inter-
action in analytic foreign language teaching. International Journal of Educational Research, 37(3–4),
271–283. doi:10.1016/S0883-0355(03)00005-3
Misiejuk, K., Ness, I. J., Gray, R. M., & Wasson, B. (2023). Changes in Online Course Designs: Be-
fore, During, and After the Pandemic. Frontiers in Education, 7, 996006. Advance online publication.
doi:10.3389/feduc.2022.996006
Moser, K. M., Wei, T., & Brenner, D. (2021). Remote teaching during COVID-19: Implications from a
national survey of language educators. System, 97, 102431. doi:10.1016/j.system.2020.102431
Nikitina, L. (2011). Creating an authentic learning environment in the foreign language classroom.
International Journal of Instruction, 4(1).
O’Malley, J. M., Chamot, A. U., & Küpper, L. (1989). Listening comprehension strategies in second
language acquisition. Applied Linguistics, 10(4), 418–437. doi:10.1093/applin/10.4.418
Paribakht, T. S., & Wesche, M. (1997). Vocabulary enhancement activities and reading for meaning
in second language vocabulary acquisition. Second Language Vocabulary Acquisition: A Rationale for
Pedagogy, 55(4), 174–200.
Paschal, M. J., & Melly, I. K. (2023). Ethical Guidelines on the Use of AI in Education. In Creative AI
Tools and Ethical Implications in Teaching and Learning (pp. 230–245). IGI Global. doi:10.4018/979-
8-3693-0205-7.ch013
Pérez-Núñez, A. (2023). Exploring the Potential of Generative AI (ChatGPT) for Foreign Language
Instruction: Applications and Challenges. Hispania, 106(3), 355–362. doi:10.1353/hpn.2023.a906568
Pikhart, M. (2020). Intelligent information processing for language education: The use of artificial
intelligence in language learning apps. Procedia Computer Science, 176, 1412–1419. doi:10.1016/j.
procs.2020.09.151 PMID:33042299
Piotrowska, M., Czyżewski, A., Ciszewski, T., Korvel, G., Kurowski, A., & Kostek, B. (2021). Evalu-
ation of aspiration problems in L2 English pronunciation employing machine learning. The Journal of
the Acoustical Society of America, 150(1), 120–132. doi:10.1121/10.0005480 PMID:34340465

218

Redefining Traditional Pedagogy

Preis, R., Bećirović, S., & Geyer, B. (2023). EFL Teaching in a Digital Environment. Map Education
and Humanities. doi:10.53880/2744-2373.2023.3.1.56
Pujiani, T., Sukmawati, I. D., & Indrasari, N. (2022). Teachers’ Readiness Toward the New Paradigm
of English Language Teaching: A Narrative Inquiry. Uc Journal Elt Linguistics and Literature Journal.
doi:10.24071/uc.v3i2.5363
Radić, N., Atabekova, A., Freddi, M., & Schmied, J. (2021). The world universities’ response to CO-
VID-19: Remote online language teaching. Research-publishing. net.
Ryan, J., & Viete, R. (2009). Respectful interactions: Learning with international students in the English-
speaking academy. Teaching in Higher Education, 14(3), 303–314. doi:10.1080/13562510902898866
Sahami, M. (1999). Using machine learning to improve information access. Stanford University.
Sari, S. N., & Aminatun, D. (2021). Students’ perception on the use of English movies to improve
vocabulary mastery. Journal of English Language Teaching and Learning, 2(1), 16–22. doi:10.33365/
jeltl.v2i1.757
Seedhouse, P. (2004). The organization of turn taking and sequence in language classrooms. Language
Learning: A Journal of Research in Language Studies.
Selwyn, N. (2019). Should robots replace teachers? AI and the future of education. John Wiley & Sons.
Shadiev, R., Liu, T., & Hwang, W. (2020). Review of research on mobile‐assisted language learn-
ing in familiar, authentic environments. British Journal of Educational Technology, 51(3), 709–720.
doi:10.1111/bjet.12839
Shortt, M., Tilak, S., Kuznetcova, I., Martens, B., & Akinkuolie, B. (2023). Gamification in mobile-
assisted language learning: A systematic review of Duolingo literature from public release of 2012 to
early 2020. Computer Assisted Language Learning, 36(3), 517–554. doi:10.1080/09588221.2021.1933540
Shumin, K. (2002). Factors to consider: Developing adult EFL students’ speaking abilities. Meth-
odology in Language Teaching: An Anthology of Current Practice, 12(35), 204–211. doi:10.1017/
CBO9780511667190.028
Stephenson, B., & Harvey, A. (2022). Student equity in the age of AI-enabled assessment: Towards
a politics of inclusion. In Assessment for Inclusion in Higher Education (pp. 120–130). Routledge.
doi:10.4324/9781003293101-14
Sternberg, R. J. (2014). Most vocabulary is learned from context. In The nature of vocabulary acquisi-
tion (pp. 89–105). Psychology Press.
Su, J., & Yang, W. (2023). Unlocking the power of ChatGPT: A framework for applying generative AI
in education. ECNU Review of Education.
Suresh, A., Jacobs, J., Lai, V., Tan, C., Ward, W., Martin, J. H., & Sumner, T. (2021). Using transformers
to provide teachers with personalized feedback on their classroom discourse: The TalkMoves application.
arXiv Preprint arXiv:2105.07949.

219

Redefining Traditional Pedagogy

Sutton, R. S., & Barto, A. (1998). Reinforcement Learning: An Introduction. IEEE Transactions on
Neural Networks, 9(5), 1054. Advance online publication. doi:10.1109/TNN.1998.712192
Toquero, C. M. D. (2020). Challenges and Opportunities for Higher Education Amid the COVID-19
Pandemic: The Philippine Context. Pedagogical Research. doi:10.29333/pr/7947
Tumbal, S., Liando, N. V., & Olii, S. T. (2021). Students’ perceptions toward the use of Google Translate
in translating. Kompetensi, 1(02), 313–320. doi:10.53682/kompetensi.v1i02.1853
Ünal, E., & Güngör, F. (2021). The continuance intention of users toward mobile assisted language
learning: The case of DuoLingo. Asian Journal of Distance Education, 16(2).
Van Dijk, T. A. (1977). Context and cognition: Knowledge frames and speech act comprehension. Journal
of Pragmatics, 1(3), 211–231. doi:10.1016/0378-2166(77)90035-2
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin,
I. (2017). Attention Is All You Need. https://doi.org//arxiv.1706.03762 doi:10.48550
Warschauer, M., & Healey, D. (1998). Computers and language learning: An overview. Language Teach-
ing, 31(2), 57–71. doi:10.1017/S0261444800012970
Webb, S. (2007). The effects of repetition on vocabulary knowledge. Applied Linguistics, 28(1), 46–65.
doi:10.1093/applin/aml048
Wong, J., & Waring, H. Z. (2020). Conversation analysis and second language pedagogy: A guide for
ESL/EFL teachers. Routledge. https://books.google.com/books?hl=en&lr=&id=fybxDwAAQBAJ&
oi=fnd&pg=PP11&dq=conversation+analysis+language+teaching+correction&ots=5gbus7JfWb&s
ig=-mgbXRuvOTp4vHDNcMaVDgQTAcs
Zou, D., Xie, H., & Wang, F. L. (2018). Future trends and research issues of technology-enhanced lan-
guage learning: A technological perspective. Knowledge Management & E-Learning, 10(4), 426–440.

KEY TERMS AND DEFINITIONS

Application, App: Here, computer or software application. A computer program to carry out a
specific task for a specific purpose. Designed for an end user.
Application Programming Interface (API): A software service that allows two programmes to
transmit data between each other. Allows to access other company’s data or software to enhance func-
tionality and features in another app without having to create it from scratch.
Deployment: Here: software deployment. Activities that make software available to use on a device.
Low and no code environments often have integrated deployment solutions. Other free services include
Netlify and Heroku.
Generative AI: A subset of artificial intelligence (AI) that focuses on developing models and algo-
rithms capable of generating content, such as text, images, or even videos, in a way that appears to be
created by humans.
Graphical User Interface (GUI): A form of user interface using graphical icons and menus.

220

Redefining Traditional Pedagogy

Large Language Models (LLM): Advanced machine learning models that are particularly designed
for natural language understanding and generation tasks.
Machine Learning (ML): Computer algorithms which improve through the use of data, without
following explicit instructions. Part of artificial intelligence.
Natural Language Processing (NLP): A subfield of artificial intelligence (AI) that focuses on
enabling computers to understand, interpret, and generate human language. NLP involves tasks such as
language translation, sentiment analysis, and speech recognition.

ENDNOTE
1
The app can be accessed here: https://talktomelanguagelearning.streamlit.app/

221
222

Chapter 11
Creating Stories:
Generative Artificial Intelligence
Tools as Writing Tutors

Franziska Lys
https://orcid.org/0000-0001-8979-5601
Northwestern University, USA

ABSTRACT
This chapter focuses on examining the strengths and limitations of prompt-driven ChatGPT for a cre-
ative writing task using German as a foreign language. College students of German at the advanced
level were asked to develop, write, and illustrate a unique children’s story using ChatGPT as a thinking
partner. Interacting with ChatGPT in German, students engaged in informal and low-stakes writing-
to-learn activities that could help them think through ideas and key concepts for their stories, as well
as learn new vocabulary, expressions, and language patterns. Answering to learner-produced prompts,
ChatGPT provided both explicit and implicit learning situations that focused on vocabulary develop-
ment and grammar in a meaning-focused context, creating conditions in which learners could learn
according to their current language proficiency. The author discusses how they set up the project, what
tasks and prompts they used to elicit content, and how they prepared illustrations using an artificial
intelligence image generator.

Writing is an important and necessary skill to communicate with others effectively. It can be challenging,
however, to be able to express oneself accurately and convincingly, especially for learners of a second
or foreign language. Achieving a high level of proficiency, that is, effectiveness of meaning, structure,
tone, and mood of one’s writing, presupposes a good understanding of grammatical features as well as
a large vocabulary. The question of how to best help a group of college students learning German at
a university in the Midwest in the U.S. improve their writing and grammar skills surfaced during the
preparation of one of the author’s latest teaching assignments, a class on advanced German grammar.
The author had taught this course before, using a grammar book for speakers at the C1 level. Although
students seemed to be satisfied with the course material and grammar assignments and thought they had

DOI: 10.4018/979-8-3693-0872-1.ch011

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

Creating Stories

learned a reasonable amount, in-class writing tasks, homework assignments, and quiz results suggested
otherwise. Overall, students were able to solve grammar exercises such as fill-in-the-blanks and short
rewrites when presented with rules and examples but failed to use or understand the same structures in
more contextualized and meaning-driven contexts. For example, students were able to fill in past tense
forms in prepared sentences, but unable to explain the usage and meaning of the following verb forms
found in a children’s book Die Kleine Hexe: Ausflug mit Abraxas (Preussler et al., 2017):

• Das hätte ihm höchstens die kleine Hexe erklären können. Aber die hatte sich längst mit Abraxas
davongeschlichen (Only the little witch could have explained that to him. But she had long since
sneaked away with Abraxas).
• Als sie auch noch ihren Besen Purzelbäume schlagen ließ, unterbrach sie Abraxas (As she was
also making her broom do somersaults, Abraxas interrupted her).

A further conundrum concerned the grammar points to present and practice. As experience had
shown, many of the explanations and exercises that the grammar book offered were beyond students’
active language use. The students could translate expressions such as angesichts des schlechten Wetters
(given the bad weather), kraft ihres Amtes (by virtue of their office), ungeachtet der Warnungen (regard-
less of the warnings), as well as reflexive verbs such as sich ins Zeug legen (to do your best) and they
could also use these expressions in full sentences, but they could not use them clearly and correctly in
different contexts. Similarly, most students struggled to see the relevance to their learning of sentences
such as the ones below, either because of the complexity of the grammar (subjunctive and passive) or
the strange context:

• Wenn die Deiche nicht ausgebaut worden wären, hätte es zu grösseren Überschwemmungen kom-
men können (If the dikes had not been expanded, major flooding could have occurred).
• Je mehr Schokolade eine Frau ißt, je besser ist sie vor Schlaganfällen geschützt (The more choco-
late a woman eats, the better protected she is against strokes).

Chavez (2016, 2017) investigated what grammar points college learners of German (1st through 4th
year) found to be the most difficult to learn as well as the least relevant for self-expression. Third-year
college learners of German listed adjective endings and noun gender as the most difficult, and fourth-year
college learners mentioned cases, noun gender, and adjective endings. The forms third-year learners listed
as the least relevant for self-expression for them were passive and subjunctive. Some of the reasons the
students gave for the abovementioned difficulties were the complexity and opacity of rules, the number
of rules, and the infrequent occurrence of certain forms in the material they encountered. There was a
disconnect between what the grammar book provided (i.e., the forms that the book’s author felt needed
to be practiced as well as how to practice them) and what the learners perceived as difficult and worthy
of reviewing and practicing.
In order to provide a more engaging and effective learning environment, the author added a task-
based writing project that involved the creative use of ChatGPT (https://chat.openai.com) to the class
syllabus: The instructor asked the students to develop, write, and illustrate a unique children’s story
using ChatGPT as a thinking partner. Interacting with ChatGPT in German via its Web-based interface,
the students developed their story by weaving together ChatGPT’s suggestions to text prompts eliciting
cultural and linguistic information. The instructor chose a task-based approach because of its focus on

223

Creating Stories

meaning and form, which presents language in context and promotes incidental grammar and vocabulary
learning. Prewriting learning tasks included the reading and analysis of a set of children’s books to pres-
ent new vocabulary and language forms in context and occasional explicit grammar lessons followed
by structural exercises.
In this chapter, the author discusses ChatGPT’s potential as an innovative learning and teaching tool
for students of German as a second language. The goal of the project is to provide a better understand-
ing of the issues involved, to uncover the strengths and limitations of prompt-driven uses of ChatGPT
for developing writing in a foreign language including the development of grammar, and to design a
roadmap for instructors on the most effective use and integration of ChatGPT. The chapter is structured
as follows: The background section provides an overview of the theoretical and pedagogical underpin-
nings of the project, such as explicit and implicit learning, and explains how writing-to-learn tasks can
potentially improve language learning. Furthermore, the section presents the pedagogical implications
of reading and analyzing children’s books as a precursor or preparatory task to the writing of the stu-
dents’ own stories. The methodology section provides information on how the author set up the project,
the participants in the project, and the material the author collected to evaluate the use of ChatGPT.
The author adopted an explorative approach to evaluate the effectiveness of ChatGPT. The researcher
collected qualitative data from observations, unstructured focus group discussions, personal interviews
with students, and the analysis of ChatGPT’s discussion protocols. The discussion and implementation
section illustrates the author’s findings and offers suggestions on how to best integrate ChatGPT to
ensure a successful experience.

BACKGROUND

Theoretical Underpinnings

Grammar knowledge is important for language learners to improve proficiency, but how grammar learn-
ing fits into the overall learning of a second language is an unresolved question. Some language learners
find studying and memorizing grammar rules and doing isolated skill drills frustrating and exhausting
since they often fail to improve meaning-focused writing or speaking skills. Other learners, however,
think of it as giving reassurance that their writing or speaking will become clear and effective. Research
has shown that it is not uncommon for students and instructors to have mixed feelings about grammar
instruction. Several study results (Incecay & Dollar, 2011; Jean & Simard, 2011; Loewen et al., 2009)
have shown that instructors and students perceive grammar as important and necessary to improve
language proficiency, but, at the same time, not as something desirable and enjoyable. They considered
communicative activities, authentic materials, and real-world tasks as more effective and sought-after
learning activities. This makes teaching grammar unnecessarily complex.
In this section, the author elaborates on two theoretical underpinnings that support the incorporation of
ChatGPT-driven learning tasks as described in this chapter. First, the author will highlight the distinction
between explicit and implicit learning and how focus on form (FonF) can support incidental learning and
promote the acquisition of grammar (Pouresmaeil & Vali, 2023). Task-based language teaching as an
effective, form-focused, learner-centered, and experiential approach that fosters language use in meaning-
ful contexts is within this framework (Byrnes & Manchón, 2014; East, 2015). Second, while writing (or
learning-to-write) is often seen as an assessment tool to ascertain how well language has been learned,

224

Creating Stories

writing-to-learn tasks can play a facilitative role for language acquisition, as the relatively slow-paced
activity and the resulting written record encourage increased reflection and monitoring (Williams, 2012).

Explicit or Implicit Grammar Teaching and Focus on Form

The question of how best to teach grammar plays a central role in the field of second language teach-
ing. The distinction between explicit teaching of grammar, in which the learner is taught grammar rules
and explanations, and implicit teaching of grammar, where learning happens experientially through
meaning-focused communications in the target language, is important and has drawn much attention
in the literature (Basturkmen, 2023). There is ample debate on these two approaches and how much
explicit or implicit grammar teaching contributes to the overall language proficiency, and the results
are mixed. For example, after synthesizing much of the research on explicit instruction over the last 35
years, Leow (2019) concluded that explicit instruction was better than implicit instruction. Sok et al.
(2019), on the other hand, found little difference between the success of explicit and implicit grammar
teaching, except that implicit teaching had a longer-lasting effect. Lys (2013a) reported the results of a
year-long empirical investigation of the effectiveness of extended explicit grammar practice (i.e., grammar
explanations and controlled exercises) on the overall language development of learners of German. Her
results suggested that prolonged grammar practice on discrete grammar items translated into higher gain
scores on quiz questions (i.e., explicit knowledge), but did not influence the quality of two open-ended
meaning-focused tasks (i.e., implicit knowledge). In a follow-up study, Lys (2013b) investigated how
the use of meaningful, purposeful, and goal-directed discourse affected the development of students’
oral proficiency. In this empirical study, students were asked to chat once a week with a partner online
on a variety of cultural topics and then record a short video containing spontaneous reactions to a set
of questions on the topic. The results showed that, despite the lack of explicit grammar instruction, the
language students produced in the videos became more complex as learners gained more experience
using their L2 in the meaning-focused chats. The learner-centered and task-based language learning
approach facilitated interactions and provided scaffolded assistance.
Ellis (2009) suggested that a more nuanced understanding of explicit and implicit learning may be
helpful and that some degree of attention to form may be necessary for learners to develop high levels
of proficiency. First introduced by Long (1991), and cited by Ellis (2016), two forms of attention have
received considerable recognition in the literature: Focus on forms (FonFs) and FonF. Ellis pointed out
that the understanding of these terms has considerably changed since they were first introduced, and he
uses the terms not to describe teaching approaches, but different teaching techniques:

Focus on form entails various techniques designed to attract learners’ attention to form while they are
using the L2 as a tool for communicating. In contrast, focus on forms entails various devices (such as
“exercises”) designed to direct learners’ attention to specific forms that are to be studied and learned
as objects. (Ellis, 2016, p. 409)

Given the need for a communicative context, FonF can successfully be introduced in task-based learn-
ing where the focus is on meaning and form. While there are proponents of both forms of teaching, Ellis
(2016) points out that current research has not been able to tease out which approach is more effective.
However, some data suggest, according to Ellis (2016), that FonF interactions are more meaningful
and result in incidental acquisition of language, especially through implicit corrective feedback such as

225

Creating Stories

recasts. Pouresmaeil and Vali (2023) reviewed several studies on the effectiveness of incidental FonF
and concluded that incidental FonF facilitates the development of learners’ new language, and that this
technique may benefit learners with a higher level of proficiency more than learners with a lower level
of proficiency. The results of their study revealed that incidental FonF helped develop learners’ language
knowledge across different linguistic categories, including vocabulary, pronunciation, and grammar.

Writing-to-Learn Activities

In many teaching environments, writing in a foreign language largely serves as a tool for instructors to
assess the quality of student writing, often a final product of a class. While writing is a very complex
process that encompasses “cognitive and linguistic processes and resources, conscious problem solving,
and efficient self-regulation strategies” (Kormos, 2023, p. 622), it can also play a facilitative role in learn-
ing a language, as the relatively slow-paced task and the resulting written record encourage increased
reflection and monitoring, as well as thinking through evaluative feedback (Williams, 2012). As such,
writing is understood as a tool to promote learning, hence the term “writing-to-learn.” Proponents of
writing-to-learn activities believe in the process of writing and not in the outcome. For them, composing
and producing a text opens various avenues for exploration and critical reflection on the content as well
as on the language used, and such explorations foster critical thinking and learning (Chmarkh, 2021). The
idea that writing promotes learning is not new, as Langer and Applebee had already described it in 1987:
“There is clear evidence that activities involving writing lead to better learning than activities involving
reading and studying only. Writing assists learning” (as cited in Chmarkh, 2021, p. 92). However, research
into writing-to-learn practices, in which researchers looked for effective strategies that make use of the
unique properties of writing to help learning, has only recently figured prominently in the literature,
and many of the processes are not clearly understood yet. Summarizing the results of empirical research
on the concept and practice of writing-to-learn research between 2004 and 2019, Chmarkh’s (2021)
concludes that “… implementing writing to learn tasks result in notable learning benefits in language
and content area classrooms” (p. 93) and therefore should be included as a possible learning strategy:
“Informal, ungraded, writing activities such as learning journals, reflections, and online discussions are
viable avenues for students not only to negotiate and construct their understanding of content but also
to develop their critical thinking skills” (p. 93).

Task Design

Reading as a Prewriting Task

The importance of reading for the development of writing is well established, whether it is in the native
language or in a second language. The more people read, the more familiar they become with the structure
of a text, the development of a character, the description of a setting, unfamiliar words and expressions,
and different writing styles. In the author’s class, the students read several German children’s books dur-
ing the first five weeks of the quarter as a prewriting exploration: The students learned how to analyze
children’s stories by discussing topics, themes, characters, and storylines, as well as the language used.
These texts served as models and inspirations for the students.
The idea to explore children’s books with adult learners who are normally accustomed to moving to
more advanced books may seem for some a bit questionable, at first glance. However, Rundell (2019, 2023)

226

Creating Stories

pointed out that adults reading stories they enjoyed as children will find them still interesting because
they remember what made these stories so precious: Learning about shared experiences, customs and
norms, struggles and adversities, and family and community life. More importantly, research has shown
(Nation et al., 2022) that the variety, depth, and sophistication of the language (i.e., words and syntactic
constructions found in the narratives are normally not used in speech) in children’s books help develop
social, emotional, and verbal skills. Children who read much showed improved sentence comprehension
and grammaticality judgment and were more likely to use difficult grammatical patterns in their speech.
The author selected the children’s books for this class not only for the quality of the language, but
for the themes and illustrations which could speak to the varied interests of the students in class. Der
Struwwelpeter (Hoffmann, 2005) and Max und Moritz (Busch, 2015) contain stories in which children
often suffer drastic consequences because they behave recklessly. While students were horrified by some
of the consequences the children in the stories suffered, they were interested in the teaching aspect of
these two books. Die kleine Hexe: Ausflug mit Abraxas (Preussler et al., 2017), the second volume of
the trilogy of a little witch developing self-confidence and strength to be able to exist in the adult world,
provided complex language and ample material for grammatical analysis. The author chose the famous
biblical story of Die Arche Noah (Janisch & Zwerger, 2008) because of its relevance today, namely the
question of whether life on Earth is threatened. In addition to connecting the theme to current environ-
mental issues, this story gave the learners the opportunity to analyze particularly expressive and thought-
ful illustrations. The author chose Zwei Papas für Tango (Schreiber-Wicke & Holland, 2017) because
it dealt sensitively with the topics of homosexuality and rainbow families, and it showed students that
real-life stories could easily become topics of a children’s book. Zarah und Zottel (Birck, 2017) is a
magical story of a child longing for acceptance among a group of children who are different from who
she is. Moving with her mother to a new neighborhood where she initially is told “to go back to where
she came from,” Zarah wants to be like her father, an American Indian, who, in her imagination, rides
a horse all day long. This makes her special.
The analysis and discussion of the language in the stories the students read was based on a set of
questions the author adapted from Reading and Writing Haven: A Blog for Educators (https://www.
readingandwritinghaven.com/), and included the following:

• Is the author using specific nouns, verbs, adjectives, and adverbs? How do they contribute to the
meaning of the story? Does the author use words with multiple meanings? What is the effect of
this wordplay?
• What punctuation does the author use in the text and in the dialogues? What effect do punctuation
marks such as ellipses, dashes, and colons have on the reading experience? Are there parts without
proper punctuation and what effect does the lack of punctuation have on the reader?
• What grammar features or topics can you recognize? How do these elements contribute to the
meaning, overall tone, or mood of the story?

Setting up the Writing Task

The creative task for this class was to write a children’s story including illustrations using generative
artificial intelligence (AI) tools. When developing the frame of the story, the students followed these
guidelines:

227

Creating Stories

• The topic of the story should interest and inspire children (and adults, too). Think of stories from
everyday life, fantasy stories or stories from the distant world.
• The place and time of the story could include the realistic world, the fairy tale world detached
from time and space, as well as futuristic places. Consider these questions: What does the place
look like? What is the weather like and how does it smell? What can you discover there? Who
lives in the world you created? How is the social structure and are there any rules in this world?
• Interesting characters can draw the reader into the story. What does your protagonist look like?
How can you describe the character of your protagonist? How does your protagonist act?
• Find a goal for your character to pursue. Include at least three turning points (i.e., the triggering
event, the character’s journey, and the final event). Consider these questions: What is your char-
acter’s goal? What motivates your character to achieve this goal? Who is stopping your character?
Who will help your character? What hurdles does your character have to overcome along the way?
What insights does your character gain from the journey?

Incorporating ChatGPT

Discussing and analyzing the children’s stories during the first five weeks of the quarter gave the students
a chance to start storyboarding their story by developing the topic, theme, setting, storyline, and plot,
as well as main characters (e.g., protagonists, heroes, and villains). During the second five weeks of
the quarter, the students began to further develop their ideas with the help of ChatGPT. They interacted
conversationally by writing prompts in German and by evaluating and responding to the answers Chat-
GPT provided. The idea of using ChatGPT as a model for effective writing in a second language is not
completely new. For example, Kwon et al. (2023) studied the effect of chatbot-based writing practices
on Korean elementary school students learning English as a second language. In this study, the results
of the posttest showed that the experimental group had learned more than the control group, suggesting
that the writing practice with a chatbot facilitated language acquisition.
The goal of the author’s study on the incorporation of ChatGPT was to try to understand the strengths
and limitations of various prompt-driven language exchanges. What could a learner reasonably expect
from the dialogue format of ChatGPT? Would it be possible to get answers to questions on vocabulary,
idiomatic expressions, and grammar issues, to get help in rewriting a short text with a different focus
including corrections or explanations of mistakes, and to get descriptions or short conversations? How
sensitive was ChatGTP to input or queries that were written in less-than-perfect German? Because rec-
ognizing and learning new German language patterns was an important part of their intellectual growth,
the students evaluated ChatGPT’s output not only for its cultural significance (i.e., focus on meaning),
but also for its linguistic value (i.e., focus on meaning and form). The instructor asked the students to
pay attention to new words, expressions, and idiomatic phrasing, and to specific grammatical forms (i.e.,
use of simple past and past perfect tenses, imperatives, relative clauses, present and past participles as
adjectival forms; subjunctive and passive sentences, onomatopoeic expressions, and alliterations) in
their queries.

228

Creating Stories

METHODOLOGY

Study Design

In this study, the author adopted an explorative approach to investigate the experiences of the students
using ChatGPT for a creative writing assignment, and to design a roadmap for instructors on the most
effective use and integration of ChatGPT. The researcher collected qualitative data through observations,
unstructured focus group discussions, personal interviews with the students, and ChatGPT discussion
protocols or queries. The author chose this research method as a viable approach to determine the nature
of the integration of ChatGPT (i.e., what, why, and how) and to provide a better understanding of how
the students learned with it. The students interacted with ChatGPT via the Web-based interface: They
wrote text prompts in German as input and evaluated and answered ChatGPT’s output. The goal of the
study was to explore the following:

• What can ChatGPT offer to language students developing a creative writing project? What are
some of the limitations?
• What are effective language prompts and why? What are effective rewrites or follow-up prompts?
• How well can ChatGPT understand input that is less than perfect in grammar and vocabulary?
• While the writing task was a meaning-focused activity, did the students also pay attention to the
form of the language? What kind of help did ChatGPT provide?

Participants

A group of 10 college students from a private university in the Midwest of the U.S., five males and five
females, all learners of German as a second language, took part in the study. The students were enrolled
in an advanced grammar class during the Spring quarter of 2023. The prerequisite for the class was a
proficiency level in German of B1/B2 on the Common European Framework of Reference for Languages
(Council of Europe, n.d.) scale or Intermediate High/Advanced Low on the ACTFL scale (ACTFL Per-
formance Descriptors for Language Learners, 2024). As is typical of advanced classes, the proficiency
levels of the students in the class varied, a result of aptitude and language learning background (i.e.,
taking various German classes in high school and/or college and study abroad experiences). All students
showed a high interest in learning German: Two of the students were majoring and six were minoring
in German.

Data Collection

The class met twice a week for 80 minutes over 10 weeks of instruction. During the first five weeks of
instruction, the students read and analyzed a series of children’s books and reviewed several grammar
chapters using a grammar book at the C1 level. Topics covered ranged from a quick review of verb tenses,
subjunctive mode, passive construction, to adjectives and adverbs and declension and comparisons.
During the second five weeks of instruction, the students began to use ChatGPT productively through
in-class instructional units targeting the creative use of prompts. The instructor gave them several home-
work assignments where they were encouraged to use similar prompt sequences to help them write and
design their own children’s book. They continued to review grammar using the grammar book as well

229

Creating Stories

as examples taken from the readings. Topics covered ranged from the use of conjunctions (i.e., “and”
and “but”) and conjunctive adverbs (i.e., “however” and “at the same time”) to appositions (e.g., “Leo,
the neighbor’s dog, is destroying my backyard”), relative clauses, participial clauses (e.g., “waiting for
my neighbor, I prepared some tea”), and infinitival constructions.
The students interacted with ChatGPT in class during four 40-minute sessions. During these interac-
tions, the instructor observed the students and took notes on their reactions, questions, and comments.
Each class session concluded with a brief unstructured focus group discussion on how the session had
gone and what might have been helpful as input for their own project.
All the students presented their final story, including comments on how they had used ChatGPT, to
the class, at the end of the 10 weeks. The author encouraged each student to meet for a personal inter-
view to discuss the use of ChatGPT, but only a handful of students found time. The instructor asked the
students to hand in examples of their ChatGPT discussion protocols at the end of the quarter.

ANALYSIS

In this section, the author analyzes samples of ChatGPT queries in German to understand how students
interacted conversationally with the chatbot. The author selected the sample queries from personal student
ChatGPT protocols and from the protocols generated during class sessions.

Writing a Full Story

One of the first in-class tasks the author assigned to the students was to ask ChatGPT to write a brief
story about two fictional main characters. The prompt was quite nonspecific (i.e., “write a brief children’s
story about a friendship between two main characters”). Then, the participants shared and discussed the
resulting stories in class. Since the students needed to write a unique story with twists and turns, there
was general disappointment about the simple and cliché-like stories that ChatGPT had created, often
with happy fairy-tale endings like “and if they have not died, they are still alive today.” The students
immediately recognized the inability of a chatbot to create an intricate story with twists and turns with
a simple straightforward request. They realized that they would need to work with smaller parts of the
story, be more precise, and create successive follow-up prompts.

Finding Appropriate Names

Developing a description for the protagonist in the story as well as other characters began with the search
for appropriate names. The students did not have much experience with German names and ChatGPT
was fully capable of providing a list. Below is an example of an initial exchange the instructor and the
learners developed together in class:

You: Ich schreibe ein Kinderbuch. Finde einen Namen für die Hauptperson, ein Kranich. (I am writing
a children’s book. Find a name for the main character, a crane.)
ChatGPT: Wie wäre es mit dem Namen “Karl” für deinen Hauptcharakter Kranich? Andere Optionen
könnten “Kiki,” “Krümel,” “Kasimir” oder “Kira“ sein. (How about the name “Karl” for your
main character Crane? Other options could be “Kiki,” “Krümel,” “Kasimir” or “Kira”.)

230

Creating Stories

You: “Krümel” gefällt mir. Krümel hat einen Freund, einen roten Frosch, der am Ufer des Teiches wohnt.
Wähle einen Namen für den Frosch. (I like “Krümel.” Krümel has a friend, a red frog, who lives
on the banks of the pond. Choose a name for the frog.)
ChatGPT: Ein süßer Name für den roten Frosch könnte “Felix” sein. Andere Optionen könnten “Frido-
lin,” “Finn,” “Florian” oder “Ferdinand” sein. (A cute name for the red frog could be “Felix.”
Other options could be “Fridolin,” “Finn,” “Florian” or “Ferdinand”.)
You: Finde einen Namen für den Frosch, der zu der roten Farbe passt. (Find a name for the frog that
matches the red color.)
ChatGPT: Ein passender Name für einen roten Frosch könnte beispielsweise “Rubin” sein, da dieser
Edelstein ebenfalls eine rötliche Farbe hat. (A fitting name for a red frog could be “Rubin” as this
gemstone is also reddish in color.)
You: Keiner dieser Namen gefällt mir. Was könnte es noch sein? (I don’t like any of those names. What
else could it be?)
ChatGPT: Wie wäre es mit dem Namen “Rufio”? (How about the name “Rufio”?)

Working With Descriptions

A third task the author developed as a class project was asking ChatGPT to help write a character de-
scription. The students had already prepared a simple description of their main character: Krümel ist ein
majestätischer Vogel mit einem langen, schlanken Hals, einem rötlichen Kopf, und einem langen spitzen
Schnabel (Krümel is a majestic bird with a long, slender neck, a reddish head, and a long, pointed beak).
They asked ChatGPT for suggestions on what they could improve, including a short rewrite. ChatGPT
suggested that they should add details about the feathers (are they grey or white?), the color of the eyes,
and the size of Krümel. Then, ChatGPT offered the following rewrite:

ChatGPT: Krümel ist ein majestätischer Vogel von mittlerer Größe mit einem schlanken, langen Hals
und einem wohlgeformten rötlich gefärbten Kopf. Sein langer, spitzer Schnabel ist perfekt geformt
zum Fischen und Jagen von Beute. Seine Federn sind weiß und grau mit auffälligen schwarzen
Mustern auf den Flügeln. Krümels Augen sind groß und bernsteinfarben und glänzen in der Sonne.
(Krümel is a majestic bird of medium size with a slender, long neck and a well-shaped reddish-
colored head. Its long, pointed beak is perfectly shaped for fishing and hunting prey. Its feathers
are white and gray with striking black patterns on the wings. Krümel’s eyes are large and amber
and shine in the sun.)

The students felt the paragraph was too stilted. They asked ChatGPT to rewrite it in a simpler version
that would be better suited for a children’s book and would contain information on what the crane was
doing during the day. ChatGPT’s next suggestion read:

ChatGPT: Krümel ist ein schöner Vogel mit einem langen Hals und einem spitz zulaufenden Schnabel.
Er hat ein rotes Köpfchen und graue, weiche Federn, die ihn warm halten. Krümel liebt es, im
Sumpfgebiet zu leben und im Teich nach Fischen zu suchen. Er ist ein sehr geschickter Jäger und ein
lustiger kleiner Vogel zum Beobachten. (Krümel is a beautiful bird with a long neck and a pointed
beak. It has a small red head and grey, soft feathers that keep it warm. Krümel loves to live in the
swamp area and look for fish in the pond. He is a very skilled hunter and a fun little bird to watch.)

231

Creating Stories

The instructor used these two rewrites as a writing exercise for the students to come up with a third
description considering information from both paragraphs and adding additional material, if appropriate.
The students also used ChatGPT to generate ideas for describing the place where the two main char-
acters lived. They asked for a list of things Krümel and Rufio would see walking along the edge of the
pond, and ChatGPT offered several examples with appropriate explanations. The first two were as follows:

ChatGPT: Wasserlilien: Sie sehen wunderschöne Wasserlilien, die auf der Oberfläche des Teiches
schwimmen. Die bunten Blütenblätter der Lilien öffnen sich der Sonne entgegen. (Water Lilies:
They see beautiful water lilies floating on the surface of the pond. The colorful petals of the lilies
open towards the sun.)
ChatGPT: Libellen: Über dem Wasser tanzen bunte Libellen mit glänzenden Flügeln. Sie fliegen elegant
von Blatt zu Blatt und jagen nach Insekten. (Dragonflies: Colorful dragonflies with shiny wings
dance above the water. They fly elegantly from leaf to leaf and hunt for insects.)

ChatGTP was also able to give accurate descriptions of what a frog in a children’s story might do,
distinguishing between appropriate activities for a shy and quiet female frog and for a boyish and confident
female frog. The activities suggested for Lilya, the shy frog, were: Counting water lilies, watching the
fish in the pond, sunbathing on a sea leaf (but not for too long), and helping the mother look for insects.
The activities suggested for Lilly, the boyish, bold, and confident frog, were: Jumping, diving, chasing
insects, and discovering new things, among others. This was an excellent description, as the frogs in this
story had human qualities; yet ChatGPT described activities appropriate to the environment in which
the two characters lived (i.e., in and around a pond).

Developing a Larger Vocabulary

One of the most powerful learning activities was the development of unfamiliar language such as
searching for words or phrases including definitions and translations. The students were still using
online dictionaries and translation programs they had used before. They soon realized that dictionaries
were limited in what they could provide, when compared to the powerful language ChatGTP presented
them. One of the students developed a children’s story about her service dog, a diabetic alert dog. She
checked in Google Translate for “service dog” and was presented with the word “Servicehund,” not an
expression that is used very much in German. ChatGPT, however, provided a much more helpful and
more accurate learning sequence:

You: Wie nennt man einen Hund, der Menschen hilft? (What do you call a dog that helps people?)
ChatGPT: Ein Hund, der Menschen in verschiedenen Aspekten unterstützt, wird oft als “Therapiehund”
oder “Servicehund” bezeichnet. (A dog that assists people in various aspects is often referred to as
a “therapy dog” or “service dog”.)

ChatGPT then provided a list of specific names with accompanying definitions. Some examples are:

• Blindenhund: Unterstützt Menschen mit Sehbehinderungen oder Blindheit. (Guide Dog: Supports
people with visual impairments or blindness.)

232

Creating Stories

• Mobilitätshund: Hilft Menschen mit eingeschränkter Mobilität, indem er Gegenstände aufhebt,

Türen öffnet und andere unterstützende Aufgaben erledigt. (Mobility Dog: Helps people with
limited mobility by picking up objects, opening doors, and performing other supportive tasks.)
• PTSD-Begleithund: Speziell ausgebildet, um Menschen mit posttraumatischer Belastungsstörung
zu unterstützen. (PTSD Service Dog: Specially trained to support people with post-traumatic
stress disorder.)
• Diabetikerwarnhund: Riecht Veränderungen im Blutzuckerspiegel und warnt seinen Besitzer vor
einem möglichen Anfall. (Diabetic alert dog: Smells changes in blood sugar levels and warns its
owner of a possible seizure.)
• Rollstuhlbegleithund: Speziell ausgebildet, um Menschen im Rollstuhl zu unterstützen, indem
er Türen öffnet, Gegenstände aufhebt und andere Aufgaben erledigt. (Wheelchair Service Dog:
Specially trained to assist people in wheelchairs by opening doors, picking up objects, and per-
forming other tasks.)
• Such- und Rettungshund: Wird in Katastrophen- und Suchsituationen eingesetzt, um vermisste
Personen zu finden. (Search & Rescue Dog: Used in disaster and search situations to find missing
persons.)

In addition to these translation exercises, students used ChatGPT to find words beyond the ones they
already knew to develop a more nuanced language for their stories. For example, to describe the main
character as traurig (sad), one student wanted a list of synonyms and was presented with niedergeschla-
gen, bedrückt, betrübt, melancholisch (despondent, depressed, unhappy, melancholic). Another requested
examples of idiomatic expressions to describe their character as good natured (Er ist so gutmütig wie
ein Lamm/He is good-natured as a lamb) and as eating super-fast (Er isst wie ein Scheunendrescher/He
eats like a threshing machine). Other students asked for nouns that expressed various emotions (Liebe,
Hass, Freude, Trauer, Angst, Eifersucht, Hoffnung, Verzweiflung, Glück, Einsamkeit/love, hate, joy,
sorrow, fear, jealousy, hope, despair, happiness, loneliness) and verbs that expressed joy and happiness
(lachen, strahlen, jubeln, hüpfen, tanzen, singen, klatschen, umarmen, küssen/laugh, beam with you,
cheer, jump, dance, sing, clap hug, kiss). One student was interested in an interjection (i.e., a word used
to express a feeling or to request something, usually used in dialogues). Asked what a frog would say
in certain situations, ChatGPT provided Boah! Huch! Irre! Mannomann! Unglaublich! (Wow! Yikes!
Crazy! Well! Incredible!). The student asked for German expressions that were frog-like since the list
provided did not seem appropriate to her for an animal. ChatGPT presented Quaak oder Kwaak (Quaak
or Kwaak) as the most used onomatopoeic expression but offered more options: Krah! Ripp! Kroa! Krick!
Brumm! Grummel! Platsch! The student then wanted to know when and how one would use Grummel
and Platsch. ChatGPT’s answers were:

ChatGPT: Ein Frosch macht normalerweise “Platsch,” wenn er ins Wasser springt. (A frog usually
makes a “splash” when it jumps into the water.)
ChatGPT: Die Interjektion “Grummel! ” wird oft genutzt, um Unzufriedenheit, Verärgerung oder
Missfallen auszudrücken. (The interjection “Grumble!” is often used to express dissatisfaction,
annoyance, or displeasure.)

Even alliterations in German (i.e., a literary device that repeats consonant sounds in two or more
nearby words), a technique the students had encountered in their readings, became the subject of a

233

Creating Stories

prompt. A student asked for language examples that had to do with his protagonist, a monkey, cleaning
his room. The student learned the following phrases: Saubere Socken sortieren (sorting clean socks) and
Bananenschalen behutsam beseitigen (carefully removing banana peels).

Developing Grammar Knowledge

Given the large output ChatGPT produced for the prompts the students wrote, the class had much mate-
rial that they could analyze for specific grammar practice, especially punctuation, inflectional forms,
and verb tenses, including word order. The students also used prompts and queries to improve their own
grammar skills, such as asking for corresponding past tense forms or asking for grammar feedback on
individual sentences. It was most surprising to the students to realize that ChatGPT could even handle
a variety of inputs that were lacking accurate spelling, grammar, and even word choices.

You: Können Sie ein Name, der mit ein “Sch” anfangen, machen? (Can you make a name that starts
with “Sch”?)
ChatGPT: Natürlich! Hier sind einige Namen, die mit “Sch” beginnen und zu deiner Affen-Hauptfigur
passen könnten: Schoko, Schiller, Schröder, Schnufel, Schalko. (Of course! Here are some names
that start with “Sch” that might suit your main monkey character: Schoko, Schiller, Schröder,
Schnufel, Schalko.)
You: Ich wird mein Buch “Schrödi der schelmischer Affe” heißen. Gefällen Sie? (My book will be called
“Schrödi the mischievous monkey.” Do you like it?)
ChatGPT: “Schrödi der schelmische Affe” klingt großartig! (“Schrödi the mischievous monkey” sounds
great!)
You: Ich will mein Affe weiblich zu sein. Können Sie mein Title verändern? (I want my monkey to be
female. Can you change my title?)
ChatGPT: “Schrödi, die schelmische Affendame”. (“Schrödi, the mischievous monkey lady”.)
You: Das Wort “Affendame” gefällt mir nicht. Können sie “Äffin” stattdessen benutzen? (I don’t like
the word “monkey lady. ” Can you use “monkey” instead?)
ChatGPT: “Schrödi, die schelmische Äffin”. (“Schrödi, the mischievous monkey”.)

Most useful were the recasts ChatGPT provided. Here is one example that involves the correct use
of an adjective ending:

You: Ich wird mein Buch “Schrödi der schelmischer Affe” heißen. Gefällen Sie? (My book will be called
“Schrödi the mischievous monkey.” Do you like it?)
ChatGPT: “Schrödi der schelmische Affe” klingt großartig! (“Schrödi the mischievous monkey” sounds
great!)

Some students pointed out that they were learning about their mistakes simply by paying attention
to the accurate language in ChatGPT’s answer.
ChatGPT turned out to be very creative in writing dialogues. Again, as a group project, the students
asked ChatGPT to write a dialog between the frog parents forbidding the children to play with Rufio,
the red frog, who lived at the edge of the pond. This output provided source material for the students to
discuss punctuation rules in German for direct speech as well as conjunctions and word order.

234

Creating Stories

Papa Frosch: “Kinder, ich möchte nicht, dass ihr mit diesem roten Frosch namens Rufio spielt.” (“Kids,
I don’t want you to play with that red frog named Rufio.”)
Mama Frosch: “Ja, das stimmt. Rufio ist anders als wir. Er ist rot, nicht grün wie wir. Und wir wissen
nicht, woher er kommt oder wer seine Eltern sind.” (“Yes, that’s right. Rufio is different from us.
He is red, not green like us. And we don’t know where he’s from or who his parents are.”)
Papa Frosch: “Es ist besser, wenn ihr mit den anderen grünen Fröschen spielt. Sie sind wie wir und ihr
wisst, dass ihr mit ihnen sicher spielen könnt.” (“It’s better if you play with the other green frogs.
They’re like us, and you know you can play with them safely.”)
Kind 1: “Aber Papa, Rufio ist nett zu uns und wir mögen ihn. Warum können wir nicht mit ihm spielen?”
(“But Dad, Rufio is nice to us and we like him. Why can’t we play with him?”)
Mama Frosch: “Es geht nicht darum, ob er nett ist oder nicht. Es geht darum, dass wir nicht wissen, wer
er ist oder woher er kommt. Es ist besser, wenn ihr mit den anderen grünen Fröschen spielt.” (“It’s
not about whether he’s nice or not. The point is that we don’t know who he is or where he comes
from. It’s better if you play with the other green frogs.”)

Creating Illustrations Using an Artificial Intelligence Image Generator

Illustrations are a crucial part of a children’s book: They help clarify the storyline and unfold visually
what the text describes. Beyond simply showing what is expressed in the text, illustrations can add new
elements that are not described in the text, therefore providing a fresh viewpoint or narrative. Good il-
lustrations make the reader fall in love with the protagonist or simply draw the reader into the story and
keep the reader hooked. In illustrating their books, the students were free to use their drawing talents,
take their own photographs, or work with a graphics editor such as Photoshop. Students were introduced
in class to the concept of an AI image creator, a program that could create original and realistic images
and art by simply understanding a description of the subject matter.
Students experimented with DALL•E (https://labs.openai.com/) and Bing Image Creator (https://
bing.com/create). Both AI image generators were able to create fairly accurate pictures, although the
learners needed to experiment with the way a prompt was phrased: Ein Kranich und ein roter Frosch,
im Kinderbuchstil (A crane and a red frog, in children’s book style) resulted in more accurate drawings
(Figure 1) than Ein roter Frosch und ein Kranich, im Kinderbuchstil (a red frog and a crane, in children’s
book style), where the crane appeared red (Figure 2).
The longer or more complex the input, the more difficult it was for the program to create a true rep-
resentation. The students experimented with the description Ein Kranich und ein roter Frosch spazieren
am Ufer eines idyllischen Teiches, im Kinderbuchstil (A crane and a red frog walk on the banks of an
idyllic pond, in children’s book style), but AI was not able to generate a satisfactory picture (Figure 3).
In some of the stories created, the protagonists were not humans but animals or fantasy characters,
while in others the protagonists represented a diverse and inclusive mix of characters, which added to
the difficulty of finding the right illustration. Depending on the complexity, the AI generator could not
represent the input accurately.
While creating a unique and interesting representation of the protagonist had its difficulties, to make
sure that this unique character would appear in all subsequent drawings to represent the story accurately
was almost impossible. In the end, the students experimented with other image creators (e.g., NightCafé,
https://creator.nightcafe.studio/studio) and other ways of illustrating their storybook: Some searched for
appropriate images online, took their own pictures, used their drawing skills, or used image editor soft-

235

Creating Stories

ware such as Photoshop to manipulate pictures and create appropriate compositions or collages. Figure
4 below is an example of a page of a student-created story book called Oska, der Ökoheld (Oska, the
Eco-Hero) integrating text and images. The images represent a collage of elements generated by AI.

Figure 1. Ein Kranich und ein roter Frosch, im Figure 2. Ein roter Frosch und ein Kranich, im
Kinderbuchstil (A Crane and a Red Frog, in chil- Kinderbuchstil (A Red Frog and a Crane, in chil-
dren’s book style) dren’s book style)
Note. Picture generated using DALL•E. Note. Picture generated using DALL•E.

Figure 3. Ein Kranich und ein roter Frosch spazieren am Ufer eines idyllischen Teiches, im Kinderbuchstil
(A Crane and a Red Frog Walk on the Banks of an Idyllic Pond, in children’s book style)
Note. Picture generated using DALL•E.

236

Creating Stories

Figure 4. Example page from Oska, der Ökoheld (Oska, the Eco-Hero), a student-created story
Note. Translation of the text: One day, they saw something funny while they were fly fishing. A well-dressed toad, carrying a
walking stick and top hat, was walking with a foreman’s frog.
“Well,” said the wealthy frog, “this is a wonderful place for our landfill.”
“Definitely, Count BrightFrog,” croaked the foreman.
“Landfill?” asked Oskar. “But you mustn’t do that! This pond is our home!”
“Well, Mr. Oscar, I am Count BrightFrog, the richest toad far and wide, and your little pond is mine. This deed states that
everything I want to do with this pond is allowed, and you can’t do anything about it.”

DISCUSSION

The writing of an original children’s story was primarily a meaning-focused task. FonF, as the interac-
tions with ChatGPT lay bare, occurred because of lexical, grammatical, and pragmatic questions the
students asked in trying to convey accurate meaning. Engaging in the chatbot-mediated writing activities
in class and on their own was therefore a welcome addition to the learning environment. The class was
taught during Spring 2023, and ChatGPT had been released only a few months before (Open AI released
an early version of ChatGPT at the end of 2022). As a result, most of the students were not familiar yet
with how to interact with ChatGPT. None of them had used it in German or had entertained the idea
that they could work with ChatGPT in a foreign language. They were surprised to learn that ChatGPT
could understand and answer in German.
The first exercise in class using ChatGPT turned out to be important. The students discovered im-
mediately that ChatGPT, at this stage, could not provide a full children’s story beyond simple cliché-like
narratives. This was useful in setting work expectations. Realizing that for a good final project, students
would have to actively work on writing and responding to prompts as well as on making critical deci-
sions on what material to use in their final story, legitimized the use of ChatGPT as a German tutor.
The students had been told in several other classes that the use of ChatGPT was not allowed because of
plagiarism concerns. Understanding that this was not about simply copying output, but that their task
included a conversational exchange in German through which their story would take shape, was a relief.

237

Creating Stories

ChatGPT turned out to be a powerful and effective tutor who could answer questions or react to
prompts even if they were written in less-than-perfect German. As the author outlined above, the confus-
ing question Ich wird mein Buch “Schrödi der schelmischer Affe” heißen. Gefällen Sie? was responded
to with a semantically valid answer making meaningful conversations with the learner: “Schrödi der
schelmische Affe” klingt großartig! This turned out to be important for students, as their questions were
often composed hastily without too much concern for the exact grammar.
Where ChatGPT was most helpful was in all areas of language development. The students frequently
asked questions about expanding their vocabulary, and the conversations with the chatbot helped the
learners solve problems often better than the dictionaries to which they were used. A prime example
listed above is the search for the German term for “service dog,” where the learner was presented with a
list of possible translations including definitions in German. Other excellent examples were the search
for synonyms (i.e., what is another word for “sad”) or the search for semantic expansions of a category
of words (i.e., give me a list of verbs that express “joy”). To mimic the type of language the students had
explored in the children’s book they read, one student asked for alliterations in German (i.e., Saubere
Socken sortieren/sorting clean socks) and another for interjections to make the dialog more native-like
(i.e., platsch/splash). Representing sounds in German was another semantic area that the students ex-
plored. One student wanted to know how to say “alarm clock” in German and how to represent the sound
it would make. Finally, ChatGPT proved helpful for a student who wanted to use an idiomatic expression
to describe the protagonist as good-natured. The chatbot provided Er ist so gutmütig wie ein Lamm/He
is good-natured as a lamb. To indicate that the protagonist stopped suddenly, the chatbot provided Er
blieb wie angewurzelt stehen/He stopped in his tracks.
Many students were using ChatGPT to inquire about grammatical information. For example, strug-
gling with the past tense forms of verbs which were important for the stories they wrote, one student
asked for a list of verbs indicating “running” and the equivalent forms in the simple past tense. The
instructor and the students had previously discussed the possibilities of forming extended participles as
adjectival phrases and one student created, using several prompts, the following description: Eine gut
gekleidete, Gehstock und Zylinder tragende Kröte (A well-dressed toad carrying a cane and top hat).
Sometimes, ChatGPT reminded student to check for grammatical accuracy: A student wanted a list of
German adjectives that could be alliterative with Mut (courage) and could be used to complement some-
one. After providing examples such as mutig (courageous), majestätisch (majestic), mächtig (mighty),
and mitfühlend (compassionate), ChatGPT reminded the student to adapt the adjectives to match the
gender and number of the person they were complimenting. In some instances, where prompts were less
than grammatically perfect, ChatGPT provided recasts to help students onto the right track. One student
wanted a name that would start with “Sch,” another wanted a list of names that started with “A,” and
both times ChatGPT answered with the correct grammar.

You: Können Sie ein Name, der mit ein “Sch” anfangen, machen? (Can you make a name that starts
with an “Sch”?)
ChatGPT: Natürlich! Hier sind einige Namen, die mit “Sch” beginnen und zu deiner Affen-Hauptfigur
passen könnten. (Of course! Here are some names that start with “Sch” that might suit your main
monkey character.)
You: Können Sie mehr Namen gleich ihnen finden, besonders Namen, die mit ein “A” anfangen? (Can
you find more names like them, especially names that start with an “A”?)

238

Creating Stories

ChatGPT: Natürlich! Hier sind weitere Namen, die mit dem Buchstaben “A” beginnen und dem Stil der
zweiten Liste ähneln. (Of course! Here are more names that start with the letter “A” and are similar
to the style of the second list.)

Quite often recasts involved the correct use of adjective endings, as in this example where a student
input Schrödi der schelmischer Affe was corrected in ChatGPT’s answer with Schrödi der schelmische Affe
(Schrödi the mischievous monkey). Adjective endings were one of the areas college learners of German
found to be the most difficult to learn (Chavez, 2016, 2017). It was very important for the students to
have a tutor who would answer their questions at the time when they were most salient, notwithstanding
their own language limitations and mistakes in their prompts. ChatGPT did not judge the students, but
provided answers with which they could start developing and improving their writing skills.
The class found some limitations when working with ChatGPT. ChatGPT lacked creativity and imagi-
nation and was not able to create engaging storylines that included intricate plots or multidimensional
characters. It also had considerable difficulties at times to mimic the genre of children’s stories, and the
descriptions sounded more like an encyclopedic entry, even if asked to rewrite the text for a children’s
book. At times, there was significant input required in the form of follow-up prompts to develop the sto-
ryline, and some students simply gave up relying on their imagination and skills and/or double-checking
with a human tutor.
This chapter represents only a snapshot of the work with ChatGPT. Nevertheless, it highlights the
endless potential ChatGPT has to engage students in creative writing in a foreign language. Teaching
the class, the author learned much about what to do better and what not to do. To ensure a successful
experience, the following guidelines could be helpful to make sure that students are prepared:

• Acquire Strategies for Prompt Design: One of the first tasks was to model for the students in
class how to write a prompt. This allowed everybody to discover the variety of prompts that were
possible, such as asking for grammar help, or additional vocabulary and appropriate expressions.
Open-ended or vague prompts were not successful in getting good information.
• Critically Analyze the Prompt Output: Beginning this project as a collaborative task in class
sharing and discussing prompts and corresponding answers was crucial in many ways. Through
discussions, the students discovered limitations in terms of the quality of the output (e.g., unso-
phisticated, cliché-like storylines, a few things were factually wrong) and the lack of nuanced and
unique answers.
• Use Effective Prompt Rewrites to Narrow the Prompt Output: The students learned to be criti-
cal but forgiving. ChatGPT may not get everything right the first time, especially if the prompt
is less than specific. Rethinking the output and why it was not what the student was looking for
helped refine the prompts to receive the desired output.
• Focus on Smaller Writing Sections: Working with individual sections of the full story (e.g.,
brief descriptions, narrations, and dialogues) was more successful. Examples the students prac-
ticed in class were description of a character (mental disposition or physical appearance of the red
frog), description of the environment (what the red frog saw when he walked along the pond), and
dialogues (what his parents warned him about when swimming in the pond). Asking for too much
or overloading a prompt with information overwhelmed the chatbot on occasion.
• Work Sequentially Throughout the Project: A story such as a children’s book cannot be created
through one prompt or in one sitting, especially if the storyline is complex with twists and turns.

239

Creating Stories

The students were most successful when working sequentially through the story, refining each part
with well-crafted prompts, and assembling the outputs to create the final story.
• Keep at It: On occasion, the students needed encouragement to continue working with ChatGPT.
The students who had a particular answer in mind found it sometimes difficult to phrase the
prompt in such a way that it would elicit the desired material. However, the more students prac-
ticed writing prompts, the better the exchanges.

LIMITATIONS

This project was not intended to show that students using ChatGPT advanced their language proficiency
more than students who did not use ChatGPT. The author only had a small group of students involved in
the class and not enough to set up a reliable control group. Since the use of ChatGPT to further language
proficiency is rather unexplored, the goal of the study was to describe the experiences of language learn-
ers using ChatGPT in German and to reflect on the potential for learning grammar and new vocabulary.
The author used an explorative approach, collecting ChatGPT protocols (class protocols and individual
protocols), detailing observations, and conducting unstructured focus group interviews and personal
discussions to gauge students’ interaction and satisfaction with ChatGPT. These activities, however,
were voluntary and not all the students participated equally.
While many of the observations made on language use, the suggestions provided for how to set up the
learning task, and how best to incorporate ChatGPT are valuable contributions to the field of language
teaching and learning, more data need to be collected, potentially in different languages, to be able to
generalize across all languages. For this project, ChatGPT was an effective tool for engaging students in
a variety of language tasks, and the quality of the students’ final children’s stories showed that they did
advance their writing skills substantially, even in areas that were not explicitly discussed or practiced.
However, whether learning was the sole result of ChatGPT use is not clear. The students were free to
meet with a human tutor to go over their writing, and some took advantage of that offering.
For the interactions with a chatbot, the author used the free version of ChatGPT, version 3.5, to ensure
that all the students had equal access. The current version, ChatGPT 4.0, however, is more powerful, and
the interactions and results the author presented in this chapter may look different when using ChatGPT
4.0 or a later version.

CONCLUSION

Overall, the learners treated ChatGPT as a valuable addition to their learning tools: They felt that these
active, in-time, and student-directed interactions helped them practice their creative thinking and writing
skills in fundamentally new ways. There was much they wanted to know and much ChatGPT provided:
New vocabulary and expressions such as idiomatic phrases, expansions of semantic and syntactic cat-
egories, rewrites, and creative suggestions such as short descriptions or dialogues. Most importantly, the
students worked in areas that had relevance to them and that were important for each one at their stage
of learning and language development.
It became clear to students that ChatGPT was not a substitute for their engagement, and the more
they interacted the more they learned and the better ChatGPT was with providing accurate answers.

240

Creating Stories

They also realized that every learner was bringing a unique perspective and voice to their story and that
an overreliance on AI-generated content would not ensure an individual and unique project.
Working with the students on developing and discussing prompts was an effective way of getting
them to become familiar with AI. They learned that the interactions were at the level of a conversation
with a patient interlocutor whom they could ask follow-up questions and with whom they could disagree
at times. Using the language that ChatGPT provided in the output was helpful in forming follow-up
questions. The students also realized that their input did not have to be perfect in terms of grammar and
vocabulary for ChatGPT to understand, and that ChatGPT’s answers quite often contained the correct
way of saying or writing something they had attempted.
The exchanges with ChatGPT created conditions in which the learners could learn according to
their learning style and their current language proficiency. Grammar was highlighted not according to
a prescribed syllabus, but according to the current needs of the learner (Ellis, 2006). The transcripts
showed that learning how to write correctly and effectively is a complex undertaking that includes both
explicit and implicit learning processes (Ellis, 2015, 2016; Pawlak, 2021). The conversations unfolding
between the learners and ChatGPT provided context and various techniques for the students to focus
on meaning and on FonF, including incidental FonF, to facilitate the development of learners’ second
language (Pouresmaeil & Vali, 2023).

REFERENCES

ACTFL. (2024). ACTFL performance descriptors for language learners. https://www.actfl.org/educator-

resources/actfl-performance-descriptors
Basturkmen, H. (2023). Explicit versus implicit grammar instruction and knowledge. In J. I. Liontas (Ed.),
The TESOL encyclopedia of English language teaching (pp. 1–7). doi:10.1002/9781118784235.eelt0060
Birck, J. (2017). Zarah und Zottel: ein Pony auf vier Pfoten. Fischer Sauerländer Verlag.
Busch, W. (2015). Max und Moritz: eine Bubengeschichte in Sieben Streichen. Esslinger Verlag.
Byrnes, H., & Manchón, R. M. (2014). Task-based language learning: Insights from and for L2 writing.
An Introduction. In H. Byrnes & R. M. Manchón (Eds.), Task-based language learning—Insights from
and for L2 writing (pp. 1–23). John Benjamins. doi:10.1075/tblt.7.01byr
Chavez, M. (2016). Students’ accounts of grammatical forms of German that are difficult, unattainable,
and irrelevant for self-expression. Language Awareness, 25(3), 197–221. doi:10.1080/09658416.2016
.1165238
Chavez, M. (2017). Hard rules and bad memories: College learner’s accounts of what makes learning
German grammar difficult. Die Unterrichtspraxis, 50(1), 1–21. doi:10.1111/tger.12018
Chmarkh, M. (2021). “Writing to learn” research: A synthesis of empirical studies (2004-2019). Euro-
pean Journal of Educational Research, 10(1), 85–96. doi:10.12973/eu-jer.10.1.85
Council of Europe. (n.d.). Common European Framework of Reference for Languages: Learning, teach-
ing, assessment. https://www.coe.int/en/web/common-european-framework-reference-languages

241

Creating Stories

East, M. (2015). Task-based teaching and learning: Pedagogical implications. In N. Van Deusen-Scholl
& S. May (Eds.), Second and foreign language education. Encyclopedia of language and education (pp.
85–95). Springer. doi:10.1007/978-3-319-02323-6_8-1
Ellis, N. C. (2015). Implicit AND explicit learning of language. In P. Rebuschat (Ed.), Implicit and
explicit learning of language (pp. 3–24). Benjamins. doi:10.1075/sibil.48.01ell
Ellis, R. (2006). Current issue in the teaching of grammar: An SLA perspective. TESOL Quarterly,
40(1), 83–107. doi:10.2307/40264512
Ellis, R. (2009). Implicit and explicit learning, knowledge, and instruction. In R. Ellis, S. Loewen, C.
Elder, H. Reinders, R. Erlam, & J. Philp, J. (Eds.), Implicit and explicit knowledge in second language
learning, testing, and teaching (pp. 3–26). Multilingual Matters. doi:10.21832/9781847691767-003
Ellis, R. (2016). Focus on form: A critical review. Language Teaching Research, 20(3), 405–428.
doi:10.1177/1362168816628627
Hoffmann, H. (2005). Der Struwwelpeter. Loewe Verlag GmbH.
Incecay, V., & Dollar, Y. K. (2011). Foreign language learners’ beliefs about grammar instruction and error
correction. Procedia: Social and Behavioral Sciences, 15, 3394–3398. doi:10.1016/j.sbspro.2011.04.307
Janisch, H., & Zwerger, L. (2008). Die Arche Noah. Minedition.
Jean, G., & Simard, D. (2011). Grammar teaching and learning in L2: Necessary, but boring? Foreign
Language Annals, 44(3), 467–494. doi:10.1111/j.1944-9720.2011.01143.x
Kormos, J. (2023). The role of cognitive factors in second language writing and writing to learn a second
language. Studies in Second Language Acquisition, 45(3), 622–646. doi:10.1017/S0272263122000481
Kwon, S. K., Shin, D., & Lee, Y. (2023). The application of chatbot as an L2 writing practice tool.
Language Learning & Technology, 27(1), 1–19.
Leow, R. P. (2019). ISLA: How implicit or how explicit should it be? Theoretical, empirical, and peda-
gogical/curricular issues. Language Teaching Research, 23(4), 476–493. doi:10.1177/1362168818776674
Loewen, S. (2018). Focus on form versus focus on forms. In J. I. Liontas (Ed.), The TESOL encyclopedia
of English language teaching (pp. 1–6). doi:10.1002/9781118784235.eelt0062
Loewen, S., Li, S., Fei, F., Thompson, A., Nakatsukasa, K., Ahn, S., & Chen, X. (2009). Second language
learners’ beliefs about grammar instruction and error correction. Modern Language Journal, 93(1),
91–104. doi:10.1111/j.1540-4781.2009.00830.x
Lys, F. (2013a). Computer-mediated grammar teaching and its effect on different language tasks. In P.
Hubbard, M. Schulze, & B. Smith (Eds.), Learner-computer interaction in language education: CALICO
Journal: A Festschrift in Honor of Robert Fischer (Vol. 30, pp. 166–186). Academic Press.
Lys, F. (2013b). The development of advanced learner oral proficiency using iPads. Language Learning
& Technology, 17(3), 94–116.

242

Creating Stories

Nation, K., Dawson, N. J., & Hsiao, Y. (2022). Book language and its implications for children’s
language, literacy, and development. Current Directions in Psychological Science, 31(4), 375–380.
doi:10.1177/09637214221103264
Pawlak, M. (2021). Implicit versus explicit grammar learning and teaching. In E. Macaro & R. Woore (Eds.),
Debates in second language education (1st ed., pp. 165–182). Routledge., doi:10.4324/9781003008361-12
Pouresmaeil, A., & Vali, M. (2023). The effects of incidental focus on form on learning vocabulary,
grammar, and pronunciation. Language Teaching Research, 0, 1–24. doi:10.1177/13621688231185419
Preussler, O., Preussler-Bitch, S., & Napp, D. (2017). Die kleine Hexe: Ausflug mit Abraxas. Thiene-
mann Verlag.
Rundell, K. (2019). Why you should read children’s books, even though you are so old and wise. Blooms-
bury Publishing.
Rundell, K. (2023, July 11). Why adults should read children’s books. https://www.bbc.com/culture/
article/20230711-why-adults-should-read-childrens-books?mibextid=Zxz2cZ
Schreiber-Wicke, E., & Holland, C. (2017). Zwei Papas für Tango. Thienemann Verlag.
Sok, S., Kang, E. Y., & Han, Z. (2019). Thirty-five years of ISLA on form-focused instruction: A meth-
odological synthesis. Language Teaching Research, 23(4), 403–427. doi:10.1177/1362168818776673
Williams, J. (2012). The potential role(s) of writing in second language development. Journal of Second
Language Writing, 21(4), 321–331. doi:10.1016/j.jslw.2012.09.007

KEY TERMS AND DEFINITIONS

AI Image Generator: An AI-powered tool or software that creates realistic images or art pieces using
the information from the description or text prompt the user entered. The images created are entirely new.
ChatGPT Prompt: A statement, a question or instruction written by the user and entered into Chat-
GPT to generate an answer. A prompt is a request for information or a conversation starter.
Explicit Grammar Learning: Grammar learning that takes place through explicit instruction where
the learner is given a grammar explanation or rule.
Focus on Form (FonF): The learning of a foreign language through engagement in meaning-oriented
activities that encourage learners to notice various language forms.
Focus on Forms (FonFs): The learning of a foreign language through drills and structured exercises
in controlled learning environments.
Implicit Grammar Learning: Grammar learning that takes place through meaning-focused tasks
where the learner is not being taught a grammar explanation or rule.
Task-Based Language Teaching: In this approach to second or foreign language teaching, learners
are asked to complete a task or tasks using the foreign language which engages their natural abilities for
incidental language acquisition.
Writing-to-Learn Activities: Informal and low-stakes writing activities that are designed for the
learner to think through key concepts or ideas and to learn how to express, clarify, and organize content.

243
244

Chapter 12
Redesigning a Foreign
Language Course With
the Help of AI:
Benefits and Challenges

Natalie Khazaal
https://orcid.org/0000-0002-7430-9794
Georgia Institute of Technology, USA

ABSTRACT
This chapter evaluates the use of AI for redesigning a foreign (Arabic) language course to significantly
incorporate several SDGs. The course provides conditions for experiential learning where students ex-
amine their impact on the planet, make meaningful improvements to their lifestyles to lower their carbon
footprint, and grow as thoughtful global citizens. It also stimulates students to reflect on the differences
between Western and Arab countries’ engagement with sustainability goals through real-world scenarios.
The analysis focuses on the positive contributions and challenges that AI presents toward the redesign-
ing goal. In particular, it explores how using AI technology in class and for creating course materials
affects HIPs elements: significant time on task; frequent, timely feedback; substantive interactions with
faculty, peers, and diverse people and ideas; structured reflection and integration of learning; real-
world applications; public demonstration of competence; significant learning elements: foundational
knowledge, application, integration, human dimension, and learning to learn.

INTRODUCTION

Although the neural networks (transformers) technology used in most recent artificial intelligence (AI)-
assisted tools only took off around 2017, AI has spread in healthcare, business, science, entertainment,
agriculture, and education, and is expected to eliminate many current jobs as well as create future ones
(Samochowiec, 2020; Davenport & Ronanki, 2018; Manyika et al., 2017). In a knowledge-based society,

DOI: 10.4018/979-8-3693-0872-1.ch012

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

Redesigning a Foreign Language Course With the Help of AI

AI is becoming a tool of tremendous importance for students’ future careers. And debates about its best
uses are becoming more prominent.
Debates around the educational uses of constantly evolving technology more generally have been
raging for decades (Zawacki-Richter et al., 2019). While no one questions the need to apply technology
in education, debates have turned to the benefits and challenges of specific technology, especially how
different disciplines can best incorporate particular AI tools in the curriculum. Any time educators test
latest AI tools in the classroom, students increase their AI literacy (Almelhes, 2023; Educause, 2018;
for AI literacy see Burgsteiner, Kandlhofer, & Steinbauer, 2016; Kong, Cheung, & Zhang, 2021; Ng et
al., 2021). Soon, classrooms will most likely be unthinkable without some use of AI. According to Xu
(2020), instructors who know how to use AI will likely replace those who don’t. This prediction captures
one of the most significant recent trends in education to orient toward incorporating AI and the increased
demand it places on instructors’ investment in their own professional development.
But is AI important to the classroom only as a skill set for employment after graduation or for instruc-
tors’ job security? Why should instructors invest time and effort to research and develop educational cur-
ricula that increasingly incorporate AI? Will AI solve important problems in education? Two important
problems in education that concern this chapter are first, how to make learning, particularly language
learning, effective and second, how to make learners’ experience engaging. Indeed, AI (used together
with older technology applications) promises to make the process of learning more effective (Ng et al.,
2022; Fan et al., 2021; Arnold & Pistilli, 2012), to improve current learners’ experience through greater
personalized engagement (Cavalcanti et al., 2021), and to make educators’ job more efficient (Vazhayil
et al., 2019). As reported in multiple studies, after using AI, learners improve their language abilities
and attitudes. They also perceive AI as “effective, efficient, accurate, easy to use, and useful/helpful for
language learning,” and report “having interesting, enjoyable, and satisfactory experiences with these
tools” (Woo & Choi, 2021, p. 1787).
Developers of AI for language learning have invested in tools that bypass in-person human instruction
in classroom settings, deploying online AI chatbots and aps like ChatGPT, Bing AI, Bard AI, Duolingo,
Rosetta Stone, Phase6, Andy, Lanny (Eggbun), Babbel, Bisuu, Mondly, Memrise, Kommunicate, Na-
Takallam, Yalla!, etc. Although Duolingo and Rosetta Stone were built on traditional machine learning
(ML) algorithms in natural language processing (NLP) that preexisted large language models (LLMs),
recently they have started adding LLM-based assistance. And even the obsolete translation models for
language learning on which Dulingo is based (Almelhes, 2023) may offer learners materials tailored to
their individual progress as well as personalized conversations that mimic native speech with tips about
grammar, vocabulary, and cultural context. Yet, AI chatbots and aps are not sufficiently advanced to
guarantee success without human input, which makes them useful as an added bonus to college courses
(Almelhes, 2023) instead of replacing such courses.
Instructors remain a main conduit for language learning, with many having a strong desire to adopt
AI tools not just as an added bonus but in more integrated ways that address the two issues of effective
and engaging language learning experience. However, there is a large gap between instructors’ grasp of
AI’s potential and their understanding of the appropriateness, utility, and limitations of adopting specific
AI tools (Almelhes, 2023). Indeed, there may be a single comprehensive review of AI tools for language
learning, spanning between 2017 and 2020 (Woo & Choi, 2021). Its authors describe their main con-
cerns about instructors’ insufficient knowledge of AI tools and the resulting lack of preparation about
how and which tools they can use “to generate personalized and customizable learning experiences for
the purposes of optimizing language learning by increasing autonomy, motivation, engagement, and ef-

245

Redesigning a Foreign Language Course With the Help of AI

fectiveness” (p. 1784). They also discovered that the majority of research published on how to use AI in
foreign language learning took place in Asia, is about learning English, focuses on skills like speaking,
listening, writing, and pronunciation, targets university students, and more often explores beginner learn-
ers. Given this gap in literature, it is beneficial to explore how AI can be adopted in languages other than
English such as Arabic, and for learners beyond the beginner level, which is the focus of this chapter.
In general, when most instructors begin researching the use of AI in foreign language learning, they
tend to made little distinction among terms like Intelligent Computer Assisted Language Learning
(ICALL), NLP, NNs, chatbots, and intelligent tutoring systems. So where does a foreign language in-
structor start if they would like to incorporate appropriate AI tools to boost student learning, motivation,
and satisfaction with the learning process? What tools are appropriate for elementary versus intermediate
versus advanced levels? Are all AI tools as effective for harder languages like Arabic and Russian versus
easier languages like Spanish and English for example? What can AI tools do and for what shouldn’t
they be utilized? What usages will enhance learning outcomes and what might undermine them? And
how can AI tools be applied support and advance any number of other goals that instructors might have
like framing the learning process around experiential learning, HIPs, or the SDGs?
This chapter is a case study focused on the experience of redesigning a language course for university
learners of Arabic in the US. It sets out to explore how to integrate AI to make language learning effec-
tive, to make learners’ experience engaging, and to support and advance other central curricular goals
like experiential learning, HIPs, or the SDGs. First, it explores several methodological axes on which
the course is structured, starting with the selection, testing, and evaluation of the AI tools. The next
three sections explore how AI can aid curricular goals related to experiential learning and High-Impact
Practices (HIPs), including UN’s Sustainable Development Goals (SDGs) in (language) learning, and
goals specific to the field of teaching Arabic. The discussion section analyzes and compares four types
of specific examples for engaging the language classroom with AI, while the conclusion section sum-
marizes the benefits and challenges of using AI in the language classroom.

EXPERIENTIAL LEARNING AND HIPS

Experiential learning is learning by doing (Dewey, 2023; Kolb, 1983). According to experiential learning
theory, the experience of learning to do something new is an optimal learning strategy. Learners engage
in a new experience, reflect on its aspects and meaning, adopt new concepts and methods based on this
experience, and apply them to their lives. Experiential learning is beneficial as learners remember new
concepts and methods much more vividly and lastingly when they try them out. It typically enhances
cooperative attitudes and motivation, and thus better prepares learners for the future. Experiential learn-
ing is a type of high-impact practice (HIP). HIPs are program designs and pedagogies that demonstrate
great student involvement and success across diverse populations, for example, capstone courses, col-
laborative projects, first-year seminars, internships, service learning, writing-intensive courses, etc.
(Kuh, O’Donnell, & Schneider, 2017; Kuh & O’Donnell, 2013; Kuh, 2008). The benefits are roughly
summarized as better grades, higher retention, and higher graduation rates (Brownell & Swaner, 2010).
While these are primarily institutional practices (Fink, 2016; see also Fink, 2013), the redesign of this
Arabic course required to focus on the following HIPs elements (high-impact teaching practices) as-
sociated with long projects: significant time on task, frequent, timely feedback, substantive interactions
with faculty, peers, and diverse people and ideas, structured reflection and integration of learning, real-

246

Redesigning a Foreign Language Course With the Help of AI

world applications, public demonstration of competence, use of AI tools, research on sustainability in

understudied areas (Middle East).
AI can play a significant role in enhancing experiential learning by providing personalized, adaptive,
and immersive experiences. For instance, AI can also analyze individual learning styles, preferences, and
performance data to create personalized learning paths. This ensures that learners engage with content
at a pace and in a manner that suits their unique needs. AI-driven tutoring systems can provide real-
time feedback and guidance during experiential activities. When such activities involve cross-cultural
interactions, AI-powered language translation tools can facilitate communication, contributing to a more
inclusive and culturally sensitive learning environment. AI can power interactive learning platforms that
simulate real-world situations, allowing learners to apply theoretical knowledge in practical contexts.
These platforms often incorporate gamification elements to make experiential learning more engaging.

THE VALUE OF THE SDGS IN (LANGUAGE) LEARNING

In 2015 the UN adopted the 2030 Agenda for Sustainable Development which lays out the following 17
Sustainable Development Goals (SDGs):

Figure 1. United Nations’ Sustainable Development Goals, UNDP

Integrating the SDGs into language education offers students a context-rich learning experience beyond
linguistic proficiency that aligns language acquisition with global awareness and social responsibility.
This approach fosters critical thinking, empathy, and a sense of responsibility, empowering learners to
engage with real-world challenges. This interdisciplinary approach prepares students to be global citizens
who can navigate linguistic and cultural diversity while contributing to the broader goals of social and
environmental sustainability.
AI-created materials can significantly enhance student engagement with the Sustainable Develop-
ment Goals (SDGs) in a language class by providing dynamic, interactive, and personalized learning
experiences. For example, AI tools can generate diverse learning materials, including videos, podcasts,
and infographics, presenting information on the SDGs in various formats. This caters to different learn-
ing preferences and enhances engagement by offering a multimedia learning experience. Class work
with products created by AI could serve as scaffolding by familiarizing students with the existence

247

Redesigning a Foreign Language Course With the Help of AI

and capabilities of AI tools they later use to create their own SDG-related projects. If instructors are
comfortable with that, AI can also assist in generating prompts for project-based learning activities that
involve researching, presenting, and discussing topics related to the SDGs. This approach encourages
collaborative learning and empowers students to apply language skills to solve real-world problems.
Infographics or other material created with the help of AI can serve as a base for creating multiple lan-
guage games, the questions for which could be drafted by chatbots for the instructor to work from (see
Alzahrani & Alhalafawy, 2023; Mageira et al., 2022). For advanced learners, AI can simulate virtual
language experiences with native speakers discussing sustainability topics. These simulations create
a more immersive language learning environment, allowing students to apply their language skills in
practical scenarios. Image- and video-based AI-generated content can incorporate cultural nuances and
context relevant to the regions associated with the SDGs. This connection to real-world cultural contexts
enhances language learning by providing students with a deeper understanding of the global implica-
tions of sustainable development.

STATE OF THE FIELD OF TEACHING ARABIC

With over 300 million speakers worldwide, Arabic is the fifth most spoken language in the world and the
eighth most commonly-taught language in the US with 31,500 university students (US census).1 Arabic
enrollments jumped 1,600 percent after 9/11, 2001 but started rolling back slowly a decade later (MLA
data, see Figure 2), and then plateaued before the COVID 19 pandemic with around 150 US institutions
that offer Arabic (Abu Melhim, 2014). According to Awad Awad (2023), director of the Salaam MENA
Cultural Center at the University of Illinois, Urbana-Champaign, currently Arabic programs suffer from
low student retention beyond the introductory level, low-enrollment class cancelations, low student
proficiency, old curricula, and unrealistic expectations.

Figure 2. Arabic language enrollments for 1998, 2009, 2013, and 2016. MLA data.

Indeed, Arabic diglossia (using two varieties, one spoken, one written, simultaneously) has been a
serious obstacle to learners. And so has been the lack of multiple, easily accessible authentic materials
at the lower competency levels. When available in the future, AI tools can potentially help solve this
incurable issue by adapting any written or oral content to a personal or group learner level. AI-powered

248

Redesigning a Foreign Language Course With the Help of AI

platforms can adapt content difficulty and learning activities based on the learner’s proficiency level,
ensuring that the material remains challenging but not overwhelming. AI could also recast content from
the spoken variety to the written and vice versa as an essential basis for any Arabic related application
in order to help learners improve their weaknesses and develop multiple competencies. And why stop
at only 1 Arabic spoken variety rather than include over 20, each associated with a different country?
In this sense, AI algorithms, which can analyze individual learning progress and preferences to create
personalized learning paths, should potentially strengthen learning effectiveness by focusing on areas
where learners need improvement and progress at their own pace and level. AI-driven chatbots can
provide tutoring through immersive language experiences by engaging learners in conversations, offer-
ing real-time feedback on pronunciation, grammar, and vocabulary usage. AI technologies with voice
recognition capabilities can assess and provide feedback on learners’ pronunciation, helping them refine
their speaking skills and sound more natural.
AI can also gamify language learning, creating interactive and engaging experiences that motivate
learners to practice Arabic in a playful and enjoyable way, as this field for Arabic is perhaps among
the lowest served fields among all other global and many non-global languages. And last, AI tools can
incorporate cultural nuances and context into language lessons, providing learners with a deeper under-
standing of the cultural aspects of Arabic language and communication.
The options are much more but to sum, the use of AI to revamp Arabic language courses is both
innovative and timely, aligning with the increasing interest in technology integration in education. The
rest of the chapter offers a valuable overview of various AI tools applicable to language education,
benefiting educators seeking to incorporate technology into teaching. The inclusion of a case study on
redesigning an Arabic language course provides practical insights, making the concepts discussed more
instructive for readers.

METHODOLOGY

In the fall of 2023, a team of a hired student assistant and a faculty member tested a number of AI tools
for the college-level Arabic course taught. The course uses ‘Arabiyyat al-Naas, the latest edition of a
textbook published by Routledge. There were 18 enrolled students in the course, all in their 20s. Their
background ranged from heritage students who had never taken Arabic courses at different skill levels in
Arabic, to others with middle and high school Arabic, to Muslim students with some Quranic Arabic, to
non-native speakers who had taken all previous courses in the Arabic sequence. None had any previous
Arabic courses that incorporated AI tools.
AI tools were selected based on how well they help students develop language proficiency simulat-
ing the course materials, particularly reliance on audio-video content and embracing of diglossia as an
integral part of learning Arabic (with a practical focus on communication skills through speaking in an
Arab dialect and good skills in reading and writing the standard Arabic, Fusha). This led to the narrow-
ing of the tools that were explored to visual tools, such as images and videos, and multimedia tools that
incorporate visual elements such as comic strips and again videos. Given the dependence of the redesign
of the course on a grant that required a fast turnaround of outcomes, other AI tools were excluded either
because they did not offer strong or any visual content (e.g. ChatGPT) or because exploring too many
AI tools all at once would have been unfeasible under the stipulations of the grant.

249

Redesigning a Foreign Language Course With the Help of AI

The list of AI tools were tested within minimum basic criteria such as how professional the content they
created looked, if it was visually stimulating, and if would be potentially engaging for learners. Another
criterium was if the tool handled and produced Arabic script and if it offered voiceover with Lebanese
accent (since the textbook is based on Lebanese Arabic and Lebanese culture). One important criterium
was the AI tool’s cultural sensitivity, for example, if the images of people or the inside and outside en-
vironments looked like they came from Lebanon, or if they produced Gulf- or Western-looking options.
Only the tools that produced the best results based on the above criteria were used to create the resulting
learning materials. As shown in Table 1 these are: GenCraft for creating AI-generated images, Pictory
for creating AI-generated videos, AI Comic Factory (in combination with another tool such as Canva)
for creating AI-generated comic strips, MapFight for creating AI-generated geographic comparisons,
and Quizlet and Kahoot for learning games and quizzes. These tools are recommended here because
they enhanced learning effectiveness student engagement and they also were helpful in addressing goals
related to incorporating experiential learning, HIPs, and the SDGs.
Materials generated with these tools were incorporated into the Canvas learning management system
(LMS). They were accessible to students on Canvas during class within class activities as well as after
class in assignments, projects, or posted keynote presentations.

Table 1. List of AI algorithm/program/tool tested for college-level Arabic

Time to Recommend? Yes/

Product
Name of AI Algorithm/Program Purpose for Use Accomplish No
Created
Goal Why?
MapFight Compare sizes of Geometric Seconds-
1 Yes
https://mapfight.xyz geographic areas image minutes
AI Comic Factory, in combination with
Illustrate Yes
another tool such as Canva
2 vocabulary, idea, Comic strips Hours Exceptional visual
https://huggingface.co/spaces/jbilcke-hf/ai-
topic, grammar tool
comic-factory
Yes
Gives several options
GenCraft Text (prompt) to and each can be used
3 Image Seconds
https://gencraft.com/generate image generator as another instance/
angle for the same
entity
ArtBreeder Creative mixer of
4 Image Seconds To some degree
https://www.artbreeder.com/ image and prompt
Yes
AI-enhanced
personalized
Quizlet AI-enhanced Tests, quizzes, quizzes practice
5 Minutes to hours
https://quizlet.com learning platform learning tools tests, expert-written
homework solutions,
transformative AI
study tools
Yes
AI-enhanced game- learning
Kahoot AI-enhanced learning
6 based learning games, trivia Minutes to hours
https://create.kahoot.it games or trivia
platform quizzes
quizzes
Pictory Text (prompt) to Yes, with caution
7 Video Hours
https://pictory.ai/ video generator about Western bias

250

Redesigning a Foreign Language Course With the Help of AI

Finally, gathering and analyzing student feedback for the success of the materials created by the AI
tools took two approaches. The first was immediate oral feedback solicited from the students by the
instructor usually at the end of class or occasionally after the use of the particular tool. This approach
was effective in quickly improving materials for the next use of the tool, usually within a class or two.
The second approach was a survey administered at the end of the semester. It was used to gain a broader
picture of the usefulness of the incorporated AI tools as a group, rather than a singular tool, which is
effective in taking stock of the general use of AI in language learning.

DISCUSSION

Four Examples for Learning Effectiveness and Student

Engagement in the Foreign Language Classroom With AI

Comparative Map Generators

Foreign (and even many heritage) learners of Arabic often lack a geographical sense of the Arab world,
its countries, and their relative prominence be it in terms of land size, population, or economic output.
Since there are 22 countries in the League of Arab States, a learner may need visual help to grasp these
parameters. One tool is MapFight, which creates maps that compare different geographic areas. For
example, when the students in this class learned about SDG 1: No Poverty and reviewed comparative
adjectives, an image created by MapFight helped them form a fast, clear, and visceral sense for the rela-
tive size difference between a) California and Lebanon, or b) Sham (the Levant) and Sudan, for example.
Such sense then helps them become better equipped to understand more qualitative differences between
them, such as available arid land, natural resources, population economic opportunities related to land,
poverty, etc. It also helps learners practice grammatical structures like comparatives and superlatives in
a meaningful way (which depends on the specific class and topic).

Figure 3. MapFight images that visualize the relative size difference between a) California and Lebanon
or b) Sham (the Levant) and Sudan

251

Redesigning a Foreign Language Course With the Help of AI

Specific tools like MapChart (https://www.mapchart.net/) allow to create maps for different countries
or territories, color them in one or multiple colors, add country names, city names, borders, etc. Any
number of Arabic words or names could be added to such maps to respond to specific linguistic and
cultural learning goals.

Figure 4. MapChart image of Arab countries and territories

While MapFight and MapChart are free, there are a number of paid map generators that can offer a
whole new way of teaching a course from a visual perspective. Those could be used to create or exemplify
scenarios, fantasy worlds or living spaces created specifically for the class, or campus or other maps to
help with any number of tasks such as giving directions, navigating space, etc.

Figure 5. Images by 3d Map, Inkarnate, and MapMe

Comic-Strips Generators

The tool students liked the most was comic-strips generators. After testing several different tools, AI
Comic Factory was selected as the best tool. Three AI-driven art generators were tested before it—Deep-
Dream, GenCraft, Runway ML, and Artbreeder—to generate background images or design elements

252

Redesigning a Foreign Language Course With the Help of AI

that can be incorporated into comic-strip panels. They were given the same prompt that was developed
for the in-person class session, which coincided with Halloween. The prompt built on an activity from
an earlier class in which the students were split into teams to role-play a situation with three characters:
Rima (a Lebanese heritage student on a year abroad at AUB, Lebanon), her school mate Lina (born and
raised in Beirut), and Lina’s “tetta” (grandmother) with whom Lina lives. Rima is visiting tetta to talk
about moving in with her and Lina. During the role play, the students decided that Rima tattled on the
secretly smoking Lina and tetta kicked both of them out, which meant that they would need a new place
to live. After class, the following prompt was created to continue developing this story and also make it
relevant to the specific cluster of lessons from the textbook that were about apartment hunting and rentals:

Two Lebanese college students Rima and Lina are looking to rent an apartment together. The first
apartment they see is too dark because it doesn’t have electricity and it’s cold in the winter. The second
one they check out is on the 10th floor and doesn’t have running water or elevator, so they need to lug
up bottles of water. The third one is perfect but comes with a ghost called Marwan. Marwan is friendly
but can’t stop talking. Rima and Lina discuss their options and choose #3. Now they need ghost busters.

The prompt was created in English to test the art with empty speech balloons that would be filled in
later with Arabic text. Here are some of the results:

Attempt 1: The first AI tool only generated pictures but not comics when fed in the prompt. As a result,
the student assistant split the story into couples of sentences and ran it again. But the tool generated
girls that looked like different people in each picture.

Figure 6. Images by DeepDream

253

Redesigning a Foreign Language Course With the Help of AI

Attempt 2: GenCraft and ArtBreeder were then tested with slightly rewritten prompts. While GenCraft’s
art is most like that of comic-strips, it still generates girls that look like different people in different
panels. On the other hand, ArtBreeder’s girls looked very consistent but it didn’t generate adequate
panels with three different apartments and a ghost.

Prompt 3 & 4:

Figure 7. Two Lebanese college girls looking to Figure 8.

rent an apartment in Beirut

Prompt 5: Comic strip showing the apartment, the two Lebanese college girls annoyed by a ghost
who talks too much.

Figure 9. Images by GenCraft Figure 10. Images by GenCraft

254

Redesigning a Foreign Language Course With the Help of AI

Figure 11. Images by ArtBreeder

Figure 12. Images by ArtBreeder

255

Redesigning a Foreign Language Course With the Help of AI

Attempt 3: The last tested AI tool was AI Comic Factory, which proved the winning tool if used in com-
bination with another tool such as Canva to organize the images. AI Comic Factory was consistent,
generated our story exactly following the prompt, had great visual appeal, and the panels looked
professionally designed.

Figure 13. Images by AI Comic Factory (for individual panels) in combination with Canva (to compile
the best matching panels)2

Video Generators

The video generators were probably the most challenging tool to use, as a result more options were sought.
The first issue was learning how to combine the video images by Pictory with voice over created by a
separate tool. Since the video had to be in the Lebanese dialect, which is the basis for the textbook, the
two best voice-over choices found proved suboptimal—one was in the standard literary Fusha Arabic with
a Lebanese accent (which is different from spoken Lebanese dialect), the other in spoken Syrian (again
different from the typical Lebanese). The third option was for the student assistant, who was Lebanese,
to record himself narrating the video. While this addressed the issue with the language variety, it created
a new issue which many video makers have faced—“the non-professional narrator.”
The second issue was that the video generator created scenes with Western-looking characters de-
spite multiple tweaks to the prompts to create “Arab,” “Lebanese,” “Middle Eastern,” etc. spaces and
characters. In the end, the AI-generated video footage was cut into inappropriate scenes (which were
discarded) and appropriate scenes which were stitched up to outside images or short scenes. That took a
lot of time, editing, and generating multiple versions for a less than ideal result. That’s why videos that
were 5-15 seconds turned out to be much better products than those that were longer (the latter brough
in more instances of bias).

256

Redesigning a Foreign Language Course With the Help of AI

Figure 14. Three most important SDGs for Figure 15. The Lebanese cedar and climate change
Lebanon Videos by Pictory https://pictory.ai/

Image Generators

Images are an important part of illustrating many concepts and vocabulary items not only in the lower
but also at higher levels of learning a foreign language. They make cultural specificities easier to grasp.
While GenCraft was not first choice as a comic-strip generator, it is an excellent place to generate images
for any language classroom and was especially sensitive to cultural differences. In addition, there are a
number of other simpler drawing generators that are easy to work with and can serve as a counterbal-
ance to fill in spaces of handouts or presentation slides that are already showcasing more developed
images. For example, AutoDraw turns a rough sketch into a technical drawing, while providing multiple
suggestions to choose from.

Figure 16. Lebanese grandma

257

Redesigning a Foreign Language Course With the Help of AI

Figure 17. Lebanese college student

Figure 18. AutoDraw

Images by GenCraft

Students were particularly engaged with the AI-generated images of the two “mascots” for the course,
one male who was named “Kareem,” the other female called “Reema,” both engineering students at
Georgia Tech, Atlanta. The following prompt was used:

• 2 cartoon characters, male & female

• Lebanese

258

Redesigning a Foreign Language Course With the Help of AI

• 20-25 years old

• Enthusiastic
• Optimistic
• Happy
• One has headphones, loose on the neck
• The other wears a beanie
• One wears glasses
• No religious symbols
• Clothes: for millennials
• Colors for clothes: pastel green, blue, yellow

While the tool never placed the headphones on Kareem’s shoulders, or created full body images in
different postures by the same characters, the results of front and side faces were very satisfactory. The
images were used throughout the semester to engage the students by framing multiple activities such as
competitions between “Teem Kareem” and “Team Reema” on topics like “Should the job of househu-
sband become widely acceptable and practiced in the Middle East” (debate between the two teams) or
“Which important clean energy sources are currently most in use (choose from wind, water, sunlight,
geodesic)” (ranking competition among teams) or “Should Reema live with a Lebanese family during
her summer abroad in Beirut, or not—perspectives by Reema and her new boyfriend Kareem” (discus-
sion and persuasion activity among teams), etc.

Figure 19. Mascot images, Kareem Figure 20. Mascot images, Reema

259

Redesigning a Foreign Language Course With the Help of AI

Other AI tools like Kahoot and Quizlet were also used for multiple purposes like vocabulary review,
vocabulary competitions, testing grammar skills (multiple-choice questions, yes/no questions), etc.

Student Feedback

At the end of the semester, the students were administered a written survey regarding their experience with
the inclusion of AI, the SDGs, and experiential learning. Here are the results of the survey: The majority
of the students described their experience with this course as “enjoyable,” satisfactory,” engaging,” and
“positive.” They said they enjoyed the AI-generated or AI-assisted materials because they were “original”
and provided “substantial amount of learning aid.” According to the surveys, the students’ preferred tool
was the comic strips, the mascots, and the other images, as well as how these were organized within the
structured keynote pair, small group, team, and whole class activities. The surveys indicated that the
students found the AI tools “helpful” and “effective” as they “enhanced” students’ various “skills” in
Arabic and the “interesting visual materials” helped visual learning and made for “better class content.”
This resulted in “satisfaction” with the course, where all but one student “loved” the course, as their
comments in the surveys showed. The single student who didn’t write they loved the course shared that
they felt it was “catering to heritage students” and they had somewhat harder time keeping up. When
asked what aided their language acquisition, some students mentioned AI tools, while others related
various other aspects of the course, including class activities, the SDGs, projects, emphasis on producing
language, and the textbook materials. The student-observed benefits of using AI tools in this course, as
demonstrated by the surveys, were confirmed in the regular Course Instructor Opinion Survey (CIOS)
comments administered at the end of the semester, e.g.,

Dr. Khazaal has tried some new ways of language learning that I think worked wonderfully. First and
foremost, the original resources that Dr. Khazaal created using AI tools were absolutely amazing. I have
to say that was my favorite part. The comic strips were fun and engaging because they were made at an
appropriate level (challenging but doable) and, of course, they fit well in our class because they were
specially made. The emphasis on speaking by doing oral exercises was also very helpful. Lastly, the
projects were a good opportunity to practice speaking skills with full length presentations.

The student surveys demonstrate that the incorporation of AI-generated materials aids learning and
the acquisition of various language skills, making it a tool for increasing effective learning. The surveys
are also a testament to the substantial level of engagement with the learning process that the students
attributed to AI tools, especially visual materials and, unanimously, the comic strips. Because of the stu-
dents diverse background and skill levels, the visual aids including the comic strips provided an engaging
outlet for practice. Surveys provide a valuable assessment of the curricular aspects, which instructors
and administrators can use to make informed decisions about educational programs. Since surveys can
identify what students deem important, they also show where schools should spend their money. In this
case, students’ surveys can be interpreted as a signal that school investment in instructors’ support and
professional development in the field of using AI tools can potentially result in greater effectiveness of
the learning process and in students’ greater engagement with it.

260

Redesigning a Foreign Language Course With the Help of AI

Outcomes Analysis

According to Tom Kashdan (2009), engagement is the first step toward real learning. Three key principles
that optimize student engagement are emotions, building a sense of community, and helping students
create meaningful and relevant narratives around the content. Emotions are strong motivators because
they use neuropathways dedicated to survival, while we learn only things that we care about (Immordino-
Yang, 2015). Sarah Rose Cavanagh’s (2020) tip on how to harness the power of emotions to produce
student engagement is to use emotional hooks such as a relevant controversy, a provocative question, an
unsolved mystery, or a humorous meme. Story-telling, as our “most natural form of thought” (Schank
& Abelson, 1995), chunks information and optimizes memory space, allowing students to focus their
attention on what is important. It also helps them understand better by organizing content into meaning.
A successful Arabic course redesign can benefit greatly from incorporating AI tools as a remarkable
vehicle for delivering all the above hard-core principles of engagement. Mascots’ images were effective
in engaging students in debates relevant to their own lives such as navigating friendships and romance
within the specificity of Arab cultures, and appreciating the continuous changes in traditional male and
female behaviors and attitudes surrounding household duties and parenting. Comic strips were just as
effective in engaging students in story-telling that helped them relate the subject matter to the holiday
calendar of their own society as well as to the SDGs and economic realities in the Middle East. In ad-
dition, they invited students to identify with the main characters who were of the same age and going
through similar student life experiences. This created space to relate their own visions about the comic
strips, tell stories from their lives, and deliberate broader social issues creatively applying the textbook’s
vocabulary and structures in meaning real-world scenarios (albeit imagined).

CONCLUSION

Benefits and Challenges of Using AI in the Language Classroom

This chapter explored a case study of redesigning an Arabic language curriculum to incorporate AI
tools in meaningful ways that benefit both the effectiveness of the learning process and the engagement
of the students with the textbook materials and broad issues of importance like sustainability. While
this process created many positive outcome, thus offering potential benefits that could be replicated, it
also showed areas with challenges that those interested in adopting AI for a language class should heed.

Benefits

Personalization. One of the key benefits of incorporating AI tools in the language classroom for this
case has been the personalization of the learning process. We can think of this through multiple
perspectives. For example, on an individual basis, tools like ChatGPT can serve as conversation
partners and help students practice the new language at their specific level in writing or speaking
and adapt to the student’s pace and topics of interests. Other tools like Kahoot and Quizlet can
serve the student to practice vocabulary displaying flashcard decks in different order and offering
practice on grammar in a question format that students can retake in order to learn better. We can
also think of personalization on a group basis as well, such as the specific group of students who

261

Redesigning a Foreign Language Course With the Help of AI

are taking the class this semester with their interests, levels, and needs. For example, while Kahoot
can be a truly individualized tool, it also lends itself well to seeing the strengths and weaknesses
of this particular group of students if the tool is used during class. The 2023 Ghaza war took place
during this course, which made some of the planned SDGs somewhat irrelevant. Ultimately, it was
pivotal to shift toward SDG 16 “Peace, justice, and strong institutions” and use AI tools to imagine
scenarios for ending the conflict and establishing lasting peace and justice afterwards. Another
way in which AI helped personalize learning for this group was continuing the story lines students
created during class into AI products, for example the ghost story created after Reema and Lina
were thrown out by grandma (tetta). In this way, every class can have its personal mythology.
Instant feedback. In either case (individual or group), AI tools provide instant feedback. They can assess
individual students’ language skills in real-time, providing feedback on pronunciation, grammar,
and vocabulary. This instant feedback helps students identify and correct errors promptly, enhanc-
ing the learning process. AI tools used in class also give the instructor quick statistical information
about how many students have grasped or mastered a language item, as we do with Kahoot for
instance. Pausing to explain the issue and discuss the correct answer offers students immediate
feedback and an opportunity to improve accuracy. It also lets them see that they are not the only
student who made this mistake. The non-judgmental nature of AI feedback can create a supportive
learning environment when a student works on their own, or when the tool provides anonymous
feedback while working in class. As a result, students often feel less anxious about making mis-
takes, as they know they can receive constructive feedback without judgment, fostering a positive
attitude towards language learning.
Redefined instructor role. It is challenging to completely redefine the instructor’s role given how time
consuming this is and how rooted such role is in current educational settings. However, limited
redefinitions may lead to positive outcomes. For example, when it comes to assessment and feed-
back, typically provided by instructors, AI tools may handle certain aspects, including giving instant
feedback. This function is still in its infancy; however, long-term, instructors can shift their focus to
more personalized instruction, addressing individual needs, and providing additional support where
required. They can also use AI-generated data to identify patterns, assess teaching strategies, and
make informed decisions to enhance the overall learning experience for students. This redefined
instructor role emphasizes mentorship and guidance.
Instructor creativity enhancement. AI tools can also enhance instructor creativity, which is their most
useful function for me as of today. For example, they can assist in creating interactive and adap-
tive learning materials, such as language games, quizzes, and activities. They can also be utilized
to generate visuals, infographics, or animations that help illustrate complex language concepts,
which was accomplished in this course with the help of AI Comic Factory, GenCraft, MapFight,
Pictory, etc. Visual aids can enhance understanding and retention, making language lessons more
accessible and enjoyable. Furthermore, AI tools can curate and analyze current news articles, social
media, or other online content in Arabic, allowing teachers to incorporate real-world and culturally
relevant materials into lessons. This connection to current issues makes language learning more
dynamic and practical. Using AI tools, then, can make language learning more enjoyable and cater
to different learning styles, making the classroom experience more engaging.

262

Redesigning a Foreign Language Course With the Help of AI

In sum, incorporating AI tools in the Arabic language classroom has the potential to revolutionize the
learning experience, making it more personalized, adaptive, and engaging for students while providing
valuable support to teachers in their instructional roles.

Challenges

Today, AI algorithms and programs may be useful teaching and learning tools, however, they also have
a number of small and big challenges.

Financial support. On the small side, many of them are associated with costs that allow instructors not
only to test them but also to use them continuously. Since each AI tool comes with its own cost, no
matter how small, using several tools adds up. New tools or improved versions appear constantly,
so the best solution is institutional support for language AI tool use, either covering the costs of
individual instructor use or incorporating some of the most useful tools into web-based learning
management system (LMS) like Canvas, Moodle, Blackboard, etc.
Time investment. Another challenge that can be tackled relatively painlessly is the lack of instructor
familiarity with AI tools that might be useful to language instructors. This requires time investment
to explore which AI tools are adequate and effective for which course. Again, the solution to this
is better tackled on an institutional level by creating professional development programs involving
webinars, group discussions, or sharing best practices by experienced inside or outside practitioners.
That could become part of instructors’ service load and help lessen the steep learning curve due
to the proliferation of different tools and updated version, and to the constant need for instructors
to reinvent their teaching with technology.

And then, there are harder challenges to solve.

AI tool performance. Currently, most AI tools are not able to address the long list of learners’ and
instructors’ needs, especially since no one tool can fit all. This case study showed that video and
comic-strip editors currently require that many functions be outsourced to other tools and/or to
human labor if instructors want to succeed in using them. The solution here is both technical and
financial. On the technical side, we expect that with time AI tools will improve, so waiting might
be the best strategy. On the financial side, institutions should invest in hiring student assistants to
work with instructors on the creation of materials with AI, or giving instructors personal grants or
course buy-outs to cover their efforts.
Assignments and assessment. Another serious issue is the ease with which AI tools allow undetectable
cheating, avoiding doing homework, and subverting the learning process for the sake of receiving a
(good) grade. During this attempt to redesign the Arabic course, it was constantly clear how many
students attempted this. Therefore, we need to seriously rethink student assignments and assess-
ment. We are entering a new age of learning.
Boredom/learning preferences. An unexpected problem for this redesign is how quickly students get
bored with one particular tool, or how the tool’s use may not have matched well their learning
preferences. When they were first asked to do a competitive, team Quizlet game on vocabulary, the
activity was planned as a single game. However, the students demanded to repeat it four times with
different teams for the sake of winning. On subsequent trials, there was considerably less enthusi-

263

Redesigning a Foreign Language Course With the Help of AI

asm and this tool is now being used once every three-four sessions. The solution here is of course
to have more research that results in insights into how technology and its fast-paced innovation
affects the expectations of the human brain for engagement, entertainment, and stable attention.
This might also indicate general issues of gamification in learning, not so much using a specific
tool. According to the narrative presented here, the students don’t seem to enjoy, and instructors
may need to find out how to avoid the strict “win”/”lose” aspect of the tool to enhance engagement.
Ethics. The last challenge discussed here is lack of appropriate ethical consideration when AI tools are
developed for public use. Students frequently fail to notice bias or intellectual property issues (Gong
et al., 2020). For example, some suspect that AI can cultivate notions that perpetuate colonialist
world views (Williansom & Eynon, 2020). In this case study it was the Western bias of the video
generators. In addition, AI may have negative effect on instructors if it is used to measure their
performance for punitive purposes (Selwyn & Gasevic, 2020), or on students if it is used to profile
or dox them (Selwyn, 2019).

We don’t know how AI will ultimately impact education, but we need to pay attention. Instead of just
utilizing AI tools to teach foreign languages, we need to critically reflect how inclusive, fair, transparent,
and ethical these tools are (Hagendorff, 2021; Zawacki-Richter et al., 2019).

Limitations

While the results in this study clearly show that AI can benefit a foreign language classroom, the small
sample size of 18 enrolled students could be a limitation. Most language courses are small, ranging from
5 to 25 students. However, replicating this study by adopting the suggested AI tools in other classrooms
could strengthen the study’s conclusions.
Furthermore, some courses in languages other than Arabic might have already incorporated more AI
tools, perhaps even those proposed here, and thus this chapter would benefit them as a confirmation of
the tools’ utility, rather than a suggestion for new tools.
Last, AI tools are in constant flux, with new one appearing fast and published ones receiving fre-
quent modifications or new versions. As a result, in addition to relying on this chapter’s research, one
should also do supplementary exploration of the latest AI tools that might be applicable to the foreign
language classroom.

REFERENCES

Abu Melhim, A. (2014). The Status of Arabic in the United States of America post 9/11 and the Impact
on Foreign Language Teaching Programs. Advances in Language and Literary Studies, 5(3), 70–81.
doi:10.7575/aiac.alls.v.5n.3p.70
Almelhes, S. A. (2023). A Review of Artificial Intelligence Adoption in Second-Language Learning.
Theory and Practice in Language Studies, 13(5), 1259–1269. doi:10.17507/tpls.1305.21
Alzahrani, F. K., & Alhalafawy, W. S. (2023). Gamification for Learning Sustainability in the Blackboard
System: Motivators and Obstacles from Faculty Members’ Perspectives. Sustainability (Basel), 15(5),
4613. doi:10.3390/su15054613

264

Redesigning a Foreign Language Course With the Help of AI

Arnold, K., & Pistilli, M. (2012). Course signals at Purdue: Using learning analytics to increase student
success. Proceedings of the 2nd international conference on learning analytics and knowledge (pp.
267–270). New York: ACM. 10.1145/2330601.2330666
Awad, A. (2023). Interview by author. MESA.
Brownell, J., & Swaner, L. (2010). Five High-Impact Practices: Research on Learning Outcomes,
Completion, and Quality. Association of American Colleges and Universities.
Burgsteiner, H., Kandlhofer, M., & Steinbauer, G. (2016). Irobot: Teaching the basics of artificial intel-
ligence in high schools. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1). Advance
online publication. doi:10.1609/aaai.v30i1.9864
Cavalcanti, A. P., Diego, A., Carvalho, R., Freitas, F., Tsai, Y. S., Gaˇsevi´c, D., & Mello, R. F. (2021).
Automatic feedback in online learning environments: A systematic literature review. Computers and
Education: Artificial Intelligence, 100027.
Cavanagh, S. R. (2020). How to make your teaching more engaging. The Chronicle of Higher Education.
Davenport, T. H., & Ronanki, R. (2018). Artificial intelligence for the real world. Harvard Business
Review, 96(1), 108–116.
Dewey, J. (2023). Experiential Education: Complete Collection: Problem-Based Learning, Pragmatic
Philosophy of Scholarship, Democracy & Education. Sharp Ink Publisher.
Educause. (2018). Horizon report: 2018 higher education edition. Author.
Fan, Y., Saint, J., Singh, S., Jovanovic, J., & Gasevic, D. (2021). A learning analytic approach to un-
veiling self-regulatory processes in learning tactics. LAK21: 11th international learning analytics and
knowledge conference, 184–195.
Fink, L. D. (2016). Five High-Impact Teaching practices (Vol. 9). Collected Essays on Learning and
Teaching.
Fink, L. D. (2016). Creating significant learning experiences: An integrated approach to designing
college courses. John Wiley& Sons.
Gong, X., Tang, Y., Liu, X., Jing, S., Cui, W., Liang, J., & Wang, F. Y. (2020, October). K-9 artificial
intelligence education in qingdao: Issues, challenges and suggestions. IEEE international conference
on networking, sensing, and control (ICNSC), 1–6.
Hagendorff, T. (2020). The ethics of AI ethics: An evaluation of guidelines. Minds and Machines, 30(1),
99–120. doi:10.1007/s11023-020-09517-8
Immordino-Yang, M. T. (2015). Emotions, Learning, and the Brain: Exploring the Educational Implica-
tions of Affective Neuroscience. Norton Professional Books.
Kashdan, T. (2009). Curious? Discover the Missing Ingredient to a Fulfilling Life. Harper Collins.
Kolb, D. (1983). Experiential Learning: Experience as the Source of Learning and Development. Pren-
tice Hall.

265

Redesigning a Foreign Language Course With the Help of AI

Kong, S. C., Cheung, W. M. Y., & Zhang, G. (2021). Evaluation of an artificial intelligence literacy
course for university students with diverse study backgrounds. Computers and education. Artificial
Intelligence, 100026.
Kuh, G., O’Donnell, K., & Schneider, C. (2017). HIPs at Ten. Change, 49(5), 8–16. doi:10.1080/0009
1383.2017.1366805
Kuh, G. D. (2008). High-impact educational practices: What they are, who has access to them, and why
they matter. Washington, DC: Association of American Colleges and Universities.
Kuh, G. D., & O’Donnell, K. (2013). Ensuring Quality & Taking High-Impact Practices to Scale. Wash-
ington, DC: Association of American Colleges and Universities.
Mageira, K., Pittou, D., Papasalouros, A., Kotis, K., Zangogianni, P., & Daradoumis, A. (2022). Educa-
tional AI chatbots for content and language integrated learning. Applied Sciences (Basel, Switzerland),
12(7), 3239. doi:10.3390/app12073239
Manyika, J., Lund, S., Chui, M., Bughin, J., Woetzel, J., Batra, P., Ko, R., & Sanghvi, S. (2017, Decem-
ber). Jobs lost, jobs gained: Workforce transitions in a time of automation. McKinsey Global Institute.
Ng, D. T. K., Leung, J. K. L., Chu, S. K. W., & Qiao, M. S. (2021). Conceptualizing AI literacy: An
exploratory review. Computers and Education: Artificial Intelligence, 2, 100041.
Ng, D.T.K., Luo, W., Chan, H.M.Y., & Chu, S.K.W. (2022). Using digital story writing as a pedagogy to
develop AI literacy among primary students. Computers and Education: Artificial Intelligence, 100054.
Samochowiec, J. (2020). Future skills: Four scenarios for the world of tomorrow. Jacobs Foundation.
doi:10.59986/WGTT6117
Selwyn, N. (2019). What’s the problem with learning analytics? Journal of Learning Analytics, 6(3),
11–19. doi:10.18608/jla.2019.63.3
Selwyn, N., & Gasevic, D. (2020). The datafication of higher education: Discussing the promises and
problems. Teaching in Higher Education, 25(4), 527–540. doi:10.1080/13562517.2019.1689388
Vazhayil, A., Shetty, R., Bhavani, R. R., & Akshay, N. (2019, December). Focusing on teacher educa-
tion to introduce AI in schools: Perspectives and illustrative findings. In 2019 IEEE tenth international
conference on technology for education (pp. 71–77). IEEE.
Williamson, B., & Eynon, R. (2020). Historical threads, missing links, and future directions in AI in
education. Learning, Media and Technology, 45(3), 223–235. doi:10.1080/17439884.2020.1798995
Woo, J. H., & Choi, H. (2021). Systematic Review for AI-based Language Learning Tools. Journal of
Digital Contents Society, 22(11), 1783–1792. doi:10.9728/dcs.2021.22.11.1783
Xu, L. (2020, December). The dilemma and countermeasures of AI in educational application. In 2020
4th international conference on computer science and artificial intelligence (pp. 289–294). ACM.
Zawacki-Richter, O., Marín, V. I., Bond, M., & Gouverneur, F. (2019). Systematic review of research on
artificial intelligence applications in higher education–where are the educators? International Journal
of Educational Technology in Higher Education, 16(1), 1–27. doi:10.1186/s41239-019-0171-0

266

Redesigning a Foreign Language Course With the Help of AI

ADDITIONAL READING

Appleton, J. J., Christenson, S. L., & Furlong, M. J. (2008). Student engagement with school: Critical
conceptual and methodological issues of the construct. Psychology in the Schools, 45(5), 369–386.
doi:10.1002/pits.20303
Finn, J. D., & Rock, D. A. (1997). Academic success among students at risk for school failure. The
Journal of Applied Psychology, 82(2), 221–234. doi:10.1037/0021-9010.82.2.221 PMID:9109280
Fredricks, J. A., Blumenfeld, P. C., & Paris, A. H. (2004). School engagement: Potential of the concept,
state of the evidence. Review of Educational Research, 74(1), 59–109. doi:10.3102/00346543074001059
Handelsman, M. M., Briggs, W. L., Sullivan, N., & Towler, A. (2005). A measure of college student course
engagement. The Journal of Educational Research, 98(3), 184–192. doi:10.3200/JOER.98.3.184-192
Kahu, E. R. (2013). Framing student engagement in higher education. Studies in Higher Education,
38(5), 758–773. doi:10.1080/03075079.2011.598505
Kuh, G. D. (2009). What student affairs professionals need to know about student engagement. Journal
of College Student Development, 50(6), 683–706. doi:10.1353/csd.0.0099
National Survey of Student Engagement (NSSE). (2021). Documenting Effective Educational Practices.
Indiana University Center for Postsecondary Research.
Schank, R. C., & Abelson, R. P. (1995). Knowledge and memory: The real story. In R. S. Wyer Jr., (Ed.),
Knowledge and memory: The real story (pp. 1–85). Lawrence Erlbaum Associates, Inc.
Skinner, E. A., & Belmont, M. J. (1993). Motivation in the classroom: Reciprocal effects of teacher
behavior and student engagement across the school year. Journal of Educational Psychology, 85(4),
571–581. doi:10.1037/0022-0663.85.4.571
Trowler, V. (2010). Student engagement literature review. Higher Education Academy.
Zepke, N., & Leach, L. (2010). Improving student engagement: Ten proposals for action. Active Learn-
ing in Higher Education, 11(3), 167–177. doi:10.1177/1469787410379680

KEY TERMS AND DEFINITIONS

AI: Stands for Artificial Intelligence. It is a form of teaching computers to think and make decisions
on their own. They can learn from information and do tasks that usually need human intelligence.
Experiential Learning: Is learning by doing. Instead of just reading or listening, you learn better
by actively experiencing and practicing things.
HIPs: Are special and effective ways of teaching and learning. They often involve students doing
hands-on projects, working in teams, or having experiences that really help them learn deeply.
LLMs: Are big computer programs that are good with language. They can understand, generate, and
work with large amounts of text. They’re often used for tasks like answering questions or creating content.

267

Redesigning a Foreign Language Course With the Help of AI

NLP: Is a form of teaching computers to understand and use human language. It helps computers
read, understand, and respond to what people say or write.
SDGs: Are 17 big goals set by countries around the world to make the planet a better place by 2030.
Goals include ending poverty, providing clean water, and taking care of the environment
Student Engagement: Means how much a student is involved, interested, and active in their learning.
When students are engaged, they pay attention, participate in class, and enjoy what they’re doing in school.

ENDNOTES
1
https://en.wikipedia.org/wiki/List_of_most_commonly_learned_second_languages_in_the_Unit-
ed_States
2
https://huggingface.co/spaces/jbilcke-hf/ai-comic-factory

268
269

Sohyeon Lee
https://orcid.org/0009-0008-4945-0965
University of Hawaii at Manoa, USA

ABSTRACT
This chapter explores the design and implementation of a ChatGPT workshop for multilingual university
students, focusing on enhancing their L2 English academic writing skills. Utilizing the analyze, design,
evaluate (ADE) model, the workshop incorporates practical activities to guide effective, critical, and
ethical use of ChatGPT. It addresses challenges faced by L2 learners, emphasizing the tool’s role in
providing personalized feedback and improving revision processes. Ethical considerations, particu-
larly in maintaining academic integrity, are highlighted. Insights reveal ChatGPT’s value as an aid
in the writing process, encouraging its use as a facilitator rather than a substitute for students’ work.
The chapter concludes with recommendations for educators and future research directions in AI and
language education.

DOI: 10.4018/979-8-3693-0872-1.ch013

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

In recent years, the advent of artificial intelligence (AI) has ushered in a transformative wave across
various sectors of society, and academia is no exception. One noteworthy AI application that has been
making waves in the realm of education is ChatGPT, a powerful language model developed by OpenAI.
This AI-driven tool has garnered attention for its potential to enhance educational practices, particularly in
the field of academic writing and second language (L2) writing practices (Godwin-Jones, 2022; Grassini,
2023). However, its integration into the classroom is not without its fair share of concerns and challenges.
ChatGPT’s entry into academia has ignited discussions about the implications of using AI in edu-
cational settings, especially when it comes to the nuanced and complex domain of L2 English writing
(Yan, 2023). While its capabilities are impressive, there are genuine apprehensions about the ethical
considerations, potential biases, and limitations inherent in large language models like ChatGPT (Bar-
rot, 2023). It is imperative, therefore, that educators and students alike take a proactive approach to
understanding these AI tools comprehensively.
This chapter delves into the evolving landscape of AI in education, with a specific focus on how a
workshop on ChatGPT for academic writing is being leveraged to foster ethical awareness and enhance
the L2 English writing revision processes in university academic settings. I recognize that the road to
harnessing AI for pedagogical purposes is not devoid of challenges, but it also presents a plethora of
opportunities for students as well as instructors. By examining the responsible use of AI, we can turn
these tools into effective instruments for both learning and teaching.
To achieve this balance through the implementation of a workshop to acquaint students with the
intricacies of ChatGPT and to cultivate their critical thinking skills in its usage, I designed and con-
ducted a 75-minute instructional workshop for L2 English learners at an American University, focusing
on responsible and critical usage of ChatGPT to improve their L2 English academic writing skills. I
evaluated the workshop’s impact through pre- and post-workshop questionnaires, assessing shifts in
students’ perceptions of ChatGPT. In my research based on the workshop, I aspired to understand how
the perceptions of multilingual university students regarding the use of ChatGPT for academic English
writing evolve before and after participating in a 75-minute instructional workshop.
Hopefully, the workshop can serve as a crucial bridge between the potential of AI and its ethical
and practical application within the academic context. It may also empower students to navigate the AI
landscape with proficiency, enabling them to make informed decisions while composing and revising
their academic writing. This study can lead to a significant pedagogical implication as well in that Chat-
GPT can provide targeted assistance for individual learners with different needs when used responsibly.
Consequently, this chapter aims to shed light on the dual nature of AI in education, acknowledging its
transformative potential while addressing concerns that accompany its adoption. Through an exploration
of a ChatGPT workshop, I endeavor to provide educators and learners with valuable insights, strategies,
and best practices for harnessing the power of AI responsibly and ethically. Ultimately, by embracing AI
as a tool for learning and teaching, we can pave the way for a future where academic writing becomes
more approachable, meaningful, and effective for students in L2 English language programs within
university academic settings.

CHALLENGES OF L2 ENGLISH WRITERS AT AMERICAN UNIVERSITIES

Academic writing, particularly at the university level, is a multifaceted endeavor that demands a high
degree of cognitive thinking and language proficiency, which can be one of the fundamental challenges

270

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

faced by L2 English writers. To elaborate further, the process involves not only linguistic skills and
cognitive abilities but also textual and cultural context knowledge such as rhetoric and genre awareness,
making it a challenging amalgamation of diverse competencies (Godwin-Jones, 2022; Harklau & Pinnow,
2008). Therefore, academic writing necessitates a structured and systematic approach unlike everyday
communication: It demands an intricate interplay of ideas, evidence, and arguments, all intricately woven
into a coherent narrative. Attaining such a sophisticated command of language skills, textual understand-
ing, and cultural context knowledge presents a formidable challenge, particularly for students who are in
the process of enhancing their language proficiency as L2 learners (Ferris & Hedgcock, 2014). This task
is further complicated when the writing conventions in a student’s first language (L1) differ markedly
from those in their second language (L2), a phenomenon that Kaplan has illustrated through his theory
of contrastive rhetoric in relation to English (Connor, 1998). Moreover, academic writing requires a
specialized vocabulary and terminology that may be unfamiliar to L2 English learners, further adding to
the complexity. For L2 English learners, this journey through the intricate landscape of academic writing
can often feel like navigating uncharted waters (Paltridge, 2018; Reichelt et al., 2012).
The varied backgrounds and unique needs of multilingual learners add another layer to the intrica-
cies of achieving proficiency in L2 English writing. These students bring with them a wealth of experi-
ences that significantly shape their approach to learning the language. Some students may have learned
English as a foreign language in their home countries and may be categorized as “eye-learners,” having
acquired their L2 English primarily through visual methods such as studying vocabulary, verb forms,
and language rules. Others may have arrived in the USA at an earlier age and received English education
in American schools, acquiring the target language more naturally and falling into the “ear-learners”
category, learning the language through listening and speaking (Reid, 1998).
Furthermore, multilingual students pursuing their degrees at American universities have diverse
academic interests, majoring in various fields ranging from natural sciences to humanities, and the fact
that some students are temporarily taking courses for exchange programs, while others are more seri-
ously pursuing their degrees full-time, leads to varied motivations and goals in their writing classes and
assignments. Previous L2 writing instruction that these international students have received also plays a
significant role, as some students may not have had any experiences with extensive reading or writing in
L2 English. These students could easily become overwhelmed by the workload of a composition course,
often becoming disengaged and losing their interest. Overall, these multilingual students coming from
diverse learning backgrounds, each with unique linguistic strengths and weaknesses can have a tough
time making the transition to the specific vocabulary and discourse patterns of academic English (Ferris
& Hedgcock, 2014; Paltridge, 2018; Reichelt et al., 2012).
Consequently, multilingual students can benefit from ongoing, timely, and individually targeted
feedback on their work. Feedback should not be limited to one-time or specific areas but should be
continuous and cover various aspects of writing, recognizing that writing is an iterative process (Ferris
& Hedgcock, 2014; Flower & Hayes, 1981; Godwin-Jones, 2022). Nonetheless, providing personalized
constructive feedback on student’s writing can be a significant challenge for writing instructors as they
often face constraints in providing extensive feedback to individual students due to heavy workloads
and large class sizes (Ferris & Hedgcock, 2014; Godwin-Jones, 2022). Furthermore, L2 English writers
can encompass a broad spectrum of abilities, from those who may require intensive language support
to those with advanced language proficiency seeking feedback on more global issues of their writing
(Godwin-Jones, 2022; Harklau & Pinnow, 2009). Tailoring instruction to address the varying needs of
this diverse student population can be a complex endeavor for educators. Thus. L2 English writers can

271

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

be left at a disadvantage, as they may not receive the level of feedback and guidance they require to
refine their writing skills effectively.
In summary, the challenges faced by L2 English writers at American universities are multifaceted and
include the sophisticated aspects of academic writing, the demand for specialized language skills, and
the need for personalized feedback. Recognizing and addressing these challenges is essential in ensur-
ing that L2 English learners have the support and resources necessary to excel in the academic writing
landscape. It is within this context that the integration of AI tools like ChatGPT and the implementation
of targeted workshops can play an essential role in facilitating their academic writing journey.

CHATGPT IN L2 ACADEMIC WRITING

In the context of the challenges faced by L2 English writers in American universities, the emergence
of ChatGPT represents a significant technological aid. This AI-driven language model from OpenAI
is distinguished by its sophisticated text generation capabilities. It offers nuanced and coherent prose,
as a result of its extensive training on diverse datasets (Teubner et al., 2023). By integrating machine
learning and deep learning mechanisms with large language data (Dale, 2021; M. Zhang & Li, 2021),
Natural Language Processing has become increasingly powerful, effectively handling human languages
and providing aid for both global and local issues in human-generated texts (Godwin-Jones, 2022; Yan,
2023). For academic writers, particularly those who are still honing their language skills, ChatGPT can
serve as a supportive tool. It assists in crafting content, offering language translation services, proof-
reading, and much more.
In addition, the user-friendly interface of ChatGPT offers efficient affordances. It is designed to be
straightforward, allowing for easy navigation without requiring specialized technological skills from
its users (Warschauer et al., 2023; Yan, 2023). Such accessibility is critical, as it ensures that the focus
remains on enhancing language proficiency and academic writing skills, without the added challenge of
overcoming a steep technological learning curve. This ease of use is particularly beneficial for L2 learn-
ers, who may already be facing cognitive overload from mastering a new language and academic content.
The integration of AI tools in education has been met with both enthusiasm and caution. In recent
years, AI-based tools have increasingly replaced more conventional linguistic resources (Nazari et al.,
2021; Wu et al., 2021). These tools have become a focal point in the pedagogy of L2 writing, falling under
the broader category of computer-assisted language learning (Adams & Chuah, 2022; Yan, 2023). Tools
like Grammarly, Quillbot, and Google Translate have demonstrated how AI can streamline the writing
process; they offer real-time corrections and suggestions that significantly enhance the quality of writing.
More specifically, studies have shown that Grammarly users tend to outperform their peers in L2
writing tasks (Dizon & Gayed, 2021). Additionally, AI-based feedback has been confirmed to positively
affect students’ motivation and self-efficacy in L2 writing (Nazari et al., 2021). The impact of Automated
Writing Evaluation (AWE) on L2 writing is also significant, as it helps multilingual writers practice writ-
ing more deliberately (Palermo & Wilson, 2020). This deliberate practice is associated with a positive
motivating effect (Camacho et al., 2021; Nunes et al., 2021), especially when users are properly guided
in its use (Grimes & Warschauer, 2010; Nunes et al., 2021).
However, it is important to acknowledge that previous AI-based tools have primarily focused on lan-
guage use and accuracy, mostly being utilized for editing purposes (Ranalli, 2021). These tools often lack
the capability to provide feedback on global aspects of writing, such as the strength of argumentation,

272

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

discourse coherence, or organization (Grimes & Warschauer, 2010; Y. Huang & Wilson, 2021). As a
result, they have been mostly integrated into the revision process in classroom contexts (Ranalli, 2021),
with a focus-on-form approach targeting specific grammar points (John & Woll, 2020).
Intriguingly, generative AI tools such as ChatGPT have extended the capabilities of previous AI tools,
prompting educators to rethink pedagogy in L2 writing. The adaptability and richness of the text generated
by ChatGPT hold significant potential to aid learners in developing their writing skills in many different
areas. Despite the integration of ChatGPT in education has been explored, with its potential strengths
highlighted (Qadir, 2022; Yan, 2023; Zhai, 2022), its adoption raises ethical concerns, including issues
of plagiarism and nuanced biases in AI-generated texts (Gao et al., 2022; Godwin-Jones, 2022; Yeadon
et al., 2022). The model can sometimes produce biased or inaccurate content, underscoring the need
for critical engagement with its output. Educators and students must be vigilant about ethical consider-
ations, such as avoiding plagiarism and ensuring proper attribution of AI-generated content (Borenstein
& Howard, 2021). Furthermore, there is the issue of authenticity for the authorship, as ChatGPT can
generate text on behalf of the human writer, potentially impacting the creativity and originality of the
writing (Godwin-Jones, 2022).
The academic community continues to gauge the impact of tools like ChatGPT on learning outcomes
and academic honesty. The challenge involves leveraging ChatGPT’s strengths, its comprehensive language
understanding and generative capabilities, while mitigating risks associated with its use (Warschauer et
al., 2023). As it is reasonable to assume that students across various disciplines are already actively using
these tools (Eaton et al., 2021), the critical and judicious use of AI-generated tools should be introduced
and taught in classrooms, guided by the instructor’s expertise (Godwin-Jones, 2022; Otsuki, 2020).

DESIGNING AND IMPLEMENTING A CHATGPT WORKSHOP

Participants and Context

The English Language Institute Writing Courses at the University of Hawaii at Manoa

The workshop, titled “Promoting Ethical and Critical Use of ChatGPT to Enhance Multilingual Uni-
versity Students’ Academic English Writing,” is designed for students at the University of Hawaiʻi at
Mānoa who are learning English as an additional language. For students who failed to meet the language
requirements (neither submitting required English proficiency test scores nor passing the ELI placement
tests), enrollment in specific courses is mandated. These courses, provided by the English Language
Institute (ELI), are geared towards enhancing the language skills necessary for success in their respec-
tive academic disciplines and involve the development of their L2 English proficiency. All ELI courses
are offered for both graduate and undergraduate students, catering to intermediate and advanced levels.
More specifically, one of the advanced writing classes, ‘ELI 83,’ consists entirely of graduate students,
and another advanced writing class, ‘ESL 100,’ is only for undergraduate students while the intermediate
‘ELI 73’ course has mixed groups of undergraduate and graduate students with similar writing abilities.
In my role as a graduate assistant, I was tasked with developing a workshop centered on the use
of ChatGPT for academic writing. This initiative followed the success of a similar workshop in 2022,
hosted by the ELI department, which focused on Grammarly for academic writing. The success of the
previous workshop led to the conception of this year’s ChatGPT workshop, designed as a continuation

273

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

of the department’s efforts to provide helpful guidance in the development of writing skills for multi-
lingual writers. Initially designed as a pilot session, the workshop was integrated into the ELI writing
course curriculum, with the goal of reaching a broader audience on campus in the following year. It was
scheduled to take place during weeks 10 to 15 of the Fall 2023 semester, aligning with the ELI writing
instructors’ schedule.

Workshop Design Process

Needs Analysis

To lay the groundwork for the workshop, a needs analysis was conducted through a survey distributed
to English Language Institute (ELI) instructors (see appendix A.). The purpose of this survey was two-
fold: to gather background information on the students’ existing L2 English writing competencies and
to identify what the instructors would want their students to achieve from the workshop. The survey
began by inquiring about the skills students were expected to possess prior to the workshop, such as
the ability to craft an outline, organize an academic paper coherently, develop content with clear topic
sentences and supporting details, and revise drafts effectively. Following this, instructors were asked to
select from a list of potential workshop objectives that they deemed most beneficial for their students.
The options included evaluating ChatGPT’s utility and limitations in academic writing, using ChatGPT
to refine and improve emails, enhancing argumentative essay outlines, obtaining draft feedback, and
citing sources properly with ChatGPT’s assistance.
Based on the survey results and discussions with ELI writing instructors, it became evident that by
the time of the workshop, students should have learned to brainstorm ideas, outline argumentative essays,
and prepare initial drafts for final submission. Additionally, there was a consensus among instructors on
the need to reduce the workload associated with providing writing feedback. Concerns were also raised
about students potentially over-relying on ChatGPT for writing tasks, which might impede their skill
development. Lastly, the ELI director who is also my supervisor advised me to incorporate hands-on
activities into the workshop to enhance student engagement and improve overall effectiveness.

ADE Approach

In the formulation of the workshop, I was guided by the principles of design-based research, particularly
the Analysis, Design, and Evaluation (ADE) model as proposed by Reigeluth and An (2021). The initial
step was to pinpoint a performance gap in the English Language Institute (ELI) students’ writing abilities
and how they are using different AI tools for their writing assignments. From the needs analysis, this
gap manifested in various ways: some students write English directly translating phrases and expres-
sions from their first language, leading to unclear communication, while others write in their native
language and use AI tools to translate their L1 writing. Meanwhile, advanced students often bypassed
tools like ChatGPT entirely, instead seeking extensive individualized feedback, which placed a demand
on instructors’ time and resources.
To bridge this gap, the workshop was conceived with the goal of equipping ELI students with the
skills to utilize ChatGPT effectively, critically, and ethically. The ADE model facilitated a structured
approach to this end. In the analysis phase, I examined the specific needs and challenges faced by ELI
students in their writing endeavors. The design phase involved creating workshop content that was both

274

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

responsive to these needs and flexible enough to cater to varying levels of proficiency. The evaluation
phase was anticipated to assess the impact of the workshop on students’ writing skills, with a focus on
their ability to integrate ChatGPT’s assistance productively into their writing process.
The workshop design was initiated with a broad, top-level ADE analysis. This initial instructional
developmental stage with a general view provided a macroscopic perspective of the instructional content
and methods. Subsequently, as the design progressed, finer adjustments were made to align with the
nuanced needs of students at different proficiency levels. By iterating through the stages of the ADE
model, the workshop was meticulously tailored to foster an environment where students could engage
with ChatGPT not just as a tool, but as a means to enhance their academic writing while maintaining
the integrity of their work.

Workshop Plan With the Top-Level ADE

In the top-level ADE (Analysis, Design, and Evaluation) stage of the instructional design process (Reige-
luth & An, 2021) the objective is to establish a comprehensive vision for the instructional experience.
This entails formulating overarching content themes, sequencing, and pedagogical methods. This stage
is crucial for delineating what content will be taught and devising the most effective strategies for teach-
ing it. In the context of the ChatGPT workshop, which aims to educate students on the proficient use of
ChatGPT for revising their essays, the design was crafted in alignment with the model’s guidelines for
task expertise. This model is particularly suited for instructional situations where the goal is to equip
students with the capability to execute specific tasks or actions. This stands in contrast to topic expertise,
which is concerned with cultivating a deep understanding of conceptual knowledge.
The initial step in the top-level design for task expertise is the identification of tasks. These are the
distinct, real-world actions students need to complete from start to finish. Subsequently, these tasks
are deconstructed into subtasks. This breakdown is essential for structuring the instruction in a way
that incrementally builds students’ skills. Following the identification and decomposition of tasks, the
next critical phase involves sequencing these tasks and subtasks. The sequencing can follow a linear
progression, mirroring the real-world order in which the tasks are typically performed. Alternatively,
a branching sequence can be employed, offering learners the flexibility to navigate through the task
completion sequence. This choice of sequencing is informed by the instructional goals and the learners’
needs, aiming to provide an intuitive and effective learning trajectory.
By embracing this methodical approach, I tried to design the ChatGPT workshop ensuring that stu-
dents not only learn how to use ChatGPT effectively, critically, and ethically but also develop a strategic
approach to the task of essay revision, thereby enhancing their overall writing competency. To do so, the
workshop’s primary objective, ‘to equip students with the skills to utilize ChatGPT for effective, critical,
and ethical revision of academic writing,’ was broken down into three key tasks, each comprising specific
subtasks. Initially, participants would be guided to raise their awareness of the ethical implications of
AI use in academic writing. For example, participants look at four different scenarios where university
students use ChatGPT for their academic writing tasks, and engage in discussions to talk about the
right and wrong ways of using AI for academic writing. This session will also involve sharing personal
concerns and experiences, followed by collaboratively establishing a set of ethical guidelines for AI
utilization. The next focus would be on identifying the strengths and weaknesses of texts generated by
ChatGPT. Students use ChatGPT to fix two different emails with errors. One email is for communicating
with a professor, while the other is for a friend. This hands-on activity lets students explore ChatGPT

275

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

and see its strengths and limitations. Participants would compare ChatGPT-generated texts with those
of their peers and conduct various inquiries to revise an email, thereby understanding the nuances of
AI-generated texts. Finally, the participants would apply their learning to revise their writing with the
assistance of ChatGPT. The third part is about students interacting with ChatGPT to get feedback and
suggestions for their writing. They chat with ChatGPT using the ChatGPT prompt that I provide in the
workshop, ask for feedback, and then change their drafts based on the suggestions. They would request
targeted feedback from ChatGPT on specific aspects such as content, organization, and language use.
Additionally, they would engage with a feature that suggests academic vocabulary, comparing it with
their own words, and then independently revise their drafts based on ChatGPT’s suggestions.
With these tasks and subtasks defined, planning for the instructional methods followed. Considering
elements such as content mastery, pacing, experiential learning, and delivery methods, a learner-centered
approach was adopted. This approach prioritizes learning by doing, an essential strategy given the work-
shop’s focus on practical tool usage. The pacing was set to group pacing, with all participants moving
through the learning process collectively, appropriate for a single-session workshop. For delivery, face-
to-face instruction was chosen, utilizing electronic forms of prepared writing samples, word processing
software like Google Docs or Microsoft Word, the ChatGPT interface, and the student’s personal laptop
computers. Given the workshop’s one-off nature, a mastery approach was deemed unsuitable due to the
limited time frame, thus not all tasks could be mastered completely, but substantial exposure to the core
concepts was ensured. For more details, please refer to Appendix B, ‘Workshop Plan.’

ChatGPT Prompts for Revision Activities

ChatGPT prompts refer to the input or questions that users provide to the ChatGPT model, prompting
it to generate responses. During the workshop, students were provided with specific ChatGPT prompts
(see Appendix C for the workshop slides) to facilitate their interaction with the AI. These prompts served
as a crucial mechanism for obtaining tailored feedback from ChatGPT, and I designed them to assist
students in their writing process. For example, a student might have asked ChatGPT: ‘Give me feedback
on my introductory paragraph based on content, organization, and language use.’ ChatGPT then gen-
erated suggestions and feedback, offering insights into the strengths and weaknesses of the paragraph
without altering the original writing. This exercise was invaluable for L2 English writers, providing
direct and specific feedback from ChatGPT to enhance their writing process. Although ChatGPT might
provide general feedback if the prompt is not specific enough, students can still utilize this feedback as
guidelines or checklists.
The workshop included two main hands-on activities. The first involved students revising emails
with pre-identified errors in two scenarios. Email writing was chosen to assess ChatGPT’s strengths and
weaknesses in generating texts, as it is a primary communication mode in everyday American contexts
and poses fewer ethical concerns than academic writing. Students input prompts like ‘revise the following
email, make it more concise, and use more casual language,’ to see how ChatGPT altered the original
text. This practice also helped international students adapt to American email writing conventions and
etiquette. By comparing ChatGPT’s revisions under different scenarios, students evaluated the effective-
ness of various prompts. They engaged in peer discussions to identify similarities and differences in the
ChatGPT-generated texts, assessing the AI’s strengths and weaknesses collectively.
For the second activity, students used ChatGPT to receive feedback and suggestions on their writing
drafts. The key prompt word was ‘feedback,’ ensuring that ChatGPT provided suggestions and explana-

276

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

tions, rather than revising the text. For instance, using the prompt ‘Can you give me feedback on my
language use errors? Are there any specific grammar errors that I should study more?’ students received
targeted feedback. Another prompt, ‘Give me suggestions for word choices to make my writing more
academic. Give me a table of words to compare,’ resulted in a table comparing their words with sug-
gested academic words.
Importantly, students were guided to make careful decisions when adopting and evaluating ChatGPT’s
feedback. While ChatGPT can be a valuable tool, it was acknowledged that not all suggestions might
be relevant or accurate. Students had the autonomy to select and apply feedback that aligned with their
writing goals, which sometimes involved rejecting irrelevant or inaccurate suggestions. Incorporating
concrete examples and practical exercises offered participants a hands-on experience, enhancing their
understanding of the workshop’s objectives and ChatGPT’s role as a writing tool.

Workshop Procedure

Five-Week Duration

The study was designed to span five weeks, allowing the workshop to be conducted across multiple
classes. This duration was set according to the assigned schedule by the instructors, but it also allowed
thorough data collection from multilingual students at varying stages of their academic English writing
development. The central element of this research was the 75-minute instructional workshop, which
aimed to rigorously evaluate its effectiveness in improving the academic writing skills of multilingual
university students. The extended five-week framework (see Table 1), encompassing multiple classes,
enhanced the data collection process by accommodating the diverse language proficiencies and academic
needs of the students.

Table 1. Schedule for ChatGPT workshops

23 Fall Week 10 Week 11 Week 12 Week 15

ELI 73-3 ELI 73-1
Class Intermediate level Intermediate level
Undergrad. + Grad. Undergrad. + Grad.
ELI 83 ESL 100 ESL 100 ESL 100
Advanced level Advanced level Advanced level Advanced level
Grad. Undergrad. Undergrad. Undergrad.

Data Collection During Workshop

During the workshop, data were collected to ensure research validity and enhance understanding of
participants’ interactions with ChatGPT. All data collection processes had received approval from the
university’s Institutional Review Board (IRB) and strictly adhered to ethical standards. Participants were
required to provide informed consent for the use of their data in research before any data collection oc-
curred. Data collection within the workshop primarily involved administering pre- and post-workshop
questionnaires, monitoring student interactions with ChatGPT, and collecting ChatGPT-generated

277

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

texts. The questionnaires were distributed via Google Forms to streamline the process, with responses
automatically stored on the researcher’s Google Drive upon submission. These questionnaires aimed to
capture participants’ initial perceptions and any shifts in understanding post-workshop. Participants were
encouraged to use ChatGPT for feedback and revision of their writing drafts. As part of the data collec-
tion, students submitted their ChatGPT chat logs, which contained conversations with the AI platform.
These chats, obtained as students worked on revising their drafts, were collected using a digital survey
form to ensure security and accessibility for subsequent analysis. Each chat represented a unique engage-
ment between the student and ChatGPT, capturing the student’s requests for feedback and ChatGPT’s
responses. These logs were carefully stored and organized for further examination, forming a critical
part of the workshop’s data collection process.

WORKSHOP EVALUATION

Methods

Pre-Workshop Questionnaire

The pre-workshop questionnaires were administered before the workshop to establish a foundational
understanding of students’ awareness and requirements in relation to ChatGPT and the academic writing
revision process. These questionnaires consisted of two open-ended questions and 14 items that included
multiple-choice questions, options for selecting all that apply, as well as a five-point Likert scale.
The questionnaire was structured into three distinct sections. The initial segment was dedicated to
gathering personal background information, delving into aspects such as participants’ age and primary
language (L1). The subsequent section concentrated on students’ writing abilities, assessing factors such
as their affinity for writing in both their native and second languages (L1/L2), self-assessed L2 writing
proficiency, and their writing habits, including the typical amount of time dedicated to the writing revi-
sion process. The final section of the questionnaire delved into ChatGPT usage, seeking to understand
the frequency of ChatGPT utilization, specific scenarios in which ChatGPT was employed for writing
assignments, awareness of ethical considerations, and students’ overall satisfaction levels with their
ChatGPT experiences. For additional details, please refer to Appendix D.

Post-Workshop Questionnaire

Following the workshop, participants were asked to complete a post-workshop questionnaire (see Appendix
E). This questionnaire aimed to evaluate the workshop’s effectiveness in enhancing participants’ confidence
in using ChatGPT to obtain feedback critically and effectively, all while maintaining ethical standards.
Additionally, the questionnaire provided students with the opportunity to offer qualitative feedback on
the workshop’s content and structure, allowing them to reflect on their learning experiences. The post-
workshop questionnaires included a total of 11 questions, encompassing two open-ended questions for
suggestions, three multiple-choice questions, and the remaining questions employing a five-point Likert
scale. These questions were divided into two sections, with each section focusing on a specific aspect
related to the participants’ post-workshop experiences and their perception of the workshop’s impact.

278

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

Findings

Pre-Workshop Questionnaires

The pre-workshop questionnaires were administered before the workshop by providing the instructors
with a link to a Google survey form, which the students completed in advance. Among the 55 students
who attended the workshop, I analyzed the results from the 46 who submitted their consent forms. The
pre-workshop questionnaire results (n=46) provided valuable insights into their comfort levels with vari-
ous English language skills. Table 2 illustrates that writing was identified as the least comfortable skill,
with only 6.5% of the students (three out of 46) considering it their strength. This finding indicates that
L2 English writing presents significant challenges for these students, more so than other language skills.
In terms of self-assessment of their L2 English writing abilities, a mere 6.5% of the students consid-
ered themselves highly proficient, scoring a 5 on a 5-point Likert scale. A larger segment, 37%, rated
their proficiency at 4, while the majority, 43.5%, assigned themselves a moderate score of 3. Notably,
13% of the students rated their writing proficiency at the lower level of 2. It was observed that students
enrolled in Advanced writing courses were more likely to select a rating of ‘4’, in contrast to those in
lower-level courses.
On average, students reported dedicating approximately two to three hours to revising major writing
assignments, such as final papers, as illustrated in Figure 1. Despite this investment of time, the data
revealed that students generally lacked confidence in their ability to revise their writing. Remarkably,
only one student (2.2%) expressed the highest confidence level, scoring a 5. A quarter of the participants
(26.1%) indicated moderate confidence with a score of 4. The largest group, encompassing 45.7%, chose
3, signifying a neutral level of confidence. A considerable minority, 21.7%, reported a lower confidence
level of 2. Additionally, 4.3% of the students rated their confidence in revising their writing at the low-
est level of 1.

Table 2. Most favored English language skill by student preference

Comfortable Lg. Skill Count (n) Percentage (%)

Listening 14 30.4
Reading 14 30.4
Speaking 15 32.6
Writing 3 6.5
total 46 100

The aspect of feedback where students expressed the most concern (see Table 3) was in areas of
spelling and grammar correction, word choice for natural language use, and the structure, clarity, and
coherence of their writing. These categories were prioritized over content, fluency, and research and
citation for desired feedback. This suggests that while students are concerned with the substantive aspects
of writing, there is a particular focus on the technical and linguistic accuracy of their work.

279

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

Figure 1. A pie chart of students’ time investment in assignment revision

Table 3. Preferred types of writing revision feedback

Feedback Type Count Percentage (%)

Spelling/ Grammar correction 28 60.87
Word choice for natural language use
32 69.57
(vocabulary, expressions)
Content (ideas) 17 36.96
Structure (organization) 24 52.17
Fluency (writing a lot) 16 34.78
Research and Citations 14 30.43
Clarity and Coherence 23 50
Note. Students could select up to three choices. (n = 46)

In the section addressing ChatGPT usage, the questionnaire data offered insights into the students’
engagement with the technology. Of the respondents, a significant majority (65.2%) indicated that they
use the free version of ChatGPT, while a small fraction (6.5%) opted for the premium version. Notably,
nearly a third of the participants (28.3%) reported no prior experience with ChatGPT. Among the students
who had used ChatGPT, approximately half (48.5%) reported utilizing the tool either daily or weekly.
This suggests a substantial integration of ChatGPT into their academic routine. Inquiring into the spe-
cific academic tasks for which students employ ChatGPT, idea generation or brainstorming emerged as
the most common use, selected by 43.5% of users. This was followed by other applications, including
proofreading, completing homework assignments, and assisting with research papers and essays.
When leveraging ChatGPT for writing support, students predominantly sought assistance with gram-
mar and punctuation, sentence structure enhancement, and organization of ideas. This trend underscores
a focus on the tool’s capability to refine the technical elements of writing, suggesting that students pri-
marily view ChatGPT as a means to polish the mechanical aspects of their work (for details, see table 4).

280

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

Interestingly, responses illustrated in Figure 2 regarding ethical concerns associated with using Chat-
GPT revealed a tendency towards fewer worries in this area. A notable number of students did not express
significant ethical apprehensions, which could indicate a possible gap in awareness or understanding of
the potential ethical issues tied to AI assistance in academic writing. This finding raises questions about
students’ recognition of the ethical dimensions of using AI tools in academic contexts and suggests a
need for more education on this topic.

Table 4. Feedback types multilingual writers look for in ChatGPT

Feedback Type Count Percentage (%)

Grammar and punctuation correction 19 57.58
Vocabulary Suggestions 18 54.55
Sentence Structure Improvements 22 66.67
Guidance on organizing ideas 18 54.55
Recommendations for improving clarity and coherence 15 45.45
Assistance with academic style and tone 10 30.30
Help with research and citations 8 24.24
N/A (Never used ChatGPT before) 13
Note. Students were given the option to select all responses that apply (n = 46). Percentages were calculated based on the number of
applicable students, excluding those who selected ‘N/A’. For instance, in the case of ‘Help with research and citations’, 8 responses were
divided by 33 (the total of 46 minus the 13 who selected ‘N/A’), resulting in a percentage of 24.24%.

Figure 2. A histogram of levels of ethical concern regarding the use of ChatGPT

Finally, the question regarding students’ satisfaction level with ChatGPT was assessed using a 5-point
Likert scale, targeting only those students who had prior experience with ChatGPT. To determine the
overall satisfaction with the feedback and suggestions provided by ChatGPT, an average satisfaction
score was calculated from the responses. The students rated their satisfaction on a scale from 1 (very
dissatisfied) to 5 (very satisfied). The calculation considered the number of responses in each category

281

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

along with their respective satisfaction ratings: 1 response rated 5 points (very satisfied), 14 responses
rated 4 points (somewhat satisfied), 10 responses rated 3 points (neutral), 7 responses rated 2 points
(somewhat dissatisfied), and 1 response rated 1 point (very dissatisfied). The resulting average satisfac-
tion score was 3.21, indicating a generally mild positive level of satisfaction among the respondents.

Post-Workshop Questionnaires

The results from the post-workshop questionnaires were gathered from 42 students who provided consent
and attended the workshop. Notably, four students who had submitted the pre-workshop questionnaire
were absent from the workshop. In the post-workshop questionnaire, the students reflected on their
experience and evaluated the effectiveness of the workshop. They highly rated its overall quality, with
45.2% labeling it as ‘outstanding’ and 54.8% as ‘good’. In terms of the content and activities of the
workshop, the majority of students felt that no significant changes were required, reflecting high levels
of satisfaction. This sentiment was particularly pronounced among those who were new to ChatGPT prior
to the workshop, implying that the framework was both accessible and beneficial even for beginners.
The questionnaire further explored changes in students’ confidence regarding their English writing
revision process and their perceptions of ChatGPT after participating in the workshop. There was a notable
increase in confidence in their ability to revise English writing using ChatGPT, with an average rating
of 4 out of 5 on the Likert scale. This suggests an enhanced level of confidence in utilizing ChatGPT
as well. Additionally, Figures 3 and 4 highlight a significant shift towards higher scores in students’
understanding of the strengths and weaknesses of ChatGPT, as well as their awareness of related ethi-
cal considerations. This indicates that the workshop effectively increased students’ comprehension and
critical awareness of these aspects.

Figure 3. A histogram of understanding the strengths and weaknesses of ChatGPT after workshop

282

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

Figure 4. A histogram of understanding ethical issues of ChatGPT after workshop

The workshop was highly successful in enhancing students’ understanding of ChatGPT. This success
was evident as the vast majority of participants, over 90%, rated their comprehension of the strengths,
weaknesses, and ethical considerations of using ChatGPT in academic writing as 4 or 5 on a 5-point
Likert scale. This high level of rating reflects a significant enhancement in their understanding and criti-
cal application of ChatGPT. In terms of feedback from ChatGPT, the aspects most valued by students
were its assistance with spelling and grammar, word choice, and organizational structure. For a more
comprehensive analysis, please refer to Table 5, which offers a detailed breakdown of these elements.

Table 5. Feedback types multilingual writers appreciated in ChatGPT feedback

Feedback Type Count Percentage (%)

Spelling/ Grammar correction 32 76.2
Word choice for natural language use
28 66.7
(vocabulary, expressions)
Content (ideas) 17 40.5
Structure (organization) 28 66.7
Fluency (writing a lot) 16 38.1
Research and Citations 5 11.9
Clarity and Coherence 9 21.4
Others (coding, translation, etc.) 1 2.4
Note. Students could select all that apply. (n = 42)

Furthermore, the workshop positively impacted the students’ anticipated future use of ChatGPT. A
significant 48.6% of the participants planned to use it more frequently, while 45.7% intended to main-
tain their current usage levels. This inclination towards increased or sustained use correlates with the
high levels of satisfaction reported with the workshop, suggesting that the workshop not only met but

283

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

potentially exceeded its intended goals in terms of enhancing students’ proficiency and comfort with the
AI tool. In the open-ended comment section of the post-workshop questionnaires, among many positive
responses, one particularly intriguing comment stood out: ‘I was happy to learn the useful functions
of ChatGPT and I think I’m going to be a heavy user of it.’ This feedback was from a student who had
never used ChatGPT before.

Guidelines and Future Directions

As educators and academic institutions increasingly adopt AI technology, it’s essential to establish
guidelines for the responsible and ethical use of AI tools like ChatGPT. Based on the insights from my
workshop research, this section aims to provide educators with a practical framework for integrating
AI-driven writing assistants into their pedagogical approaches. The overarching goal is to employ these
tools as supplements that enhance learning, rather than as replacements for writing skills.

Ethical and Responsible Use

The ethical deployment of AI in educational settings must comprehensively address issues of plagia-
rism, dependency, and the integrity of student work. These concerns were notably underscored by the
findings of my workshop. To uphold academic standards, educators should cultivate an environment
where AI tools are leveraged to support and refine students’ writing skills, rather than supplant them.
This approach involves several key strategies:

• Establishing Clear Policies: Implementing explicit guidelines on the appropriate use of AI in aca-
demic work helps in setting boundaries and expectations.
• Educating Students: Instructors should inform students about both the potential and the limita-
tions of AI, emphasizing that these tools are aids in the learning process, not definitive solutions.
• Encouraging Critical Engagement: Students should be guided to critically evaluate AI-generated
content and understand its proper role in their work.

Additionally, instructors can leverage technology to monitor the development of students’ writing
skills. By utilizing the version history features in Google Docs or Microsoft Word, both educators and
students can track changes, revisions, and improvements in writing assignments over time. Addition-
ally, incorporating occasional paper and pencil writing during class can help instructors gauge students’
real-time writing abilities. These practices are valuable for assessing current skill levels and for making
informed decisions on how to enhance students’ learning and revision processes, while also promoting
transparency and accountability in the use of AI tools.
To ensure critical and ethical use of these tools, instructors might consider requiring students to
submit their ChatGPT chat logs as well. This would allow for an analysis of how students interact with
the technology during their writing process. It is crucial for students to understand the role of AI as a
facilitator in their learning journey, rather than mistakenly perceiving it as the author of their work. This
distinction is vital to maintain the authenticity and integrity of their academic work.

284

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

RECOMMENDATIONS FOR EDUCATORS

Educators should receive comprehensive training to assist students in effectively navigating AI tools, a
need underscored by the positive outcomes observed in the workshop. This training should encompass
various strategies, including how to integrate AI feedback into the revision process in a manner that
enhances rather than overrides students’ efforts. Educators must be adept at helping students discern
between beneficial and potentially misleading suggestions provided by AI, ensuring that the student’s
original voice and intent in writing are preserved. Moreover, training should focus on how educators
can leverage AI tools to provide more personalized and nuanced feedback. By doing so, they can ad-
dress specific needs and challenges faced by individual students, thereby substantially improving the
efficiency and effectiveness of the writing and revision process. Such personalized attention, facilitated
by AI, can lead to better learning outcomes and a more supportive educational environment. In sum,
empowering educators with the skills to use AI tools responsibly and effectively is crucial for maximiz-
ing the potential of these technologies in educational settings.

CONCLUSION

In this chapter, my objective was to equip educators, researchers, and practitioners in language education
with a detailed understanding of how ChatGPT workshops can benefit multilingual students in their
academic writing endeavors. By delving into the challenges faced by L2 English learners, exploring the
design and implementation of effective workshops, and considering the ethical aspects of AI integra-
tion, my aim was to present a comprehensive view of the transformative potential of AI-driven tools in
academic writing education at the university level.
During the workshops, it became evident that student engagement in group discussions or class-
wide conversations was crucial for fostering critical thinking about ethical issues and understanding
the limitations of ChatGPT. Observations also showed that student engagement was highest when their
regular instructors participated in the activities and when a positive rapport existed among students and
between students and instructors. This highlights the importance of established relationships and expert
support in facilitating effective use of AI tools in an educational setting. For my future research, I plan to
analyze how students incorporate and modify ChatGPT suggestions in their revision processes and assess
the extent to which ChatGPT provides useful feedback, using data from students’ ChatGPT chat logs.
Additionally, further research is necessary to comprehend the long-term implications of integrating
AI in academic writing. This research should focus on how tools like ChatGPT can aid students with
diverse learning needs and backgrounds, how they influence the development of writing skills over time,
and how they can be adapted to meet a variety of educational objectives, as indicated by the preliminary
outcomes of my workshop.

ACKNOWLEDGMENT

I would like to extend my heartfelt gratitude to Priscilla, my supervisor and the director of the ELI,
for her invaluable guidance on this workshop project. My thanks also go to Dan Holden, the education
specialist, for his support. I am grateful to Dr. Crowther for encouraging the research aspect of this

285

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

project and providing helpful feedback. Special appreciation is due to my academic advisor, Dr. Isbell,
and to SLS professors Dr. Gilliland and Dr. Zheng, for their significant academic insights. Lastly, I am
thankful for the constant encouragement from the supportive SLS ‘ohana. Any oversights in this work
are my own responsibility.

REFERENCES

Adams, D., & Chuah, K.-M. (2022). Artificial Intelligence-Based Tools in Research Writing. In P. P.
Churi, S. Joshi, M. Elhoseny, & A. Omrane (Eds.), Artificial Intelligence in Higher Education: A Practi-
cal Approach (pp. 169–184). CRC Press. doi:10.1201/9781003184157-9
Barrot, J. S. (2023). Using ChatGPT for second language writing: Pitfalls and potentials. Assessing
Writing, 57, 100745-. doi:10.1016/j.asw.2023.100745
Borenstein, J., & Howard, A. (2021). Emerging challenges in AI and the need for AI ethics education.
AI and Ethics, 1(1), 61–65. doi:10.1007/s43681-020-00002-7
Camacho, A., Alves, R. A., & Boscolo, P. (2021). Writing motivation in school: A systematic review of
empirical research in the early twenty-first century. Educational Psychology Review, 33(1), 213–247.
doi:10.1007/s10648-020-09530-4
Chang, D. H., Lin, M. P.-C., Hajian, S., & Wang, Q. Q. (2023). Educational Design Principles of Using
AI Chatbot That Supports Self-Regulated Learning in Education: Goal Setting, Feedback, and Person-
alization. Sustainability, 15(17), 12921-. doi:10.3390/su151712921
Connor, U. (1998). Contrastive rhetoric: Developments and challenges. Studia Anglica Posnaniensia,
33, 105–116.
Dale, R. (2021). GPT-3: What’s it good for? Natural Language Engineering, 27(1), 113–118. doi:10.1017/
S1351324920000601
Dizon, G., & Gayed, J. M. (2021). Examining the Impact of Grammarly on the Quality of Mobile L2
Writing. The JALT CALL Journal, 17(2), 74–92. doi:10.29140/jaltcall.v17n2.336
Ferris, D., & Hedgcock, J. (2014). Teaching L2 composition: Purpose, process, and practice (3rd ed.).
Routledge.
Flower, L., & Hayes, J. R. (1981). A cognitive process theory of writing. College Composition and
Communication, 32(4), 365–387. doi:10.2307/356600
GaoC. A.HowardF. M.MarkovN. S.DyerE. C.RameshS.LuoY.PearsonA. T. (2022). Comparing scientific
abstracts generated by ChatGPT to original abstracts using an artificial intelligence output detector,
plagiarism detector, and blinded human reviewers. doi:10.1101/2022.12.23.521610
Godwin-Jones, R. (2022). Partnering with AI: Intelligent writing assistance and instructed language
learning. Language Learning & Technology, 26(2), 5–24.

286

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

Grassini, S. (2023). Shaping the Future of Education: Exploring the Potential and Consequences of AI
and ChatGPT in Educational Settings. Education Sciences, 13(7), 692-. doi:10.3390/educsci13070692
Grimes, D., & Warschauer, M. (2010). Utility in a fallible tool: A multi-site case study of automated
writing evaluation. Journal of Technology. Language, and Assessment, 8(6), 1–43.
Harklau, L., & Pinnow, R. (2009). Adolescent Second-Language Writing. In L. Christenbury, R. Bomer, &
P. Smagorinsky (Eds.), Handbook of Adolescent Literacy Research (pp. 126–134). Guilford Publications.
Huang, Y., & Wilson, J. (2021). Using automated feedback to develop writing proficiency. Computers
and Composition, 62, 102675. doi:10.1016/j.compcom.2021.102675
John, P., & Woll, N. (2020). Using grammar checkers in an ESL context: An investigation of automatic
corrective feedback. CALICO Journal, 37(2), 169–172. doi:10.1558/cj.36523
Kasneci, E., Sessler, K., Küchemann, S., Bannert, M., Dementieva, D., Fischer, F., Gasser, U., Groh, G.,
Günnemann, S., Hüllermeier, E., Krusche, S., Kutyniok, G., Michaeli, T., Nerdel, C., Pfeffer, J., Poquet,
O., Sailer, M., Schmidt, A., Seidel, T., … Kasneci, G. (2023). ChatGPT for good? On opportunities and
challenges of large language models for education. Learning and Individual Differences, 103, 102274.
doi:10.1016/j.lindif.2023.102274
Nazari, N., Shabbir, M. S., & Setiawan, R. (2021). Application of Artificial Intelligence powered digital
writing assistant in higher education: Randomized controlled trial. Heliyon, 7(5), e07014. doi:10.1016/j.
heliyon.2021.e07014 PMID:34027198
Nunes, A., Cordeiro, C., Limpo, T., & Castro, S. L. (2021). Effectiveness of automated writing evalua-
tion systems in school settings: A systematic review of studies from 2000 to 2020. Journal of Computer
Assisted Learning, 38(2), 599–620. doi:10.1111/jcal.12635
Palermo, C., & Wilson, J. (2020). Implementing automated writing evaluation in different instructional
contexts: A mixed-methods study. Journal of Writing Research, 12(1), 63–108. doi:10.17239/jowr-
2020.12.01.04
Paltridge, B. (2018). Graduate student writing. In D. Belcher & A. Hirvela (Eds.), The TESOL Encyclo-
pedia of English Language Teaching (pp. 1–6). Wiley Blackwell. doi:10.1002/9781118784235.eelt0516
Qadir, J. (2022). Engineering Education in the Era of ChatGPT: Promise and Pitfalls of Generative AI
for Education. TechRxiv xiv. 21789 434. v1 doi:10. 36227/ techr
Ranalli, J. (2021). L2 student engagement with automated feedback on writing: Potential for learning
and issues of trust. Journal of Second Language Writing, 52, 100816. doi:10.1016/j.jslw.2021.100816
Reichelt, M., Lefkowitz, N., Rinnert, C., & Schultz, J. M. (2012). Key issues in foreign language writing.
Foreign Language Annals, 45(1), 22–41. doi:10.1111/j.1944-9720.2012.01166.x
Reid, J. (2006). “Eye” learners and “ear” learners: Identifying the language needs of international student
and US resident writers. In P. K. Matsuda, M. Cox, J. Jordan, & C. Ortmeier-Hooper (Eds.), Second-
language writing in the composition classroom: A critical sourcebook (pp. 76–88). St. Martin’s.

287

Utilizing a ChatGPT Workshop to Foster Ethical Awareness

Reigeluth, C. M., & An, Y. (2019). Merging the instructional design process with learner-centered
theory: The holistic 4d model. Taylor & Francis Group.
Teubner, T., Flath, C. M., Weinhardt, C., van der Aalst, W., & Hinz, O. (2023). Welcome to the Era of
ChatGPT et al. Business & Information Systems Engineering, 65(2), 95–101. doi:10.1007/s12599-023-
00795-x
WarschauerM.TsengW.YimS.WebsterT.JacobS.DuQ.TateT. (2023, October 31). The affordances and
contradictions of AI-generated text for writers of English as a second or foreign language. doi:10.2139/
ssrn.4404380
Wu, L., Wu, Y., & Zhang, X. (2021). L2 Learner Cognitive Psychological Factors About Artificial
Intelligence Writing Corrective Feedback. English Language Teaching, 14(10), 10. Advance online
publication. doi:10.5539/elt.v14n10p70
Yan, D. (2023). Impact of ChatGPT on learners in a L2 writing practicum: An exploratory investiga-
tion. Education and Information Technologies, 28(11), 13943–13967. doi:10.1007/s10639-023-11742-4
Yeadon, W., Inyang, O.-O., Mizouri, A., Peach, A., & Testrow, C. (2022). The Death of the Short-Form
Physics Essay in the Coming AI Revolution. arXiv. . 2212. 11661 doi:10. 48550/arXiv
Zhai, X. (2022). ChatGPT User Experience: Implications for Education. SSRN Scholarly Paper. . 43124
18 doi:10. 2139/ ssrn
Zhang, M., & Li, J. (2021). A commentary of GPT-3 in MIT Technology Review 2021. Fundamental
Research, 1(6), 831–833. doi:10.1016/j.fmre.2021.11.011

288
Utilizing a ChatGPT Workshop to Foster Ethical Awareness

APPENDIX A: Survey for Instructors

1. Instructor’s Name
2. What is the name of the ELI writing course you’re teaching this semester? (e.g., ELI 73-3)
3. Please provide the course schedule for your ELI writing course (e.g., T/R 1:30-2:45 pm).
4. If you’re interested in scheduling a ChatGPT workshop for your ELI writing students, please se-
lect a suitable time slot from the schedule in the provided link, ensuring that you avoid the yellow
shaded ones. Additionally, kindly provide the name of your course when selecting the time slot.
multiple choice
◦◦ I want a workshop for my students.
◦◦ I don’t want a workshop for my students.
◦◦ Not decided yet.
5. How many students do you have in your class?
6. By Week 10, your students would have learned (and know)... checkboxes
◦◦ How to structure and make an outline for an academic paper
◦◦ How to organize academic paper and make it coherent (introduction, body, conclusion)
◦◦ How to develop content with a clear topic sentence and supporting details
◦◦ How to revise drafts (language use, transitional words, etc.)
◦◦ Other…
7. Please select the top three objectives you consider most important for a workshop involving ChatGPT.
(Your input will help me prioritize the workshop’s focus.) checkboxes
◦◦ Evaluate the usefulness and limitations of ChatGPT for academic writing.
◦◦ Revise and improve an email using ChatGPT effectively.
◦◦ Enhance an outline for an argumentative essay with the assistance of ChatGPT.
◦◦ Edit and refine a draft using ChatGPT as a writing tool.
◦◦ Properly cite sources with the guidance of ChatGPT for academic papers.
◦◦ Other
8. What specific improvements do you anticipate for your students’ writing skills from this workshop,
and in which areas do you believe the workshop can complement and enhance their skills? Please
provide detailed explanations. Open-ended
9. Have you already taught your students how to utilize ChatGPT in your course? If you have, could
you please share your experiences and provide any tips or advice for using ChatGPT in your course?
Open-ended

APPENDIX B: Workshop Plan

Workshop Description:

In this workshop, students will gain proficiency in utilizing the Large Language Model, ChatGPT,
with a critical approach to receive direct feedback during the self-revision process. The session will
also involve group discussions to foster awareness of ethical considerations associated with ChatGPT

289
Utilizing a ChatGPT Workshop to Foster Ethical Awareness

use. Participants will become acquainted with the fundamental features of the ChatGPT platform and
explore prompts for sample email revisions, enabling them to identify both the strengths and limita-
tions of ChatGPT-generated text. Subsequently, students will be equipped with strategies for effectively
leveraging ChatGPT prompts and will apply this knowledge to revise their own writing drafts, receiving
feedback on content, organization, and language usage.

Learning Objectives:

By the end of this workshop, students will be able to:

• Understand the ethical considerations of ChatGPT use.

• Evaluate ChatGPT’s strengths and weaknesses as a writing tool.
• Apply ChatGPT for effective feedback and revision in academic writing.

Materials:

Computers or tablets with internet access for each participant

Projector and screen for presentations: slides
Survey forms (Google Survey): Pre-workshop Questionnaire and Post-workshop Questionnaire
Workshop materials for activities (Google Docs)

• Chat GPT Do’s and Don’ts

• Email Prompt

Instructor Feedback
Workshop Length: 75 minutes

Before the Workshop:

• Request ELI teachers to provide links to their students’ writing drafts (these will be utilized during
the workshop; it might be advisable for teachers to discuss how to provide feedback).
• Distribute pre-workshop questionnaires ahead of time to streamline the workshop process (kindly
ask ELI teachers to allocate five minutes of class time for students to complete these question-
naires or to assign homework with time expectations).
• Examine students’ pre-workshop questionnaire responses to gain insights into their typical Chat
GPT usage habits and their perspectives on ethical concerns.

Workshop Procedure:

I. Introduction (3 minutes)

290
Utilizing a ChatGPT Workshop to Foster Ethical Awareness

• Welcome participants to the ChatGPT workshop.

• Introduce the workshop agenda, highlighting the importance of critical and ethical use of ChatGPT
for academic writing.
• Explain that the workshop will cover ethical considerations, best practices for effective use, and
practical hands-on activities.

• Listen to the workshop introduction.

II. Engaging Prior Knowledge (7 minutes)

• In pairs, have students discuss their prior experiences with ChatGPT.

• Engage in partner discussions and share their experiences and perceptions of ChatGPT.

(Students will talk about whether they’ve used ChatGPT before, how often they’ve used it, their
perceptions of its strengths and weaknesses, and any concerns they might have about using ChatGPT.)

• Share their thoughts and experiences with the class.

III. Ethical Considerations (15 minutes)

• Discuss ethical considerations when using ChatGPT, including the importance of critical thinking
and issues like plagiarism and attribution.
• Introduce ChatGPT Do’s and Dont’s, encouraging students to express their opinions on ethical
use. (Depending on the class level, the number of scenarios can be varied for the discussion.)

• Engage in discussions with their partners about ethical considerations using provided scenarios.
• Share their insights with the class.
IV. ChatGPT Walk-Through & Email Revision (15 minutes)

291
Utilizing a ChatGPT Workshop to Foster Ethical Awareness

• Provide a concise overview of ChatGPT, emphasizing its role in natural language understanding
and generation.
• Present two scenarios for email writing and demonstrate how ChatGPT can be used for revision.
• Encourage students to share their prompts and revised writings with their partners. (Depending on
the class level, the underlined parts can be omitted.)
• Introduce keywords for ChatGPT revision prompts and facilitate discussions on the differences
between student revisions and ChatGPT-generated content.

• Pay attention to the walk-through and explanations.

• Work in pairs to revise email drafts using ChatGPT.
• Explore ChatGPT’s capabilities by using different ChatGPT prompts for the Email revision
activity.
• Exchange prompts and revised drafts with their partners.
• Discuss the effectiveness of keywords for ChatGPT prompts and identify differences between
their revisions and ChatGPT-generated content. (Depending on the class level, the underlined
parts can be omitted.)
V. Feedback from ChatGPT (25 minutes)

<Teacher>:

• Introduce ChatGPT feedback prompts and keywords for feedback.

• Instruct students to use ChatGPT to receive feedback on their writing drafts.
• Encourage students to revise their writing based on ChatGPT feedback and share their experiences.
• Visit different groups to see if students need extra support.

• Use ChatGPT feedback prompts and keywords to request feedback on their writing drafts.
• Revise their writing drafts based on ChatGPT feedback.
• Discuss the effectiveness and helpfulness of ChatGPT feedback with their partners.
VI. Post-Workshop (10 minutes)

• Have students complete post-workshop questionnaires.

• Summarize the key take-home messages of the workshop, emphasizing ethical, effective, and
critical use of ChatGPT.
• Remind students to be aware of ChatGPT’s limitations.

292
Utilizing a ChatGPT Workshop to Foster Ethical Awareness

• Complete post-workshop questionnaires individually.

• Reflect on the workshop’s key messages and the importance of considering ChatGPT’s limitations
in their future use.
• Share their thoughts, ask any final questions or seek clarification.

APPENDIX C: Workshop Slides

293
Utilizing a ChatGPT Workshop to Foster Ethical Awareness

294
Utilizing a ChatGPT Workshop to Foster Ethical Awareness

295
Utilizing a ChatGPT Workshop to Foster Ethical Awareness

296
Utilizing a ChatGPT Workshop to Foster Ethical Awareness

APPENDIX D: Pre-Workshop Questionnaire

1. Name
2. Who is your ELI instructor?
3. What is your native language?

<Background information for writing competency>

1. Do you enjoy writing in English? (You might not be good at it, but you can still enjoy writing in
English.) rating: 1-5 (1=Not really, 5=Yes, I like writing in English.)
2. Which English skill do you feel most comfortable with? multiple choice
◦◦ Listening
◦◦ Speaking
◦◦ Reading
◦◦ Writing
3. How would you rate your level of English writing? Rating: 1-5 (1=beginner, 5 = advanced)
4. How much time you typically spend revising a major written assignment? (for example, a final
paper for a class) multiple choice
◦◦ 30 minutes - 1 hour
◦◦ 1 - 2 hours
◦◦ 3 - 4 hours
◦◦ More than 4 hours
◦◦ Others
5. How confident do you feel about revising your own writing? Rating: 1-5 (1=Not confident, 5 =
Very confident)
6. What kinds of feedback do you want to receive? What would be helpful for your writing revision
process? (Check up to three) Checkboxes
◦◦ spelling/grammar correction
◦◦ word choices for natural language use (vocabulary/ expressions)
◦◦ content (ideas)
◦◦ structure (organization)
◦◦ fluency (writing a lot)
◦◦ research and citations
◦◦ clarity and coherence
◦◦ Other

1. Have you used ChatGPT before? Multiple choice

◦◦ Yes, the free version.
◦◦ Yes, the premium version (I’m paying monthly fees to use ChatGPT 4.0).
◦◦ No
2. How often do you use ChatGPT for academic writing tasks? multiple choice

297
Utilizing a ChatGPT Workshop to Foster Ethical Awareness

◦◦ Daily/ Weekly/ Monthly/ Rarely/ Never/ Other

3. For which occasions do you utilize ChatGPT for academic writing tasks? (Check all that apply.)
Checkboxes
◦◦ Research papers and essays
◦◦ Thesis or dissertation writing
◦◦ Homework assignments
◦◦ Proofreading and editing assistance
◦◦ Generating ideas or brainstorming
◦◦ Citing sources and references
◦◦ Other
4. When using ChatGPT for writing assistance, what type of feedback are you looking for? (Select
all that apply) Checkboxes
◦◦ Grammar and punctuation corrections
◦◦ Vocabulary suggestions
◦◦ Sentence structure improvements
◦◦ Guidance on organizing ideas
◦◦ Recommendations for improving clarity and coherence
◦◦ Assistance with academic style and tone
◦◦ Help with research and citations
◦◦ Other
5. How confident are you in your ability to use ChatGPT for academic writing? Rating: 1-5 (1=Not
confident, 5 = Very confident)
6. Using ChatGPT can raise several ethical concerns including plagiarism (students submitting
AI-generated content as their own work, etc.). Do you have any concerns about using ChatGPT?
Rating: 1-5 (1=I’m not concerned, 5 = I’m concerned)
7. How satisfied are you with the feedback and suggestions provided by ChatGPT for your writing?
Rating: 1-5 (1=Not satisfied, 5 = Very satisfied)
8. Could you please provide a detailed explanation of your satisfaction level with ChatGPT?

APPENDIX E: Post-Workshop Questionnaire

1. Name
2. Who is your ELI instructor?
3. Please copy and paste the chatGPT link of the workshop activities.

<ChatGPT Workshop Feedback>

1. Based on my experience, the level of workshop activities was: Rating: 1-5 (1=too elementary, 5
= too advanced)
2. Overall, the quality of the workshop was multiple choice
◦◦ Poor/ Fair/ Good/ Outstanding

298
Utilizing a ChatGPT Workshop to Foster Ethical Awareness

3. The workshop materials (e.g. visual aids, writing samples, etc.) were: multiple choice
◦◦ Poor/ Fair/ Good/ Outstanding
4. Should the content and/or activities for future chatGPT workshops be changed? Please share your
comments below.

<Learning to Effectively and Critically Use ChatGPT>

1. As a result of this workshop, my confidence about my English writing has: Rating: 1-5 (1=not
increased at all, 5 = significantly increased)
2. As a result of this workshop, I can now revise my own writing more effectively based on ChatGPT
suggestions and feedback. Rating: 1-5 (1=strongly disagree, 5 = strongly agree)
3. As a result of the workshop, I now have a better understanding of ChatGPT’s strengths and weak-
nesses. (1=strongly disagree, 5 = strongly agree)
4. As a result of the workshop, I now have a better understanding of how to use ChatGPT critically
avoiding ethical issues. (1=strongly disagree, 5 = strongly agree)
5. What kind of ChatGPT’s feedback was helpful for your own draft revision process? Checkboxes
◦◦ spelling/grammar correction
◦◦ word choices for natural language use (vocabulary/ expressions)
◦◦ content (ideas)
◦◦ structure (organization)
◦◦ fluency (writing a lot)
◦◦ research and citations
◦◦ clarity and coherence
◦◦ Other
6. How frequently will you use ChatGPT after this workshop? Multiple choice
◦◦ I am not going to use ChatGPT frequently.
◦◦ I will use ChatGPT the same amount as before.
◦◦ I am going to use ChatGPT frequently.
◦◦ Other
7. Please leave any other comments or suggestions you have for future workshops. Mahalo!

299
300

Chapter 14
Leveraging AI and
Pluralistic Approaches for
Language Teaching:
A Focus on Inter-Comprehension
Between Related Languages

Lourdes Barquín Sanmartín

https://orcid.org/0000-0001-7892-2177
University College Dublin, Ireland

ABSTRACT
This chapter introduces the pluralistic teaching approach of inter-comprehension utilizing the AI tool
ChatGPT. Its objective is to heighten inter-comprehensive awareness among native English speakers
studying Spanish and facilitate the comprehension of structurally asymmetrical grammatical phenomena
between Romance languages and English. Specifically tailored to the British educational context, where
the typical language sequence comprises L1 English, L2 French, and L3 Spanish, this chapter draws
support from L3 acquisition literature. Focused on the aspectual contrast perfective/imperfective, less
prominent in English compared to Romance languages, the author showcases how to generate parallel
contrastive analyses of Spanish/French/English translations through ChatGPT.

INTRODUCTION

This chapter advocates the integration of the Pluralistic Approach of Inter-Comprehension Between
Related Languages into language classrooms, leveraging ChatGPT as a facilitative tool. Our primary
focus is on assisting teachers instructing Spanish as a third language (L3) in the UK, a linguistic trend
increasingly observed among British learners of Foreign Languages (FL). Specifically, we delve into the
implementation within Scotland’s Pluralistic 1+2 Approach and the incorporation of Spanish as an L3
within the English curriculum. In these contexts, Spanish is introduced as the L3 after English, which

DOI: 10.4018/979-8-3693-0872-1.ch014

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

Leveraging AI and Pluralistic Approaches for Language Teaching

acts as a first language (L1), and French, which is taught as a second language (L2). Moreover, the ap-
plicability of this model extends beyond the UK, potentially benefiting countries like the US, where
English is the L1, Spanish the L2, and French L3 in their FL curricula (Lusin et al., 2023).
The focus of this chapter is to recommend the integration of ChatGPT as a tool to create engaging
classroom activities that enhance students’ understanding of how languages work together. We focus
particularly on tackling challenging grammar concepts that lack direct equivalence or clarity in a student’s
native language or their previously learned languages. By employing ChatGPT for translation and develop-
ing side-by-side comparisons, students can grasp how different languages handle specific grammar rules.
This approach nurtures students’ ability to recognize similarities and differences between languages, a
skill crucial not only for mastering an L3 like Spanish but also for learning additional languages (Ln).
By comparing complex grammar rules in Spanish and languages students already know, they can identify
the most helpful prior language to aid their learning of the new language. In the UK, students commonly
know English as their L1 and French as an L2. Since students learn these languages sequentially, our
goal is to take advantage of the similarities between French L2 and Spanish L3 to assist English-speaking
learners in understanding broader grammatical concepts common to Romance languages. Specifically,
we focus on the ‘imperfective aspect,’ expressed as imparfait in French and imperfecto in Spanish, a
past tense that lacks a morphological equivalent in English, thus requiring English to employ different
grammatical structures to convey a similar concept.
This chapter accentuates the pedagogical utilization of ChatGPT, specifically within the British FL
education setting, aiming to enhance the comprehension of language as a universal concept. Rather than
focusing solely on teaching a single language in isolation, as traditional methods often do, this approach
advocates a pluralistic methodology that embraces the incorporation of two or more languages within
the classroom. This method embraces the integration of multiple languages in the teaching of the target
language, acknowledging language as a universal concept that manifests in diverse forms across different
languages. By leveraging ChatGPT for translation, this approach promotes plurilingualism by highlight-
ing shared linguistic patterns across different languages and, thus, promoting a more holistic approach
to language acquisition. Teachers can utilize ChatGPT as a translation tool to create reflective in-class
tasks. These tasks, employing parallel contrastive analysis across two or three translations, are valuable
for introducing or reinforcing new grammatical elements and assessing students’ progress.
The application of ChatGPT explored in this chapter primarily focuses on its value from a teacher’s
standpoint, aiding in planning and resource development through ChatGPT’s translation tool. How-
ever, beyond its role in teaching, we argue that ChatGPT can also be harnessed for independent and
self-directed learning from a student’s perspective. As pluralistic approaches, especially the concept of
Inter-Comprehension Between Related Languages, remain less widely understood in educational settings,
the initial sections of this chapter aim to clarify these approaches and discuss the reasoning behind our
interest in adopting this innovative teaching methodology.

TEACHING FOREIGN LANGUAGES IN ENGLAND

Before we expand on how we can leverage ChatGPT to design reflective tasks when introducing new
and complex grammatical phenomena in the Spanish classroom, it is essential to provide an overview of
the British foreign language teaching and learning landscape and its inclination towards multilingualism.
The prevailing FLs in both British secondary schools (Collen, 2020; 2021; 2022; 2023; Tinsley & Board,

301

Leveraging AI and Pluralistic Approaches for Language Teaching

2013) and British Higher Education Institutions (Critchley et al., 2021; Critchley et al., 2022) are French,
Spanish, and German. However, it is noteworthy that in primary schools, French takes precedence as the
primary FL (Figure 1). This tradition dates back to the historical significance of France as a European
power in the late 17th century and its role as a lingua franca. During that era, FL learners in the UK
predominantly studied French, many of whom are now primary school French teachers. Consequently,
almost 73% of primary schools offer French, while Spanish accounts for only 28% (Collen, 2023, p.8).
Amidst the general decline of FLs in the British compulsory education setting compared to other
subjects (e.g. Sciences, English Language and Literature), the Language Trends surveys from the last
few years show a gradual increase in the number of enrollments for Spanish in British secondary edu-
cation, which aligns with Instituto Cervantes’ latest annual report (Instituto Cervantes, 2023), where it
is shown that Brexit has led to an increase in the relative importance of Spanish within the EU and has
stimulated the demand for its study.
The dominance of French extends into compulsory secondary education in England, making it the
FL with the highest number of enrollments in the final exams or GCSE. However, the trend shifts in the
two years preceding university education, known as A levels. In 2018, Spanish overtook French for the
first time in A-level examinations (Tinsley, 2019, p. 4-5) and has maintained its position as the most
popular FL at this educational stage for four consecutive years (Collen, 2023).

Figure 1. Most frequently taught languages in English primary schools (Collen, 2023, p. 8)

TEACHING FOREIGN LANGUAGES IN SCOTLAND

Scottish primary education mirrors England’s sequential order of FLs, with French1 being the most of-
fered L2, taught in 98% of Scottish primary schools, and Spanish the most popular L3, being taught in
48% of schools that provided a third language (Scottish Government, 2022). This reflects a linguistic
paradigm in Scottish primary education where French is introduced first as an L2 (Figure 2), and Span-
ish is later taught as an L3 (Figure 3).

302

Leveraging AI and Pluralistic Approaches for Language Teaching

Figure 2. Number of Scottish primary schools providing an L2 (Scottish Government, 2022)

Figure 3. Number of Scottish primary schools providing an L3 (Scottish Government, 2022)

The language policy in Scottish primary education follows a plurilingual approach known as the
1+2 Approach (Scottish Government, 2016, 2020). This is the only plurilingual language education
program in the UK and aligns with the plurilingual initiatives of UNESCO (2003), the Common Euro-
pean Framework of Reference for Languages (CEFR thereafter) (Council of Europe, 2001, 2021), and
the Framework of Reference for Pluralistic Approaches to Languages and Cultures (FREPA thereafter)
(Candelier et al., 2013). This approach reflects the positive and European-oriented attitude of the Scot-
tish population towards language teaching. Notably, the 2016 Scottish Social Attitudes Survey revealed
an overwhelming 89% of Scottish respondents advocating for FL acquisition commencing at the age of

303

Leveraging AI and Pluralistic Approaches for Language Teaching

five, a statistic that serves as a robust indication that the prevailing attitudes toward early FL education
remain consistent in 2023 (Scottish Government, 2016).
It is important to note that Scotland’s approach is an exception in what has been a predominantly
monolingual tradition in the UK. In 2016, the UK had the highest number of monolingual individuals in
Europe, with 65.4% of adults not speaking any foreign languages, compared to the European average of
31.8%. Additionally, there was a 30% increase in monolingual individuals from 2007 to 2016, indicat-
ing a marginalization of foreign languages in the UK (EUROSTAT, 2016; Kelly, 2018). This chapter
challenges the notion that the UK is predominantly monolingual and highlights a growing cohort of
plurilingual British students learning French L2 and Spanish L3.

TEACHING FOREIGN LANGUAGES IN THE BRITISH

HIGHER EDUCATION SETTING

The most recent Language Provision surveys in British universities reveal a similar language landscape to
previous educational cycles. French, Spanish, and German remain the top three languages offered, with
French and Spanish being the only ones available in 100% of surveyed institutions (Collen, 2023; Critchley
et al., 2021; Critchley et al., 2022; Polisca et al., 2019). French continues to dominate British universities,
boasting the highest number of enrollments in undergraduate studies and non-credit language courses.
However, Spanish is closely following, and a paradigm shift is expected in the near future (Critchley et al.,
2021; Critchley et al., 2022). It is essential to note that British universities annually receive a considerable
influx of international students, a significant portion of whom are English as an Additional Language (EAL)
speakers. While not all students possess the language profile of French L2 and Spanish L3, a substantial
number are engaged in learning Spanish as an L3, with English as their L2. This diverse linguistic blend
accentuates the critical need for distinguishing between the methods involved in teaching an L2 versus an
L3 and, thus, catering to the distinct cognitive attributes of students engaged in learning more than one FL.
The sections above, which contextualize FL teaching curricula in the UK and advocate for the inte-
gration of ChatGPT into our teaching resources, intricately illustrate the evolving trends in plurilingual
education within the UK. Notably, the increasing interest in achieving proficiency in multiple languages
is not limited to the UK but extends to many European countries. In the current landscape, marked by
the widespread normalization of technology and social media use, there arises a need to reassess our
perception of FL learners. Rather than viewing them solely as monolingual individuals, it is crucial to
recognize them as active participants woven into a vibrant tapestry of diverse cultures and languages.
This societal and cultural shift underscores the necessity to move beyond terminology like ‘complete
beginner’ or ‘pure monolingual’ as well as the conventional portrayal of FL/L2 learners, recognizing
the increasing number of individuals embracing an L3 or Ln.
In our dynamic and ever-evolving linguistic landscape, embracing plurilingualism has become a
prominent trend. Translation, as a tool to foster inclusivity and pluralistic language teaching method-
ologies, assumes a crucial role within this context. By incorporating ChatGPT for translation purposes,
students are exposed to multiple languages and empowered to tap into their existing linguistic knowl-
edge bank, drawing from both their native language(s) and previously acquired foreign languages. This
comprehensive approach not only widens students’ lexical and grammatical understanding but also
strengthens their meta- and inter-linguistic awareness, which can significantly enhance the acquisition
of an L3 or subsequent Ln.

304

Leveraging AI and Pluralistic Approaches for Language Teaching

INTRODUCTION TO PLURALISTIC APPROACHES

The so-called ‘pluralistic approaches’ are outlined in the FREPA (Candelier et al., 2013), a framework
rooted in the CEFR (Council of Europe, 2001, 2021), expanding upon it to meet the goal of updating
our L2 teaching practices in a society where multiple languages coexist, and where every citizen, albeit
at varying levels of competence, possesses knowledge of more than one language and, as a result of
an increasingly hyperconnected society, is constantly exposed to other languages and cultures through
different forms of media, such as social media or the television.
Every speaker, including our own learners, brings with them a linguistic background, which constitutes
a key source of knowledge in L3 learning. Pluralistic approaches emerge in response to the rise of social
multilingualism in the European continent and the consequent increase in plurilingual competence among
citizens and language learners. This represents a paradigm shift that emphasizes the need to reinforce the
‘multilingual competence’ and ‘multicultural competence’ of L2 learners to equip them to effectively
navigate the professional, academic, and sociocultural landscape of an increasingly hyperconnected and
globalized society (Council of Europe, 2001, 2021). Despite the prevailing monolingual trends in the
formal education system of the United Kingdom, the transition to pluralistic approaches is beginning
to take shape through educational projects such as the 1+2 Approach in Scottish primary education
(Scottish Government, 2016, 2020). However, this initiative, as of now, stands as the sole indication of
interest in pluralistic approaches within the British territory.

INTER-COMPREHENSION BETWEEN RELATED LANGUAGES

The concept of globalization, although present throughout human history, has notably surged in the early
21st century due to increased migration and heightened hyper-connectedness across social, communicative,
and technological realms (Quan-Haase and Wellman, 2005). This era has seen English hold a dominant
position as a global lingua franca; nevertheless, UNESCO (2003, 2021) emphasizes the importance of
promoting FL education to support a plurilingual and pluricultural society.
Given our usage of the concept ‘plurilingual’, it is essential to distinguish between the notions of
‘multilingualism’ and ‘plurilingualism’. The former refers to the coexistence of multiple languages within
a specific nation or community, such as Europe being recognized as a multilingual continent. On the
other hand, the latter operates at the individual level, extending beyond knowing multiple languages. It
requires proactive utilization of one’s complete linguistic and extralinguistic repertoire, enhancing com-
municative competence through the interaction and enrichment of languages, known as ‘interlanguage.’
The prevalence of plurilingualism among FL learners has led to the emergence of ‘pluralistic ap-
proaches’ (Candelier et al., 2013; Council of Europe, 2021) to capitalize on these students’ previous
linguistic knowledge. The psycholinguistic premise that adult learners possess a wealth of life experiences
before learning a new language challenges the concept of an absolute initial level or complete beginner,
a perspective that encourages students to acknowledge that their language learning journey builds upon
existing knowledge and experiences.
This paradigm shift in language acquisition moves away from considering languages as independent
entities and instead embraces language as a fundamental principle inherent in all communication (Braun-
müller, 2007). By adopting this mindset, learners realize that delving into a new language taps into a wealth

305

Leveraging AI and Pluralistic Approaches for Language Teaching

of interconnected knowledge sources, as shown in Figure 4. This shift empowers students, reduces intimi-
dation associated with language learning, and enhances their intrinsic motivation to master the language.

Figure 4. Sources of knowledge in foreign language learners

Therefore, it becomes evident that having prior knowledge of the target language, receiving formal
instruction, or possessing an advanced level are not essential prerequisites for accessing and engaging
with a new language. Rather, the focus is on tapping into the wealth of diverse knowledge and experi-
ences that adult learners bring with them, capitalizing on the interconnected nature of language. This
perspective aligns with the idea that learners are not starting from a blank slate but are building on their
preexisting cognitive resources.
Collectively, the sources of knowledge shown in Figure 4 constitute our plurilingual competence,
continuously available to students as a source of support in the acquisition process of the new foreign
language. The Inter-Comprehension approach harnesses this prior knowledge, allowing teachers to guide
students in recognizing these sources of knowledge and employing them effectively for comprehend-
ing new texts written in different languages. With this approach, students can draw upon their existing
knowledge, actively applying it to enhance their proficiency in acquiring a new foreign language. Rather
than starting completely anew, they rely on these well-established knowledge bases for support.
This chapter challenges the deficiencies of traditional teaching approaches and underscores the
current acquisitive potential and relevance of pluralistic approaches. This chapter focuses on the Inter-
Comprehension Between Related Languages, first, because it is an early approach in the UK, relatively
unknown among teachers, with minimal presence in FL classrooms, and, thus, in need for wider outreach
amongst teachers and researcher; second, because of its immense relevance in the context of FL educa-

306

Leveraging AI and Pluralistic Approaches for Language Teaching

tion in the UK, where the two most offered and demanded FLs are French and Spanish, two Romance
languages with high typological proximity and structural symmetry between them.
In order to showcase the potential of inter-comprehension combined with ChatGPT, we narrow its focus
to one intricate morphosyntactic phenomenon that frequently presents challenges and pose a notable risk
of fossilization for English-speaking learners of Spanish: the aspectual contrast perfective/imperfective.
It is important to note that this grammatical feature is morphologically marked in inflectional languages
like French and Spanish. In contrast, English, because of its limited use of inflections, relies on different
morphosyntactic strategies such as word order or auxiliary verbs to express imperfective aspect.
British learners, typically equipped with French as their second language (L2) and Spanish as their
third language (L3), can substantially enhance their approach to learning Spanish L3 by harnessing the
positive transfer from their knowledge of French. From an educational perspective, artificial intelligence
tools, exemplified by ChatGPT, offer exceptional utility in crafting teaching materials to bolster students’
inter-comprehension abilities and exploit positive transfers as a learning tool. One practical approach is
the generation of translations of Spanish texts into other Romance languages, whether they geographi-
cally coexist with Spanish or not, including languages like Galician, Catalan, Portuguese, French, or
Italian, among others.

INTER-COMPREHENSION, NOTICING, LONG-TERM MEMORY, AND CHATGPT

The Noticing Hypothesis in Foreign Language Acquisition, introduced by Schmidt (1994, 2010), serves
as a pivotal framework on how language structures assimilate into long-term memory. According to this
well-established theory, learners acquire linguistic structures by consciously focusing on features embed-
ded in the input – a cognitive process termed ‘noticing.’ The deliberate awareness and observation of
these linguistic elements are instrumental in their absorption and eventual storage in long-term memory.
In the domain of language learning, ChatGPT’s ability to translate into different languages plays a
central role in facilitating the principles of the Noticing Hypothesis. Rather than directly engaging in
the translation process themselves, learners benefit from ChatGPT’s proficiency in generating transla-
tions across languages like English, French, and Spanish. Subsequently, students partake in reflective
exercises, conducting contrastive and inter-comprehensive analyses among these translations, aimed at
noticing, discerning, and comprehending underlying grammatical nuances. We argue that this is par-
ticularly beneficial when we are teaching grammar points that do not share structural symmetry with
the student’s mother tongue; for example, the imperfect tense is not morphologically marked in English,
but it is in French and Spanish.
This approach instigates a critical examination of the divergences and convergences present within
translations across the languages. By actively scrutinizing and comparing these translations, students im-
merse themselves in the process of ‘noticing’ grammatical patterns, syntactical variances, and linguistic
intricacies across the linguistic spectrum. This analytical endeavor fosters a comprehensive understanding
of grammar, fostering an awareness of the idiosyncrasies inherent in each language’s structural makeup
and, similarly, the underlying similarities across languages, despite their typological distance.
Guided by ChatGPT-generated translations, learners will actively engage in the process of ‘noticing’
grammatical subtleties, similarities, and discrepancies. Through observing how various linguistic elements
manifest differently across languages, students develop a heightened ability to identify and understand

307

Leveraging AI and Pluralistic Approaches for Language Teaching

grammatical disparities and resemblances. This not only fortifies students’ retention of language structures,
but it cultivates critical thinking around grammar and a more autonomous approach towards FL learning.

ASPECTUAL CONTRAST IN ENGLISH, FRENCH, AND SPANISH

To illustrate the practical application of ChatGPT in crafting inter-comprehension tasks, our focus cen-
ters on a specific grammatical aspect found in Romance languages like French and Spanish but notably
absent in English: the perfective/imperfective aspectual contrast. This pertains to the choice between
using the ‘imperfect’ and ‘preterite’ tenses in past narratives in Spanish.
This linguistic feature, prevalent in Romance languages, presents considerable challenges for Eng-
lish learners (Andersen, 1991; Hasbún, 1995; Ramsay, 1990; Salaberry, 1997). The complexity stems
from French and Spanish expressing grammatical aspect at a morphological level, while English lacks a
direct structural equivalent to the Romance imperfect tense. Consequently, English relies on alternative
strategies like the Past Continuous (e.g., ‘I was eating’) and lexical constructions such as ‘used to’ and
‘would’ to convey habitual actions and continuity.
For instance, the phrase ‘cocinaba un postre’ (1) signifies an ongoing action without a specific tem-
poral boundary. In English, this could be expressed using the Past Simple (1a) or the Past Continuous
(1b). However, the Past Simple may lead to aspectual ambiguity by not conveying dynamism or dura-
tion. To compensate for this inflectional gap, English employs the progressive ‘-ing’ form to impart the
imperfective aspect (1b). Therefore, English effectively portrays aspectual differences through both the
Past Simple and the Past Continuous, with the latter constructed using the ‘be + -ing’ periphrastic form
(Declerck, 2006).

(1) Lucía cocinaba un postre

a. Lucía cooked a dessert
b. Lucía was cooking a dessert

As a general rule, the Spanish periphrastic ‘estar + gerundio’ cannot be considered equivalent to
the imperfect tense since the latter encompasses a broader range of aspectual notions compared to the
periphrastic form. The periphrasis specifically highlights actions (not states) in progress that align at a
certain point (or interval) with the reference event (2b). Furthermore, the periphrasis emphasizes the
internal dynamism of the event.

(2) a. Raquel preparaba la comida cuando su hija llegó a casa.

b. Raquel estaba preparando la comida cuando su hija llegó a casa.

The distinction between the indefinite/imperfect contrast in Romance languages stands in contrast to
English, which strictly relies on the progressive/non-progressive contrast (Montrul & Slabakova, 2003).
This differentiation traces its origins back to the concept of ‘co-preterite’ (Bello, 1847), denoting an
imperfect tense coexisting with another past event. For instance, in the context of example (3), the rain
persisted for a delimited duration (i.e. hence the closed endpoints in the illustration) concurrent with
the arrival, which acts as a temporal reference point. However, it remains unclear whether the rain was

308

Leveraging AI and Pluralistic Approaches for Language Teaching

ongoing before the perfective event or if it continued after its culmination. This concurrent existence is
articulated in English through the utilization of the Past Continuous (3), conveying simultaneity with
the referenced event.

English lacks an equivalent past tense akin to the imperfect, prompting an approach through a temporal
lens (Bello, 1847; Rojo, 1990) where the Past Simple, much like the indefinido tense, functions as the
default perfective form. To differentiate Past Simple instances whose interpretation is not purely perfective,
the perfective aspect can be regarded as a functional category [±perfective] (Giorgi & Pianesi, 1997).
In English, the value [-perfective] holds little relevance as the value [+perfective] is universally as-
sociated with all non-stative predicates. Conversely, in Romance languages, the perfective value may
align with both [-perfective] and [+perfective] values due to the indefinite/imperfect contrast (Montrul
& Slabakova, 2003). This [±perfective] system aims to enlighten native English speakers that certain
past tense verbs do not consistently adhere to the [-perfective] value, a factor often leading to ambiguity
in stative predicates.
The Past Simple in English is typically seen as conclusive. However, to convey the aspectual nu-
ances akin to the imperfect tense, one must resort to using the Past Continuous. Unlike Spanish, stative
predicates expressed in the Past Simple within English remain neutral in terms of aspect, disregarding
the telicity of the predicate. Consequently, they can be understood either as prolonged states over time
(imperfective value) or as specific, delimited events (perfective value).
This lack of alignment between Spanish and English creates confusion among learners of Spanish
as a foreign language. For instance, in example (4), the state could be interpreted as ‘John [was/was
being] sick,’ showcasing an aspectual difference not accounted for in English, as illustrated in Table 1.

Table 1. Examples of lexical aspect (Andersen & Shirai, 1994)

Examples Interpretation Lexical Aspect

(4) Jonh was ill It is not known if John is still sick State
(3) John cleaned all evening John has finished cleaning already Activity
(4) John cooked dinner John has already finished making dinner Accomplishments
(5) John arrived home John has already arrived home Achievements

Despite the differences between English and Spanish, there are some values of the preterite and im-
perfect tenses that can be considered equivalent to the Past Simple and Past Continuous, respectively.
In perfective predicates, the Past Simple and the preterite express punctual events that have ended (6),

309

Leveraging AI and Pluralistic Approaches for Language Teaching

and in imperfective predicates, the Past Continuous and the imperfect tense can also express past events
that were in progress (7).

(6) María llegó tarde al trabajo

María arrived late to work
(7) Cuando mama llegó a casa, veía la tele
When mum arrived home, I was watching telly

Stative predicates are not compatible with the progressive form in English (8), thus constituting cases
of interlinguistic inequivalence between English and Spanish. Although states in gerunds are not proto-
typical combinations in English, there are special uses where English speakers deliberately choose the
-ing form to lend dynamism and temporality to the verb. In example (9), this strategy allows the speaker
to distinguish between the fact that Mary’s behavior was not appropriate in a past and transitory moment
(9a) and another where the event becomes a property of Mary’s personality (9b).

(8) Había estudiantes en clase

There were being students in class
(9) a. Mary was being rude and I grounded her
b. Mary was rude and I grounded her

English relies on grammatical structures to compensate for its limitations in expressing aspectual
nuances. In the context of the habitual imperfect, English utilizes various forms such as the Past Simple
(12), the Past Continuous (13), the structure ‘used to’ (14), or its analogous form ‘would’ (15) (Cholij,
1994, p.87). The periphrastic constructions (14) and (15) serve to emphasize the habitual nature of
the event and serve as equivalents to expressing actions or routines in the past, resembling ‘used to’ or
‘would’ followed by the infinitive (Kattan-Ibarra & Pountain, 2004)

(10) Mi marido hacía la cena todos los días

My husband cooked dinner every day
(11) María preparaba la cena cuando llegué
María was cooking dinner when I arrived.
(12) El año pasado iba al gimnasio dos veces por semana
Last year I used to go to the gym twice a week.
(13) Mamá se enfadaba si no hacíamos los deberes
Mum would get angry if we did not do our homework.

The absence of structural equivalence at a linguistic level among the three main languages in terms of
aspectual contrast presents a significant opportunity for the incorporation of reflective tasks. These tasks
primarily emphasize conscious attention to input, supported by parallel contrastive analyses among the
three languages. By simultaneously presenting the same text in the past in these languages and highlight-
ing their differences and similarities, it aims to train and enhance the learner’s interlinguistic awareness
and metalinguistic knowledge. This approach fosters the learner’s metalinguistic consciousness about
language as a universal concept and, more specifically, cultivates interlinguistic awareness regarding
the internal dynamics of the Romance languages under study.

310

Leveraging AI and Pluralistic Approaches for Language Teaching

We believe it is both crucial and pressing to focus on the development of interlinguistic awareness,
particularly among English-speaking learners. Oftentimes, due to a higher cultural interest in literature
and the relatively straightforward linguistic and grammatical nature of the English language, these
learners may not delve into deeper grammar or more terminological aspects while studying their native
language in compulsory education. In the United Kingdom, the English Language and Literature cur-
riculum in secondary schools mainly prioritizes oral and written comprehension and production skills.
Consequently, students seldom have the chance to explore the morphosyntactic structure of their native
language, resulting in a lack of a fundamental metalinguistic framework that would facilitate their en-
gagement with subsequent languages.
To illustrate, we initially offer a concise overview of the English subject in the national curriculum
for Key Stage 3 (11-12 years) and Key Stage 4 (13-15 years) in England. Subsequently, we present an
excerpt from the National 3 curriculum (13-14 years) in Scotland, delineating the objectives of the
English subject.

A high-quality education in English will teach pupils to speak and write fluently so that they can commu-
nicate their ideas and emotions to others and through their reading and listening, others can communicate
with them. Through reading in particular, pupils have a chance to develop culturally, emotionally, intel-
lectually, socially and spiritually. Literature, especially, plays a key role in such development. Reading
also enables pupils both to acquire knowledge and to build on what they already know. (Department
for Education, 2014, p.13)

The [English] Course offers learners opportunities to develop and extend a wide range of skills. In par-
ticular, the Course aims to enable learners to develop the ability to: (a) listen, talk, read and write, as
appropriate to purpose, audience and context (b) understand, analyse and evaluate texts, as appropriate
to purpose and audience in the contexts of literature, language and media (c) create and produce texts,
as appropriate to purpose, audience and context (d) apply knowledge of language. (Scottish Qualifica-
tions Authority, 2014)

A well-developed awareness of linguistic and interlinguistic aspects, coupled with the strategic utili-
zation of technological tools like ChatGPT, empowers students to become autonomous and independent
learners. This proficiency enables them to autonomously identify both symmetrical and asymmetrical
areas, particularly evident among British students, between French and Spanish. By leveraging ChatGPT’s
capabilities in providing translations and comparative analyses, learners can effectively enhance their
learning process through conscious and deliberate utilization of positive transfer while simultaneously
preventing or anticipating negative transfers.
This pluralistic philosophy transcends conventional didactic approaches. It perceives the learning of
foreign languages as an ongoing and lifelong evolutionary continuum, further facilitated by innovative
tools such as ChatGPT. Here, acquired skills are not confined solely to a single foreign language but
are instead transferable across all known and future encountered foreign languages. This perspective
emphasizes the continual growth and applicability of language skills throughout an individual’s lifetime,
with ChatGPT serving as a facilitator in fostering this multilingual and transferable proficiency.

311

Leveraging AI and Pluralistic Approaches for Language Teaching

DESIGNING INTER-COMPREHENSIVE RESOURCES WITH CHATGPT

This chapter proposes the use of ChatGPT as a translation tool to present new and complex grammati-
cal phenomena, specifically those aspects that are not marked in the students’ mother tongues. As an
example of unmarked phenomenon in English but marked in Romance languages, we focus on the
aspectual contrast perfective/imperfective as this is known to generate great difficulty when it comes
to teaching it in class and, from a students’ perspective, to understand it. Thus, this grammatical area
lead often leads to fossilization of misconceptions and error due to lack of a proper comprehension of
‘aspect’. The proposal is addressed at intermediate and upper-intermediate level Spanish classes ranging
from A2-B2 (Council of Europe, 2001, 2021), where the past tenses are introduced.
This proposal does not present the results of an actual case study where ChatGPT has been used in
a Spanish class. Rather, it proposes the potential benefits of using ChatGPT to promote plurilingual-
ism and, thus, this proposal encourages further investigation. This idea endorses the inductive teaching
approach, which initiates learning with specific examples or observations, guiding students to derive
general conclusions or principles. Rather than relying solely on established theories or rules presented in
textbooks that predominantly emphasize the target language and exclude references to other languages,
this method encourages active learning from a pluralistic lens. The inductive nature of this proposal
promotes observation, reflection, and pair discussions on how grammar works in the target language
(i.e. Spanish) and recognizes similarities and differences with other languages students already know
(i.e. English and French).
We utilize ChatGPT to generate translations in twos or threes for pedagogic purposes. These transla-
tions are then converted into well-designed and accessible reflective tasks to be explored conceptually
in a classroom setting, with the support and guidance of the teacher. Given the high levels of difficulty
encountered in teaching and learning the aspectual aspect in Romance languages, using contrastive
analysis of translations and identifying differences and similarities across them can promote the ‘notic-
ing’ of grammar in different languages.
From a learning perspective, translation can significantly enhance the ‘noticing’ process of the forms
(i.e. grammar) and, adopting a pluralistic approach, can help increase students’ interlinguistic aware-
ness by highlighting differences and similarities between languages. ChatGPT serves as a key tool in
designing in-class reflective tasks that encourage engagement and active learning and contributes to
saving time in designing teaching resources. Nevertheless, the use of ChatGPT for translation purposes
comes with its own challenges; notably having basic knowledge of all three languages involved before
carefully proofreading all three translations.
Aside from its role in generating teaching materials, ChatGPT can serve as a valuable learning tool
for students to independently review and practice Spanish at their own pace. Through incorporating
reflective tasks prompted by ChatGPT within the classroom setting, we can showcase its capabilities
and inspire students to autonomously explore using ChatGPT for their personal revision. This initiative
has the potential to significantly enrich their language-learning journey by encouraging independent
exploration and engagement with ChatGPT for Spanish revision.
To efficiently execute a reflective task using ChatGPT, we can use two stages. In Stage 1, it is crucial to
formulate a prompt that encompasses all relevant contextual details. This includes the storyline, language
requirements, desired level of difficulty, the linguistic profile of the students, and the specific grammar
structures intended to be present in the text. Crafting a prompt of this nature ensures that the vocabulary
and grammatical constructions used are comprehensible and suitable for the students’ competency level.

312

Leveraging AI and Pluralistic Approaches for Language Teaching

Stage 1. Please write an adapted version of the Beauty and the Beast in the past in Spanish. The level
of difficulty must be addressed at a B1 Spanish class of native English speakers who are working
towards a B2 by the Common European Framework of Reference. Make sure you include the three
main preterites in Spanish: the pretérito indefinido, imperfecto and pluscuamperfecto.

Following Stage 1, we proceed to Stage 2 where we utilize the Spanish version as a foundational refer-
ence for generating translations into English and French. It is imperative within the prompt to explicitly
clarify that, despite their morphological differences, the ‘passé composé’ in French and the ‘pretérito
indefinido’ in Spanish exhibit resemblances in their temporal and aspectual functions. While the archaic
‘passé simple’ in French has become obsolete, the ‘passé composé’ stands as the predominant form for
articulating past events in spoken French, primarily conveying perfectivity. Despite these disparities,
we regard both tenses as equivalent given that they both serve the purpose of recounting past actions.

Stage 2. Now, please translate this story into English and French. Use a table with three columns, one
per language. Also, please highlight in bold all cases where you use verbs in the past, including
indefinido, imperfecto and pluscuamperfecto. In English, you will have to look out for all Past
Tenses. In French, you will have to highlight the imparfait (equivalent to Spanish imperfecto) and
passé composé. Please treat the passé composé as the equivalent value to Spanish indefinido.

Following Stage 2, upon receiving the three versions of the story (Spanish, French, and English)
from ChatGPT, we can devise a reflective task that employs a square-coded system with (dis)continuous
border lines (Table 2). This system aims to facilitate the identification and comparison of discrepancies
and similarities across these languages. Utilizing a contrastive analysis between the Spanish imperfecto
and the French imparfait, both depicted in continuous lines, we can uncover their structural symmetry
(Westergaard, Mitrofanova, Mykhaylyk & Rodina, 2017), wherein the imperfective is used in precisely
the same narrative positions in both Romance languages (Bardovi-Harlig, 1998, 2000).
Furthermore, this comparative exercise allows students to observe that English (third column in Table
2) lacks morphological marking for the imperfect value, as the Past Simple tense encompasses both
imperfective and perfective values (Giorgi & Pianesi, 1997). Through this parallel contrastive analysis,
learners gain insights into the nuanced differences in how these three languages express past events,
providing a deeper understanding of their structural and functional variations.

CHALLENGES AND PROPOSED SOLUTIONS

Challenge 1: Diverse Language Backgrounds

The most apparent challenge in this task proposal is assuming that all Spanish students possess prior
knowledge of French. While our primary focus revolves around a growing cohort of British students
proficient in French as a second language (L2) and Spanish as a third language (L3), it is crucial to
recognize the diverse linguistic backgrounds within the class. Essentially, not all students may have a
foundation in a Romance language.

313

Leveraging AI and Pluralistic Approaches for Language Teaching

Table 2. Parallel contrastive analysis of English/French/Spanish translations

This diversity extends to international students, many of whom are speakers of English as an Addi-
tional Language (EAL) and may not have a prior knowledge in a Romance language. Acknowledging the
diversity of students enrolled in the British higher education is essential as the UK is the third country

314

Leveraging AI and Pluralistic Approaches for Language Teaching

in the world to receive the most international students in the university context, following behind the
United States and Australia (UNESCO, 2021).
Recognizing the widespread adoption of English as a global lingua franca among students worldwide,
irrespective of their primary language (L1) or the foreign language (FL) they are studying, it remains
within the teacher’s discretion to opt out of including French in our comparative analysis. This stands as a
choice best left to the teacher’s discretion, given their familiarity with the diverse linguistic backgrounds
of their students. Consequently, based on this nuanced understanding, the teacher maintains the author-
ity to decide which language(s) can be incorporated into the contrastive analysis task during its design.
This discretion becomes particularly pertinent in scenarios where a teacher has a small group of
Erasmus or international students in the class, possessing distinct linguistic backgrounds from the ma-
jority of the class. Such instances highlight the importance of tailoring teaching resources to suit the
specific needs arising from varying language profiles within the classroom. By accommodating these
differences, teachers can effectively cater to diverse student needs, ensuring an inclusive and adaptable
learning environment.
While this approach represents a modified interpretation of the concept of ‘inter-comprehension
between related languages,’ focusing solely on English and Spanish remains notably advantageous in
both educational and language acquisition contexts, despite the considerable differences between these
languages. In any classroom where a language is already in use as a primary means of instruction, there
naturally emerges a level of mutual understanding between languages.
The key benefit of prioritizing a comparative study of English and Spanish lies in its inclusivity, ca-
tering to a diverse range of students without singling out specific language backgrounds. This inclusive
approach cultivates an environment conducive to the comprehension of essential aspects of the target
language, accommodating both native English speakers and those for whom English is an additional
language (EAL).
This process unfolds through a reflective comparison between English and Spanish, fostering stu-
dents’ heightened awareness of linguistic disparities between the two languages. For instance, students
can discern that English lacks a direct counterpart to the Spanish imperfecto verb tense, prompting
them to delve into how English employs grammar rules to express similar concepts. This exploration
can significantly deepen their comprehension of language structures across diverse linguistic systems,
amplifying their capacity to understand and interpret languages. Moreover, this understanding builds
upon their existing knowledge, empowering them to enhance their multilingual abilities, a proficiency
that not only aids in their autonomous learning but also serves as a pivotal asset when acquiring future
additional languages.

Challenge 2: Teacher Proofreading

In addressing the challenge of ensuring accurate translations produced by AI tools like ChatGPT,
particularly with complex grammatical structures or idiomatic expressions, human oversight becomes
essential. Teachers can encourage students to critically evaluate translations, pinpoint possible errors,
or inconsistencies, and participate in discussions to understand why certain translations might deviate
from expected outcomes. This collaborative method fosters a deeper grasp of linguistic subtleties and
emphasizes the importance of human judgment alongside AI-generated outputs.
When integrating AI-driven language tools such as ChatGPT within educational contexts, it is impera-
tive to acknowledge that teachers may not possess proficiency in all languages encompassed by these

315

Leveraging AI and Pluralistic Approaches for Language Teaching

tools. Despite this limitation in comprehensive fluency, teachers frequently utilize these technologies to
aid language learning. While teachers may lack extensive knowledge of the specific languages processed
by AI tools, their role remains pivotal in guiding the learning process. They validate AI-generated content,
initiate discussions on linguistic intricacies, and create an environment conducive to critical analysis
among students regarding translation accuracy and linguistic frameworks.
Undetected errors in translations, despite thorough teacher review, offer valuable learning opportuni-
ties. Students actively engage with tasks and often discover these errors during reflection. Rather than
being viewed negatively, these mistakes encourage deeper contemplation, observation, and discussion.
Contrary to tasks solely focused on correcting grammar, identifying errors in AI-generated translations
prompts students to explore language intricacies. This process promotes critical thinking, analysis, and
a richer understanding of grammar principles. Moreover, these errors stimulate discussions exploring
language variations and contextual nuances, thereby enriching the learning experience beyond mere er-
ror correction. Ultimately, this approach fosters a more comprehensive grasp of linguistic complexities.
Within this framework, the primary responsibility of the teacher is twofold: to facilitate proficient
use of AI-based language tools by students and to cultivate an environment encouraging comprehensive
linguistic analysis. This approach goes beyond reliance solely on the teacher’s language proficiency and
grammar precision.

Challenge 3: Sociolinguistic Variations in Spanish

The vast array of language variations and dialects within Spanish poses a significant challenge. Spanish
encompasses numerous regional and cultural variations, from idiomatic expressions to dialectal dif-
ferences, which ChatGPT might not accurately capture, potentially causing confusion among students
striving for a comprehensive understanding of the language’s richness and diversity. These challenges
underline the need for promoting awareness on the different dialects and variants of Spanish and, re-
gardless of which one is being used in the translation, use supplementary human proofreading to ensure
consistency using the same variant.
In our pursuit of a more inclusive approach to encompass diverse Spanish variants and contribute
to curriculum decolonization, we can expand beyond ChatGPT’s conventional use for translations and
leverage ChatGPT’s potential to ‘translate’ or adapt one Spanish variant into different ones (Table 3).
This application of ChatGPT also serves as a powerful educational tool to highlight sociolinguistic
phenomena and generate different Spanish variants of one same text. As shown in Stages 1-3 below, a
contrastive analysis of Peninsular and Latin American Spanish can show students that the Spanish pre-
térito indefinido (Past Simple in English) and pretérito perfecto compuesto (Present Perfect in English)
can be interchangeable in some cases.

Stage 1. It’s 5pm right now, but Julio is describing to me his morning routine earlier today. Julio is
Spanish, so he prioritizes the pretérito perfecto compuesto (i.e. Present Perfect). Use vocabulary
and grammar suitable for a B1 level (CEFR). Julio is the speaker, so write it in first-person singular
and ensure it comprises at least 100 words. Write it in the past.
Stage 2. Now rewrite it in Mexican Spanish, prioritizing the pretérito indefinido (i.e Past Simple).
Stage 3. Now translate it into English

316

Leveraging AI and Pluralistic Approaches for Language Teaching

Table 3. Parallel contrastive analysis of English/French/Spanish translations

317

Leveraging AI and Pluralistic Approaches for Language Teaching

The comparative approach in Table 3 highlights the similarities between English (i.e. Past Simple)
and Mexican Spanish (i.e. Pretérito Indefinido) in the choice of the past tenses, where in both cases
the aoristic value is prioritized. In this example, however, Peninsular Spanish employs the hodiernal
past (i.e. Perfecto Compuesto) as the event took place earlier on the same day and the speaker wants to
convey proximal relation to the moment of enunciation. In addition to a heightened inter-comprehensive
awareness, this comparative analysis also nurtures an awareness of regional grammatical distinctions and
the intricate linguistic diversity present within the Spanish language. By acknowledging and appreciat-
ing these diverse linguistic practices, students gain a more holistic view of the language’s adaptability
and evolution across different cultural settings, providing them with a more profound and multifaceted
understanding of Spanish at a linguistic level.
These educational endeavors not only elevate students’ linguistic competencies but also instill values
of cultural empathy and awareness. They prompt students to acknowledge, honor, and value the multifac-
eted ways in which Spanish is utilized across various communities and regions, facilitating a profound
comprehension of sociolinguistic dynamics inherent within the language.

CONCLUSION

As highlighted in this chapter, the integration of translation within a pedagogical framework, coupled
with reflective practices such as self-reflection and classroom discussions, serves as a powerful avenue
for enhancing students’ meta- and inter-linguistic awareness. This heightened awareness plays a pivotal
role in cultivating more autonomous learners, equipped to transfer these skills to grasp additional lan-
guages in the future. This emphasis on awareness proves particularly crucial for British learners, whose
educational emphasis typically leans toward literature rather than comprehensive grammar exploration
within the English Language and Literature curriculum.
In the realm of plurilingualism, utilizing ChatGPT for pedagogical translation stands out as a cru-
cial strategy to cater to the diverse linguistic backgrounds prevalent in classrooms, particularly among
overseas and Erasmus students, many of whom are proficient in English as an Additional Language.
The efficiency of ChatGPT in saving time, alongside its effectiveness in customizing our resources and
adapting contrastive analysis tasks to cater to various language combinations within the classroom,
highlights its significance in cultivating a more inclusive learning environment.
Nonetheless, the role of ChatGPT transcends mere translation facilitation; its integration stands as a
pivotal cornerstone in strengthening pluralistic approaches within conventional teaching methodologies.
With heightened tourism, migration, and exposure to diverse languages via digital media, incorporating
supplementary languages into the classroom alongside the primary target language cultivates a more
enriched and holistic learning environment. This approach not only heightens linguistic awareness but
also facilitates the acquisition of further languages in the future.
In essence, the utilization of pedagogical translation, augmented by ChatGPT’s capabilities in transla-
tion, not only addresses the pressing need to enhance linguistic awareness but also champions inclusivity
and pluralism within educational settings. Embracing this multifaceted approach acknowledges and lever-
ages the richness of linguistic diversity, ultimately enhancing the learning experience and proficiency
of students in a rapidly globalizing world.

318

Leveraging AI and Pluralistic Approaches for Language Teaching

REFERENCES

Andersen, R. (1991). Developmental sequences: The emergence of aspect marking in second language
acquisition. In T. Huebner & C. A. Ferguson (Eds.), Crosscurrents in second language acquisition and
linguistic theories (pp. 305–324). John Benjamins Publishing Company. doi:10.1075/lald.2.17and
Andersen, R., & Shirai, Y. (1994). Discourse motivations for some cognitive acquisition principles.
Studies in Second Language Acquisition, 16(2), 133–156. doi:10.1017/S0272263100012845
Bardovi-Harlig, K. (1998). Examining the role of text type in L2 tense-aspect research: Broadening our
horizons. En P. Robinson y N. Jungheim (Eds.), Representation and process: Proceedings of the 3rd
Pacific Second Language Research Forum (pp. 139–150). Tokyo: Pacific SLRF.
Bardovi-Harlig, K. (2000). Tense and aspect in second language acquisition: Form, meaning, and use.
Blackwell., doi:10.1111/0023-8333.50.s1.7
Bello, A. (1847). Gramática de la lengua castellana destinada al uso de los americanos. Edición digital
a partir de obras completas. Tomo Cuarto, 3ªed., Caracas, La Casa de Bello.
Braunmüller, K. (2007). Receptive multilingualism in northern Europe in the Middle Ages. In J. D.
ten Thije & L. Zeevaert (Eds.), Receptive multilingualism. Linguistic analyses, language policies and
didactic concepts (pp. 25–47). John Benjamins.
Candelier, M. (2013). Janua linguarum – The gateway to languages – The introduction of language
awareness into the curriculum: Awakening to languages. Council of Europe.
Candelier, M., Daryai-Hansen, P., & Schröder-Sura, A. (2013). The framework of reference for plu-
ralistic approaches to languages and cultures–a complement to the CEFR to develop plurilingual and
intercultural competences. Innovation in Language Learning and Teaching, 6(3), 243–257. doi:10.108
0/17501229.2012.725252
Cholij, M. (1994). Practice in Spanish Grammar. Mary Glasgow Publications.
Collen, I. (2020). Language Trends 2020. Language Teaching in primary and secondary schools in
England. British Council.
Collen, I. (2021). Language Trends 2021. Language Teaching in primary and secondary schools in
England. British Council.
Collen, I. (2022). Language Trends 2022. Language Teaching in primary and secondary schools in
England. British Council.
Collen, I. (2023). Language Trends Northern Ireland 2023: Language teaching in Primary and Post-
Primary Schools. British Council.
Council of Europe. (2001). Common European Framework of Reference for Languages: Learning,
Teaching, Assessment. Cambridge University Press.
Council of Europe. (2021). Common European Framework of Reference for Languages: Learning,
Teaching, Assessment—Companion Volume. Council of Europe Publishing.

319

Leveraging AI and Pluralistic Approaches for Language Teaching

Critchley, M., Chaurin, T., & De Madeiros, A. (2022). Survey of Language Provision in UK Universities
in 2022. Report no. 4, diciembre. University Council of Modern Languages (UCML), Association for
University Language Communities in the UK and Ireland (AULC), United Kingdom.
Critchley, M., Illingworth, J., & Wright, V. (2021). Survey of Language Provision in UK Universities in
2021. Report no. 3, julio. University Council of Modern Languages (UCML), Association for University
Language Communities in the UK and Ireland (AULC), United Kingdom.
Declerck, R. (2006). The grammar of the English verb phrase.: Vol. 1. The grammar of the English tense
system. A comprehensive analysis. De Gruyter. doi:10.1515/9783110199888
Department for Education. (2014). The national curriculum in England. Key stages 3 and 4 framework
document [DFE-00183-2013]. Retrieved from: https://assets.publishing.service.gov.uk/government/up-
loads/system/uploads/attachment_data/file/840002/Secondary_national_curriculum_corrected_PDF.pdf
EUROSTAT. (2016). Number of foreign languages known (self-reported) by sex [edat_aes_l21] Retrieved
from: https://appsso.eurostat.ec.europa.eu/nui/submitViewTableAction.do
EUROSTAT. (2022). Pupils by education level and number of modern foreign languages studied - abso-
lute numbers and % of pupils by number of languages studied [EDUC_UOE_LANG02] Retrieved from:
https://ec.europa.eu/eurostat/databrowser/view/educ_uoe_lang02/default/table?lang=en
Giorgi, A., & Pianesi, F. (1997). Tense and aspect: from semantics to morphosyntax. Oxford University
Press. doi:10.1093/oso/9780195091922.001.0001
Hasbún, L. (1995). The role of lexical aspect in the acquisition of the tense/aspct system in L2 Spanish
[Doctoral dissertation]. Indiana University, Bloomington.
Instituto Cervantes. (2023). El español en el mundo 2023. Anuario del Instituto Cervantes.
Kattan-Ibarra, J., & Pountain, C. (2004). Modern Spanish Grammar: A Practical Guide. Taylor and
Francis. doi:10.4324/9780203428313
Kelly, M. (Ed.). (2018). Languages after Brexit: How the UK speaks to the world. Springer International
Publishing.
Lusin, N., Peterson, T., Sulewski, C., & Zafer, R. (2023). Enrollments in languages other than English
in US institutions of higher education: Fall 2021. Modern Language Association of America. Retrieved
from: https://www.mla.org/content/download/191324/file/Enrollments-in-Languages-Other-Than-
English-in-US-Institutions-of-Higher-Education-Fall-2021.pdf
Montrul, S., and Slabakova, R. (2003). Competence similarities between Native and Near-Native speakers:
An investigation of the Preterit/Imperfect contrast in Spanish. Studies in Second Language Acquisition,
25, 351–398. doi:10.1017/S0272263103000159
Polisca, E., Wright, V., Álvarez, I., & Montoro, C. (2019). Language Provision in UK Modern Foreign
Languages Departments 2019 Survey. University Council of Modern Languages.

320

Leveraging AI and Pluralistic Approaches for Language Teaching

Quan-Haase, A., & Wellman, B. (2005). How computer-mediated hyperconnectivity and local virtuality
foster social networks of information and coordination in a community of practice. International Sunbelt
Social Network Conference. 10.1111/1468-2427.00309
Ramsay, V. (1990). Developmental stages in the acquisition of the perfective and the imperfective aspects
by classroom L2 learners of Spanish [Tesis doctoral]. University of Oregon, Eugene.
Rojo, G. (1990). Relaciones entre temporalidad y aspecto en el verbo español. Tiempo y aspecto en
español. Cátedra.
Salaberry, M. R. (1997). The development of past tense verbal morphology in L2 Spanish classroom
instruction. Cornell University.
Schmidt, R. (1994). Implicit learning and the cognitive unconscious: Of artificial grammars and SLA.
Second Language Research, 10(2), 93–119.
Schmidt, R. (2010). Attention, awareness, and individual differences in language learning. In Handbook
of language teaching (pp. 27-63). Academic Press.
Scottish Government. (2016). Children, Education and Skills. Attitudes Towards Language Learning in
Schools in Scotland. Social Research. Cabinet Secretary for Education and Skills. Learning Directorate,
Education.
Scottish Government. (2020). 1+2 Languages Implementation Findings from the 2019 local authority
survey. Cabinet Secretary for Education and Skills. Learning Directorate, Education.
Scottish Government. (2022). 1+2 languages policy - local authority survey 2021: findings. Cabinet
Secretary for Education and Skills. Learning Directorate, Education.
Scottish Qualifications Authority. (2014). National 3 English Course Specification [C72473]. Retrieved
from: https://www.sqa.org.uk/files/nq/CfE_CourseSpec_N3_Languages_English.pdf
Tinsley, T. (2019). Language Trends 2019: Language Teaching in Primary and Secondary Schools in
England. Survey report. British Council.
Tinsley, T., & Board, K. (2013). Languages for the future: What languages the UK needs most and why.
British Council and Alcantara Communications.
UNESCO. (2003). Education in a multilingual world. UNESCO Education Position Paper. Paris:
UNESCO. Retrieved from: https://unesdoc.unesco.org/ark:/48223/pf0000129728
UNESCO. (2021). Education: Outbound internationally mobile students by host region. Institute of
Statistics.
Westergaard, M., Mitrofanova, N., Mykhaylyk, R., & Rodina, Y. (2017). Crosslinguistic influence in the
acquisition of a third language: The Linguistic Proximity Model. The International Journal of Bilingual-
ism, 21(6), 666–682. doi:10.1177/1367006916648859

321

Leveraging AI and Pluralistic Approaches for Language Teaching

KEY TERMS AND DEFINITIONS

Aspect: Grammatical phenomenon found in many languages, including Romance languages like
Spanish, French, Italian, and Portuguese. It refers to the temporal nature of an action, describing how
an action unfolds over time rather than focusing solely on its completion. Aspect deals with the internal
structure of the action, such as whether it is ongoing, completed, repeated, or continuous, rather than
when the action occurred. In Romance languages, aspect is often marked by verb conjugation or auxil-
iary verbs and can indicate whether an action is ongoing, completed, habitual, or repeated. For instance,
in Spanish, the distinction between the preterite (simple past) and imperfect tenses illustrates aspect.
The preterite often represents completed actions in the past, while the imperfect indicates ongoing or
habitual actions in the past. Aspectual distinctions can significantly impact the meaning and interpreta-
tion of sentences by providing information about the nature and duration of an action, adding depth to
the temporal context of language.
Inter-Comprehension: This is the ability of speakers of closely related languages, such as Romance
languages, to understand one another even if they do not speak the same language. This is facilitated by
the linguistic similarities among these languages.
Pedagogic Translation: Deliberate use of translation as an educational tool to enhance language
learning, cultural understanding, and linguistic proficiency. The approach combines the act of translating
texts with structured reflection. This reflection prompts students to analyze their translation choices,
linguistic challenges, cultural nuances, and strategies employed during the task. By integrating reflection,
learners gain metalinguistic awareness, develop deeper language understanding, and improve translation
skills while fostering critical thinking and self-awareness.
Pluralistic Approaches: These approaches in language teaching advocate for recognizing and em-
bracing linguistic diversity, which is especially relevant when teaching or learning multiple languages
or dialects.
Positive or Facilitating Transfer: Positive transfer occurs when similarities between one’s native
language and the target language make language acquisition easier. This often happens when linguistic
features are shared between the two languages. For example, in the context of Romance languages,
which are typologically-related, learners might find commonalities in vocabulary, grammar, and even
sentence structure due to their shared Latin origins. This shared linguistic heritage can significantly ease
the transition for learners, making it more intuitive to pick up the new language. Positive transfer serves
as a bridge that helps learners harness their existing knowledge and skills to make sense of the target
language, accelerating the learning process.
Romance Languages: These are a group of languages that have evolved from Latin and are pre-
dominantly spoken in Southern Europe. Among the prominent Romance languages are Spanish, French,
Italian, and Portuguese. While all of these languages share a common Latin origin, they have also
evolved distinctively in terms of vocabulary, grammar, and pronunciation due to a range of historical
and geographical factors. For instance, Spanish and Italian have relatively high mutual intelligibility
due to similarities in vocabulary and grammatical structure, while French exhibits more pronounced
differences, especially in pronunciation and vocabulary, which can pose challenges for learners. These
variations reflect the influence of historical events, such as the Roman Empire’s expansion and later
invasions, on the development of these languages, resulting in a rich linguistic landscape within the
Romance language family.

322

Leveraging AI and Pluralistic Approaches for Language Teaching

Transfer: This concept refers to the influence of one’s native language on the acquisition of a new
language. It can either aid or impede the learning process, depending on how similarities and differences
are managed.

ENDNOTE
1
This percentage includes primary schools that provide an L2 entitlement both fully (L2 is taught
continuously from P1 to P7) and particularly (not taught continuously from P1 to P7).

323
324

Chapter 15
Designing Language
Learning Experiences With
Generative AI Tools
Betül C. Czerkawski
https://orcid.org/0000-0002-4189-4042
College of Applied Science and Technology, University of Arizona, USA

ABSTRACT
Artificial intelligence (AI), particularly generative AI, can present many opportunities for language
learners to practice and improve their language skills, receive timely feedback on their performance,
and customize their learning based on their needs and language proficiency. AI’s benefits are not limited
to second language (L2) learners. Instructors can also benefit from the novel generative AI technologies
by using them in curriculum and lesson design, developing new teaching and assessment materials, or
addressing diverse learner skills and needs. Despite AI’s advantages, the main issue is how to design L2
environments effectively so learners can receive the best benefits from AI while reducing some associ-
ated drawbacks. This chapter argues that learning experience design (LXD) presents a road map for L2
instructors as they incorporate generative AI into their instruction. If the learning design is random and
left to good intentions, achieving meaningful learning outcomes will also be left to chance. Following
proven LXD guidelines may help alleviate the confusion around AI.

Artificial intelligence (AI) can be defined as a computer or a robot performing specific tasks that hu-
mans usually perform, such as finding solutions to problems, synthesizing information, analyzing data,
or identifying patterns. The idea of AI that can analyze information is not new. Traditionally, AI uses
discriminative modeling, making AI efficient and cost-effective. As a specific form of AI, generative
AI, on the other hand, goes further than traditional AI. Relying on transformer-based machine-learning
algorithms, generative AI can produce new and high-quality content using multiple modalities, such as
text, images, audio, and videos. Compared to the traditional option, generative AI is less cost-effective
but more efficient in producing new content that is coherent and conceptually appropriate (Hsu & Ching,
2023). The much-talked-about ChatGPT from Open AI, Bard from Google, Claude from Anthropic, and
Bing from Microsoft are examples of generative AI.

DOI: 10.4018/979-8-3693-0872-1.ch015

Copyright © 2024, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

Designing Language Learning Experiences With Generative AI Tools

Many fields, from medicine to security systems to businesses, have used AI in recent years. In the
beginning, what started with simple text suggestions, grammar checks, and email prompts turned into
a completely new direction with the automation of writing whole essays and even books. In education,
the adoption of AI tools has been relatively slow. According to a national survey in the U.S. (Sebesta
& David, 2023), 60% of higher education personnel reported scattered conversations around AI, while
75% stated a lack of incentives for using AI technologies. However, this situation is quickly changing
as higher education institutions try to adapt to rapid developments.
In second language (L2) studies, AI has increasingly been used. For instance, voice-based AI tools
such as Amazon Alexa and Apple Siri can increase communication skills (Underwood, 2017), while
chatbots can provide unlimited and real-time practice options (Jeon, 2022), coach students as they study
a language and improve their language skills (Wang et al., 2022), help with conducting critical research
and evaluation (Hsu & Ching, 2023), and assist in translating, editing, paraphrasing, revising, researching
and generating text (Warschauer et al., 2023). Researchers also reported some limitations with AI that
learners and instructors need to be aware of. For example, the current AI tools may not offer “a broad
enough view of language and culture, limiting students’ exposure to diverse perspectives” or work well
with students with accents (Wang et al., 2023, p. 2). In addition, generative AI tools can produce non-
existent sources in writing prompts or hallucinate while presenting template rigidity (Barrot, 2023). As
with any new emerging technology, the novelty effect of AI technologies may also subside over time
(Fryer et al., 2017). Finally, Zhao (2023) argues that most-AI based digital writing tools for L2 focus on
revisions and editing, while tools for completing higher-order tasks such as formulating ideas are still
lacking. An effective and careful learning design may guide to mitigate the adverse impact of genera-
tive AI for L2.
This chapter aims to present a learning experience design (LXD) approach for the effective inte-
gration of generative AI so this new technology can lead to meaningful learning experiences in L2
instruction. According to a recent report, all uses of AI in education “must be grounded in established,
modern learning principles” (U.S. Department of Education, 2023, p. 60), prioritizing learning design.
Other scholars also argued that “it takes careful planning and learning to optimally leverage GenAI’s
capabilities” (Hsu & Ching, 2023, p. 606). The chapter, therefore, will start with presenting LXD models
and practices applicable to L2 and discussing the contemporary design frameworks commonly used for
emerging technologies. From there, design implications specific to generative AI in the context of L2
will be presented after synthesizing contemporary learning experience design (LXD) models.

LEARNING EXPERIENCE DESIGN (LXD) FOR L2

In a report published in 2007 by the Modern Languages Association, the authors call for new structures
in teaching languages. While they never mention instructional design (ID) or LXD in this report, they
call for a curriculum reform that includes “explicit, principled educational goals and expected outcomes”
(MLA, 2007, para.14). The report focuses on the new type of content that needs to be included in the
curriculum with little attention to the methodology of doing it. Unfortunately, most language teacher
training curricula rarely include teaching subjects such as instructional design or learning experience
design. Hence, a comprehensive and holistic approach to learning design can provide much-needed
intentionality to deliver successful language instruction.

325

Designing Language Learning Experiences With Generative AI Tools

Instructional Design (ID) is a systematic approach to deliver effective and efficient instruction. With
the advance of digital technologies via computers and mobile devices, concepts like user interface in-
teraction or online learning are now at the forefront of education. Today, most instructors and designers
adopt a more targeted approach to curriculum design rather than designing prescriptive and limiting
curricular systems with carefully planned teaching and learning activities. This new targeted approach is
labeled as Learning Experience Design or LXD, although it should be emphasized that not all scholars
have reached a consensus on this new term. Clark (2021) even calls the LXD a field with an identity
crisis. However, he also emphasizes the importance of learning from past ID experiences and moving
into a new vantage point with LXD, where educators can resolve today’s complex learning problems by
creating context-specific learning opportunities.
LXD refers to designing learning activities, experiences, or materials using user experience design
principles to achieve expected learning outcomes. Clark (2021) points out the primary goal of LXD: learn-
ing that puts the learner at the center of every educational endeavor. Learning outcomes are achieved by
selecting the right experiences for learners and the design processes needed to create those experiences.
In other words, LXD presents a multiple-step approach to achieving its goals: first, clear and realistic
learning objectives aligned with the learner’s needs and proficiency level are identified; then, teaching
and learning activities that use human-computer interaction principles and the most recent findings of
learning science are created; content and learning activities are sequenced so students would gradually
connect the new knowledge with the prior knowledge; collaborative and social learning is supported,
and finally, authentic and meaningful assessment procedures are arranged. In the context of L2, it is
also essential to include culturally sensitive experiences for the learners to increase their intercultural
competence. Moreover, considering the complexity of digital technologies and AI-supported platforms,
LXD also provides an understanding of how students make choices and self-regulate their experiences.

DESIGN MODELS FOR EMERGING TECHNOLOGIES

Traditional ID practices utilize well-established models to guide the design process. Because the learn-
ing environment could be open-ended and fluid, ID models provide a framework for designers to con-
ceptualize, plan, and execute instructional activities. Traditional models, such as the Analysis, Design,
Development, Implementation, and Evaluation or ADDIE (Branson et al., 1975) and Dick and Carey
Model (1978) use behavioristic learning theory, while Gagne’s Nine Events of Instruction (1965) and
Merrill’s Principles of Instruction (Merrill, 2002) use cognitivist learning theory. These older models
also predominantly follow a linear design process. Compared to the behaviorist ID models, cognitivist
models offer more flexibility; nevertheless, they are still structured models with little attention to tech-
nological developments and their impact on education.
Recently, a group of new design approaches flourished, inspired mainly by the computing fields.
Unlike ID, LXD highly favors the latter computing-based approaches because of their connection to
new technologies and emerging ideas in the learning sciences. One of the main differences between the
traditional and contemporary models can be found in the linearity of the models and the learning theories
on which they are based. For instance, a traditional model like Dick and Carey Model follows certain
steps linearly, paying little attention to the contextual changes in the learning environments or differences
in learner backgrounds. On the other hand, an iterative ID model like the Successive Approximation
Model or SAM (Allen Interactions, 2021) considers the differences in each learning setting and makes

326

Designing Language Learning Experiences With Generative AI Tools

adjustments for different learner needs via iterative learning design processes. The other difference be-
tween a traditional and contemporary ID model is the scope of the design activities. While ID is more
appropriate for top-down comprehensive program-level designs, LXD focuses on course or unit-level
designs that focus on learner experiences. Regarding learning theories, contemporary LXD models
frequently use constructivist and connectivist learning theories, building on learners’ prior knowledge,
personal interpretations, and individual discoveries.
Moreover, LXD has been heavily influenced by the developments in the computing fields, such as
human-computer interaction and software development. For instance, agile design provides a highly flex-
ible activity or task-focused design technique; rapid prototyping helps designers in creating low-fidelity
learning and teaching materials to move to high-fidelity materials; and interface and interaction design
techniques consider the user experiences with the computing systems to generate meaningful learning
experiences. Finally, modern LXD models are highly customizable based on the learner’s needs and
circumstances; therefore, LXD presents a flexible approach to the learning process that is much needed
for an emerging technology such as AI.

INCORPORATING GENERATIVE AI IN L2

While applying LXD to the design of L2 environments, an instructor makes decisions in three main
areas: How do the L2 learning objectives change due to using generative AI technologies? How can the
affordances of the AI tools be used to create L2 learning and teaching activities? Finally, How does the
use of generative AI impact assessment procedures? Addressing these questions would help instructors
integrate generative AI in their L2 classrooms.

Learning Objectives and Generative AI

Learning objectives concern what learners should be able to achieve as a result of formal learning expe-
riences. In addition, learning objectives do not only refer to cognitive level objectives (e.g., knowledge
and intellectual skills) but also to affective (e.g., attitudes, emotions, interests, values, etc.) and psycho-
motor skills (e.g., physical coordination, motor skills). In schools, these objectives are also used to set
up criteria for assessment and evaluation.
Generative AI may impact how students learn languages and what they learn. Judging by the rapid
developments in AI technologies, learning objectives also need to change to reflect the circumstances of
modern education settings. In other words, instruction time could focus on L2 learning objectives that
are on the higher end of Bloom’s Revised Taxonomy (Krathwohl, 2002), such as analyzing, evaluat-
ing, and creating, while AI could be employed to save time on lower-level learning objectives, such as
remembering, understanding, and applying. For instance, rather than spending valuable instructional
time with lower-level cognitive tasks that require memorization of language concepts, instructors can
use AI applications with students to practice those tasks in a safe and non-judgmental AI environment.
Similarly, drill-and-practice exercises, such as the practice of simple grammar structures or pronunciation
of vocabulary, can be practiced using an AI program. This way, students can spend more class time on
higher-level cognitive tasks, such as critically evaluating one’s speaking performance, making cross-
cultural references, and studying linguistic pluralities that can help understand the target language’s culture.

327

Designing Language Learning Experiences With Generative AI Tools

While determining what L2 learners need to learn, instructors should consider learner perceptions
of AI tools to tailor them to their needs. According to Chan and Hu (2023), user acceptance plays a
significant role in the effective use of AI. As the learners trust their abilities in the learning environment,
their positive perceptions lead to deeper learning experiences, while negative perceptions may lead to
superficial learning. Therefore, including learners in setting learning objectives and outcomes could
also be worth considering.

L2 Activities and Generative AI

Learning experience design has important implications when creating teaching and learning activities
with AI. First, a well-grounded learning design framework assists educators in being aware of both the
affordances and limitations of chatbots and generative AI so the learners get the best benefit. Regardless
of the framework chosen, using LXD, L2 educators can start with the desired learning outcomes and find
learning activities that AI can support. Second, AI can be a complementary tool to enhance instruction
with close instructor guidance, monitoring, and modeling rather than replacing classroom instruction
led by a teacher. Finally, in selecting and evaluating which AI tool to use, the educators weigh in on their
usability and feasibility (U.S. Department of Education, 2023).
Regarding learning activities, generative AI can create engaging and interactive learning experi-
ences, offering practice in language skills, grammar, and vocabulary. Chatbots, for instance, are the
most commonly used AI tools as they can converse with the learners in the target language. What makes
chatbots effective is their ability to respond to queries, continuously learn and improve the quality of
their output, and act as tireless language-teaching assistants (Kohnke et al., 2023). In the new iteration
of chatbots, in addition to voice recognition, integration with third-party applications is also possible,
expanding chatbots’ ubiquitous use. In addition to maintaining conversations, chatbots can respond to
learner questions and assess their language skills in a written or spoken manner. Language instructors
can also develop their chatbots using a visual chatbot development system. According to a systematic
review of empirical studies, Huang, Hew, and Fryer (2021) found that chatbots have many pedagogical
affordances, from being an interlocutor (e.g., language and skill practice, group discussions) to simula-
tive practices (role-playing, learning scenarios in authentic learning environments), general assistance
(helpline), and providing recommendations (providing need-based content).
The recent L2 literature has shown that chatbots can be effective technologies for language learning.
They can decrease language anxiety (Hapsari & Wu, 2022), enable students to interact multimodally,
develop vocabulary, provide feedback (Haristani, 2019), and improve their reading skills (Bailey et al.,
2021). Chatbots can also engage learners in human-like conversations (Fryer et al., 2020) and increase
their motivation (Jeon, 2022). Despite this generally positive outlook, there is also research that cautions
about the limitations of chatbots. For instance, the researchers found that speaking with chatbots creates
an environment lacking emotions. Additionally, chatbots may feed learners with inaccurate information
(Annamalai et al., 2023; Kohnke et al., 2023). Similarly, AI technology can create an unnatural envi-
ronment for students, making it difficult for authentic interactions. According to Wang et al. (2023),
AI-based applications may be constraining in offering a broad range of cultural experiences and diverse
opinions in the target language. Other scholars found that learners speak with shorter sentences while
conversing with chatbots and use restricted vocabulary and even profanity (Hill et al., 2015). Finally,
not every L2 student may take advantage of the generative AI, as different students may need different
types of assistance when using chatbots (Wang et al., 2023).

328

Designing Language Learning Experiences With Generative AI Tools

Besides chatbots, language educators can use generative AI to foster traditional language tasks, such as
mastering grammar rules, teaching new vocabulary (Jia et al., 2022), practicing pronunciation or listening
exercises, and assisting students with reading, writing, and translation tasks. Generative AI can present
more creative ways of teaching languages, including mime, poetry, lyrics, puzzles, and game creation
in the target language, script-writing, or cultural immersion activities. Furthermore, AI can provide
additional cultural context by explaining cultural nuances and offering practices that reflect regional
differences in the target language. Finally, generative AI has great potential to individualize instruction
for different student needs. Language instructors can curate language resources for a specific learning
need and create tailored learning materials for their students (Pratama, Sampelelo, and Lura, 2023).

L2 Assessment and Generative AI

Some early research shows promising results concerning using generative AI in achieving learning
outcomes in L2 classrooms. In a study by Wei (2023), generative AI improved student achievement
and motivation and fostered self-regulated learning strategies among EFL learners. Despite such stud-
ies, generative AI has been central to many heated discussions, creating confusion about what students
gain if they employ AI in their learning. For instance, the initial reactions from writing and translation
instructors were highly cautious towards using AI in learning assessment. Lately, most L2 instructors
are reflecting deeply on how learner assessments can be re-imagined (Amin, 2023; Richardson & Cle-
sham, 2021). From the LXD perspective, it is essential to note that assessments should align with the
learning outcomes. This criterion should be supported when a new technology like AI is brought into
the classroom. Additionally, traditional assessments, such as take-home translation exercises and essays,
should be re-considered for their relevancy in the age of generative AI. Authentic assessments, such as
video-based portfolios, chats, or discussions, could be used whenever possible.
Generative AI can help language learning in three ways regarding the creation of assessments. First,
using generative AI, language instructors easily create customized assessment materials, such as quizzes,
worksheets, exams, and study materials. Some of these assessments could be used for student practice
so that they can master language skills independently. Second, instructors can provide immediate and
comprehensive feedback to their students using automated AI systems. While practicing themselves,
learners also receive immediate feedback from the AI platform. Most language programs, such as
Duolingo and Rosetta Stone, already use AI technology to customize language practices to the level of
students. Finally, generative AI can be used as an adaptive learning tool where the difficulty level of
questions can be adjusted based on student responses. The same adaptive systems also give information
about students’ learning difficulties by analyzing where their errors are. For instance, adaptive AI tools
such as Cerego and 360Learning can provide feedback to students using different formats so they can
correct their errors.
Table 1 summarizes the questions the instructors can ask themselves about learning design processes
for generative AI.

329

Designing Language Learning Experiences With Generative AI Tools

Table 1. LXD questions for Generative AI

Learning Design
Questions that Guide Learning Design
Elements
What do students need to learn? What objectives could be gained or practiced with generative AI?
Which cognitive, affective, and psychomotor level learning objectives generative AI support?
Learning Objectives
How can generative AI be tailored for different learner needs, language proficiency, and experience levels with
and Outcomes
technology?
What digital competence skills do learners need to develop to use generative AI responsibly?
What generative AI activities can support specific language skills (grammar, vocabulary, pronunciation, practice
for mastery, speaking, writing, reading, listening, and intercultural skills)?
Learning Activities
How can generative AI support student motivation, participation, and engagement?
What specific generative AI tools could be used?
How can students use generative AI to get immediate feedback on their learning?
Assessments How can learning proficiency be assessed using a generative AI tool?
What self-regulation and metacognitive skills do learners develop when using generative AI?

GENERATIVE AI TOOLS FOR L2

With the growing number of generative AI tools emerging every day, it is impossible to capture all the
tools that can be used in L2 here, but a few of them will be discussed to give an idea about the poten-
tial of AI. These tools can be categorized around L2 material development, formative assessment, and
improvement of speaking skills.

Supermeme AI (https://www.supermeme.ai) and

LingoTeach (https://lingoteach.ai)

AI can help instructors create L2 materials for instructional use. One such tool is called Supermeme AI.
Memes are fun ways of looking at an idea using an unrelated image, animation, or video. The contradic-
tion and interplay between the concept and the visual make memes entertaining for students. Supermeme
AI can generate memes by typing simple prompts into the program. The program then generates a meme
using an extensive multimedia database under fair-use policies. Memes can teach vocabulary, grammar
concepts, trends, and culture (Huang, 2023), and Supermeme AI is available in over 110 languages.
Using this app, L2 instructors can create memes for their classes or let their students find captions for a
given meme. Huang also suggests various activities that use memes, such as writing a story for a meme,
interpreting a meme, and voting for a favorite meme. The instructor can edit the meme caption to tailor
the AI-generated materials for age-appropriateness. There are other meme-generating websites, but using
the power of AI, this tool can generate random images that align with the spirit of memes better. While
Supermeme is not a free tool, some free credits are available for new users.
The other AI tool that can be used for creating instructional materials is LingoTeach. LingoTeach
allows instructors to start with selecting language structures they want their students to practice and a
topic or scenario they want them to use with the chosen language structure. Then, the program gener-
ates text for reading or listening comprehension. For listening, instructors can record their own voice or
utilize the system-generated recording. LingoTeach is available in five languages and is a fee-based tool.

330

Designing Language Learning Experiences With Generative AI Tools

Figure 1. Supermeme, an example of a creating Figure 2. Supermeme, an example of a creating

writing prompt writing prompt

Figure 3. LingoTeach, an example of a translation exercise from French to English

Formative (https://www.formative.com/ai-powered)
and Quizlet Q-Chat (https://quizlet.com/)

The second set of AI tools that can be used with L2 relates to assessment. Using Formative, instructors
can upload their text-based documents into the software, and then the AI tools generate auto-graded
quizzes, assessment tools, or presentation slides, which students can study at their own pace. The presen-
tation slides also include built-in questions to enforce student understanding as they view the content. As
an assessment tool, Formative allows instructors to select various questions, embed their time-stamped
videos into presentations to generate questions, check answers to detect plagiarism, and monitor student
progress over multiple assignments. Formative is a fee-based tool, but a free version with limited func-
tions is available. The tool can be integrated with learning management systems or Google Classroom.
While it is not specific to languages, the support for a wide range of languages allows Formative to be
an ideal tool for L2.

331

Designing Language Learning Experiences With Generative AI Tools

Figure 4. Formative AI, question bank for Spanish

Quizlet is a well-known assessment tool for all content areas, but Quizlet Q-Chat is an AI-powered
addition that helps learners assess their learning on a given topic by conversing with the Quizlet bot.
Q-Chat guides and coaches students, similar to Formative AI. Instructors who want to use their own
assessment options can use a fee-based option, Quizlet Plus, but the program is free for students. Cur-
rently, Q-Chat is available in five languages.

Figure 5. Quizlet-Q-Chat, practicing Ukrainian

Replika (https://replika.com) and TalkPal (https://talkpal.ai)

The third type of tool for L2 is AI intelligent agents for speaking. Although Replika is currently only
available in English, the company plans to expand its language capacity soon. Replika can understand
conversations in all languages but can respond in English. The basic version is free, and the program
mainly involves conversing with a chatbot using an avatar, although learners can also type their conversa-
tions using the written mode. In ESL/EFL classrooms, Replika can encourage students to speak without
fear, judgment, or social anxiety about how they sound in the target language. Replika does not conduct
any translations or Internet searches, so its primary purpose is to chat on topics learners wish or mentor

332

Designing Language Learning Experiences With Generative AI Tools

or coach them to improve their conversational skills. Each Replika offers a private chat platform, mean-
ing only one user can speak to their Replika. In one study on higher education EFL students’ views on
Replika, the author found that students enjoyed using Replika and valued the immediate feedback they
received about their conversations (Kılıçkaya, 2020). The same group of students also commented that
when Replika had problems understanding their conversations, they edited or changed their prompts,
which helped them correct their mistakes immediately. The author concluded that Replika can be used
in the classroom but also outside of the school to develop confidence in speaking.

Figure 6. Replika, chat window with the personalized avatar

TalkPal is an AI tool very similar to Replika, but the main difference is that TalkPal was explicitly
created for language learners. Therefore, it is available in a large number of languages. TalkPal aims to
strengthen all four language skills with a wide range of options for continuous practice. While a fee-
based program, TalkPal also has a free service for 10 minutes of daily practice. TalkPal can use different
language registers, such as formal, informal, and fictional conversations so that students can practice
their language skills in different modes. Like Replika, TalkPal can be used outside of the classroom to
provide additional student practice options.
It should be noted that there are other AI-powered chatbots to practice languages. For instance, tra-
ditional language software programs like Rosetta Stone, Mondly, Babbel, Duolingo, and Memrise have
AI chat options for learners. However, these programs are limited in functionality compared to Replika
and TalkPal.

FURTHER IMPLICATIONS FOR LEARNING DESIGN

The following section presents some of the implications of LXD for generative AI. As the research into
generative AI grows, further guidelines can be added to this list.

333

Designing Language Learning Experiences With Generative AI Tools

Figure 7. TalkPal, homepage for language skill selection

Reflecting on what students need to learn. Instructors need to consider revising course/unit/activity
objectives to maximize class time for attaining significant learning outcomes and minimize the class time
for repetitive language practices. Course objectives can be selected from Bloom’s Revised Taxonomy
higher level cognitive goals to enable learners to analyze, evaluate critically, and apply what they have
learned while they increase their cultural awareness. The research conducted by Cao et al. (2023) showed
that students engaged more with the chatbots when asking questions at higher cognitive levels than those
at lower cognitive levels. Furthermore, “Most language learning curricula start the learning process with
the acquisition of vocabulary and lexical bundles through the means of memorization” (Wilson & Marcin,
2022, p. 2). For advanced learners, Generative AI could help reduce redundant instructional practices
by increasing the time spent on tasks such as examining and critically assessing cultural, political, and
social elements from the target language. Some example learning objectives would be studying regional
linguistic differences, the historical reasons for the differences, creating original works in the target
language, or analyzing the development of the language in the historical context. For beginner learners,
AI tools may offer much-needed practice options without any fear of judgment.
Expanding learning experiences with fun, engaging, and motivating activities. Considering that
early research with AI chatbots shows a novelty effect that wears off quickly (Fryer et al., 2017), AI tools
should be used occasionally and cleverly to expand classroom instruction rather than trying to replace
essential teaching tasks, such as content presentation, explanations, probing student understanding and
providing individualized feedback. Content creation for stimulating language tasks or finding connec-
tions between the native and target language requires intense work on the instructor’s part. Generative
AI can help develop engaging activities for the students with memes, debate ideas, and brainstorming
options while customizing these activities for different student levels and needs.
Customizing learning experiences with diverse tasks created by AI. Tailoring AI-based programs
for learner needs has different implications for learning. The first implication is the possibility of creating
experiences for different learner needs and proficiency levels. Development of teaching materials that fit
a specific learner’s needs may be time-consuming and labor-intensive. L2 instructors could use genera-
tive AI to save time on creating visually rich content materials, fun games, or age-appropriate, exciting
materials for their students. Second, as the mostly text and speech-based generative AI becomes more

334

Designing Language Learning Experiences With Generative AI Tools

multimodal, instructors can also transform traditional language textbooks and web-based materials into
a highly interactive environment. According to Pokrivcakova (2019), using AI to create personalized
materials works against the “one-size-fits-all” approach to schooling and helps better meet individual
learner needs. Finally, applications that “utilize AI can capture, aggregate, and analyze students’ learn-
ing performance data in real time from different sources to develop a student learning profile and auto-
matically provide customized content, feedback, and learning parameters” (Kim et al., 2022, p. 6070).
Moreover, learning management systems (LMS) are expected to integrate AI into their system in the near
future, providing more customizable learning experiences for students. Currently, the learner progress
and grades are tracked with AI, but LMSs do not offer adaptive learning experiences where each learner
customizes their experiences with the course content creating personalized pathways.
Expanding class time with cultural and authentic L2 learning experiences. Authentic learning
helps make learning relevant to the students while bridging the content learned in the classroom to
real-world situations. Research in teaching culture in L2 classrooms with the help of AI tools is scarce.
However, some research exists on the authenticity and effectiveness of AI-generated content. According
to Kim et al. (2022), using AI was beneficial to achieving learning outcomes when teachers implemented
AI-generated authentic tasks. However, teachers here engaged students in AI by not leaving them alone
with the activity but guiding them along the way. In their research, teachers took a proactive role when
using AI and assisted students regularly and carefully.
Targeting all language skills holistically. According to a study conducted by Woo and Choi (2021)
in L2, AI research is mainly focused on speaking and listening (14%), writing (11%), pronunciation
(11%), grammar (7%), vocabulary (6%) and reading (5%). Intercultural competence, or teaching of
culture in general, is the area that should be addressed the most. This study shows that the full potential
of generative AI tools is only partially realized, and language skills are treated individually by most L2
instructors. The authenticity of the AI-generated tools to teach the cultural content of the target language
is an area that needs to be investigated further, as not everyone agrees that AI can generate authentic
content for instruction; hence, AI-created content falls short regarding authentic learning experiences.
Using AI-based assessments for practice and evaluation purposes. Grading student work can
often be tedious and time-consuming. AI can provide faster and more detailed assessment feedback,
sometimes even more detailed than the instructor’s (Alharbi, 2023). The research on the consistency of
AI-based evaluations is mixed. For instance, Ranalli (2021) suggests that automated writing evaluation
tools such as Grammarly fall short of expectations because the feedback provided by the writing tools
does not guarantee writing improvement. The success of the AI feedback depends on the learner and
context. Therefore, student’s proficiency level, content, instructional context, and comfort level using
AI-based tools should be taken into account by the L2 instructors when using AI for learning assessment.
Creating a space for the discussion of ethical use. With all its advantages, the use of AI also poses
serious ethical challenges, not to mention critical limitations, including the issues surrounding data pri-
vacy, bias, lack of diversity, reliability, authenticity, and academic dishonesty. Maintaining the integrity
of educational practices in the increasingly AI-driven world is the topic of ardent discussions in every
society today that should be taken seriously. While the examination of such ethical issues is beyond the
scope of this paper, for L2 instructors, there are specific implications. L2 instructors have always been
keen on incorporating new literacies in their teaching. Nash et al. (2023) argue that controversy around
new literacies has always existed. Consequently, engaging with AI technologies should also be part of
the literacy education the L2 instructors have spearheaded for decades. Modeling responsible use of AI

335

Designing Language Learning Experiences With Generative AI Tools

by the L2 instructors, having classroom debates, or creating a safe environment for learners to discuss
their own experiences could be part of language education.
Developing digital competency and AI literacy. Although generative AI can be highly useful, in
order to limit the wide range of issues about its use, both learners and teachers “must develop the specific
digital competencies needed to use such tools in ways that are pedagogically beneficial and ethical”
(Kohnke et al., 2023, p. 546). In the last two decades, educational institutions have trained many students
in using emerging technologies. However, the rapid growth of generative AI tools showed that this time,
schools and universities fell short of training their faculty and students to gain digital competency skills,
causing much confusion regarding AI. Moreover, most instructors are left alone without a clear instruc-
tional strategy and adequate infrastructure, causing further misunderstanding and chaos. A recent study
showed that an “overwhelming majority of institutions do not offer incentives to encourage faculty to
use AI, and a majority also reported no faculty development or training around AI” (Sebesta & Davis,
2022, p. 6). Digital competency with AI can be developed by continuously fact-checking the reliability
of the information, being aware of the potential ethical issues and underlying biases, and understanding
AI’s technical underworking, social, pedagogical, and technological affordances.

RECOMMENDATIONS FOR FURTHER LXD RESEARCH

L2 instruction is complex and requires further empirical research due to the increased interest in generative
AI and L2. In the last decade, most of the research attention was on AI technology; however, nowadays,
more attention is paid to developing educational AI platforms that consider learning characteristics,
educational context, and instructor capabilities. Customizable or adaptive AI-supported language instruc-
tion requires deeper pedagogical research using diverse language content and context. In L2, context is
critical, as educators need to understand what system works for whom and why. Sound teacher training
programs for integrating AI tools into language classrooms also need to be studied to understand how
teachers can effectively employ AI. If some students cannot take advantage of AI technology because
of their lack of vocabulary or accent, educators need to be aware of these limitations. Research into
context-sensitive AI models must ensure that “they are effective, safe, and trustworthy for use with
varied learners in diverse settings” (U.S. Department of Education, 2023, p. 59). Along the same lines,
instructor guidance is vital when learning with AI, and more research is needed to establish effective
teaching strategies that can help learners.
The student-AI interface interaction should be studied to respond to diverse user needs. Considering
that there is a “dearth of knowledge regarding how students interact with AI agents for language learning
and what differences may exist among distinct types of students in human-AI interactions” (Wang et al.,
2023, p. 2), more research is needed to understand learner-AI interaction processes as well as the design
considerations for AI interfaces. For instance, most AI tools used in L2 are not explicitly designed for
L2 learners. L2 learner needs, their skill level with AI interfaces, and expectations may differ; therefore,
research that includes diverse learner perspectives is needed to employ AI effectively in L2 classrooms.
Another consequence of AI use in L2 is related to reliance on technology. Considering that most AI
tools are used in conjunction with online education, an added layer of complexity should be examined
further. Likewise, research investigating the interactions between the learners and technology affordances
is needed to craft a balanced use of AI applications. In addition, more longitudinal studies should be
undertaken to understand the long-term effects of AI on L2 learning.

336

Designing Language Learning Experiences With Generative AI Tools

Finally, there is a need for more research on issues related to the accuracy of AI applications, user
data, privacy, transparency of the platforms, and ethical issues surrounding AI. As with any emerging
technology, instructors need to think carefully about generative AI and its use before employing it in
their classrooms. While the ethical use of AI for L2 learners is beyond the scope of this paper, as a
learning tool, the reliability of the information gathered via AI and its responsible use is part of the new
literacies in which L2 instructors can lead the way for other disciplines. A research-informed AI literacy
instruction and digital competency skills could help solve some issues and generate a solid ground to
promote desired AI use for L2 learners.

CONCLUSION

The leading AI program, ChatGPT, launched on November 30, 2022, attracting millions of users
worldwide. Although chatbots and AI applications are not new, with the introduction of ChatGPT, the
education world witnessed a storm of new applications accompanied by a considerable interest similar
to none. It can be argued that generative AI can arguably be used in L2 education in endless ways. While
AI technology is still developing, educators lack data-driven teaching and learning strategies and proven
pedagogical approaches.
The many research studies conducted only in the last year prove the interest in AI, mainly discuss-
ing the affordances and drawbacks of using AI in language settings. Many L2 scholars expressed their
concerns about using AI for instruction (Dakakni and Safa, 2023). Considering how ubiquitous AI is,
this idea is unrealistic because most web-based programs for writing and searching information have
already integrated AI into their system. Then, the question is how to use AI for the best results in L2.
Currently, there is little research on this issue, but the research is evolving.
This paper argued that learning experience design, as a contemporary, practical, and realistic strategy
using instructional design guidelines, provides valuable insights for educators as it shows a pedagogically
sound method of using AI in L2 instruction. More specifically, reflecting on new learning outcomes in
the age of AI, creating AI-powered activities that will enhance student learning, and using an assessment
approach that provides accurate and immediate feedback would structure some of the early excitement
and discussions around AI and offer a sound foundation for L2. The suggestions provided in this paper
can be used as a starting point while stimulating much-needed pedagogical research on AI integration.

REFERENCES

Alharbi, W. (2023). AI in the foreign language classroom: A Pedagogical overview of automated writing
assistance tools. Education Research International, 2023, 1–15. doi:10.1155/2023/4253331
Allen Interactions. (2021). E-Learning development with SAM. Allen Interactions. https://www.allen-
interactions.com/services/custom-learning/sam/elearning-development
Annamalai, N., Elmagzoub, E. M., Zyoud, S. H., Soundrarajan, D., Zakarneh, B., & Al Salhi, N. R.
(2023). Exploring English language learning via Chabot: A case study from a self-determination theory
perspective. Computers and Education: Artificial Intelligence, 5, 100148. Advance online publication.
doi:10.1016/j.caeai.2023.100148

337

Designing Language Learning Experiences With Generative AI Tools

Bailey, D., Southam, A., & Costley, J. (2021). Digital storytelling with chatbots: Mapping L2 participa-
tion and perception patterns. Interactive Technology and Smart Education, 18(1), 85–103. doi:10.1108/
ITSE-08-2020-0170
Barrot, J. S. (2023). Using ChatGPT for second language writing: Pitfalls and potentials. Assessing
Writing, 57, 1–4. doi:10.1016/j.asw.2023.100745
Branson, R. K., Rayner, G. T., Cox, J. L., Furman, J. P., King, F. J., & Hannum, W. H. (1975). Interser-
vice procedures for instructional systems development.: Vol. 1-5. TRADOC Pam 350-30, NAVEDTRA
106A). U.S. Army Training and Doctrine Command.
Cao, C. C., Ding, Z., Lin, J., & Hopfgartner, F. (2023). AI chatbots as multi-role pedagogical agents:
Transforming engagement in CS education. arXiv.org. https://doi.org//arxiv.2308.03992. doi:10.48550
Chan, C. K. Y., & Hu, W. (2023). Students’ voices on generative AI: Perceptions, benefits, and challenges
in higher education. International Journal of Educational Technology in Higher Education, 20(1), 43.
doi:10.1186/s41239-023-00411-8
Clark, D. (2021). Learning experience design: How to create effective learning that works. Kogan Page
Limited.
Dakakni, D., & Safa, N. (2023). Artificial intelligence in the L2 classroom: Implications and challenges
on ethics and equity in higher education: A 21st century Pandora’s box, Computers and Education. Ar-
tificial Intelligence, 5, 100179. Advance online publication. doi:10.1016/j.caeai.2023.100179
Dick, W., & Carey, L. (1978). The systematic design of instruction. Scott, Foresman.
Fryer, L., Coniam, D., Carpenter, R., & Lăpușneanu, D. (2020). Bots for language learning now: Current
and future directions. Language Learning & Technology, 24(2), 8–22.
Gagné, R. M. (1965). The conditions of learning. Holt, Rinehart, and Winston.
Hapsari, I. P., & Wu, T. T. (2022). AI chatbots learning model in English speaking skill: Alleviating
speaking anxiety, boosting enjoyment, and fostering critical thinking. In Innovative Technologies and
Learning. ICITL 2022. Springer. doi:10.1007/978-3-031-15273-3_49
Haristiani, N. (2019). Artificial Intelligence (AI) chatbot as language learning medium: An inquiry.
Journal of Physics: Conference Series, 1387(1), 12020. doi:10.1088/1742-6596/1387/1/012020
Hill, J., Ford, W. F., & Farreras, I. G. (2015). Real conversations with artificial intelligence: A comparison
between human-human online conversations and human–chatbot conversations. Computers in Human
Behavior, 49, 245–250. doi:10.1016/j.chb.2015.02.026
Hsu, Y.-C., & Ching, Y.-H. (2023). Generative Artificial Intelligence in education, Part One: The dynamic
frontier. TechTrends: Linking Research & Practice to Improve Learning, 67(4), 603–607. doi:10.1007/
s11528-023-00863-9
Huang, W. (2023). Memes in Language Classrooms: From Traditional to AI-Generated. FLTMagazine.
https://fltmag.com/memes-in-language-classrooms-from-traditional-to-ai-generated/

338

Designing Language Learning Experiences With Generative AI Tools

Huang, W., Hew, K. F., & Fryer, L. K. (2022). Chatbots for language learning—Are they really useful?
A systematic review of chatbot-supported language learning. Journal of Computer Assisted Learning,
38(1), 237–257. doi:10.1111/jcal.12610
Jeon, J. (2022). Exploring AI chatbot affordances in the EFL classroom: Young learners’ experiences and
perspectives. Computer Assisted Language Learning, •••, 1–26. doi:10.1080/09588221.2021.2021241
Jia, F., Sun, D., Ma, Q., & Looi, C.-K. (2022). Developing an AI-based learning system for L2 learners’
authentic and ubiquitous learning in English language. Sustainability (Basel), 14(23), 15527. doi:10.3390/
su142315527
Kılıçkaya, F. (2020). Using a chatbot, Replika, to practice writing through conversations in L2 English:
A case study. In M. Kruk & M. Peterson (Eds.), New Technological Applications for Foreign and Second
Language Learning and Teaching (pp. 221–238). IGI Global. doi:10.4018/978-1-7998-2591-3.ch011
Kim, J., Lee, H., & Cho, Y. H. (2022). Learning design to support student-AI collaboration: Perspectives
of leading teachers for AI in education. Education and Information Technologies, 27(5), 6069–6104.
doi:10.1007/s10639-021-10831-6
Kohnke, L., Moorhouse, B. L., & Zou, D. (2023). ChatGPT for language teaching and learning. RELC
Journal, 54(2), 537–550. doi:10.1177/00336882231162868
Krathwohl, D. R. (2002). A revision of Bloom’s taxonomy: An overview. Theory into Practice, 41(4),
212–218. doi:10.1207/s15430421tip4104_2
Merrill, M. D. (2002). First principles of instruction. Educational Technology Research and Develop-
ment, 50(3), 43–59. doi:10.1007/BF02505024
Modern Language Association. (2007). Foreign languages and higher education: New structures for a
changed world. https://www.mla.org/Resources/Guidelines-and-Data/Reports-and-Professional-Guide-
lines/Foreign-Languages-and-Higher-Education-New-Structures-for-a-Changed-World
Nash, B. L., Hicks, T., Garcia, M., Fassbender, W., Alvermann, D., Boutelier, S., McBride, C., McGrail,
E., Moran, C., O’Byrne, I., Piotrowski, A., Rice, M., & Young, C. (2023). Artificial Intelligence in
English education: Challenges and opportunities for teachers and teacher educators. English Education,
55(3), 201–206.
Pokrivcakova, S. (2019). Preparing teachers for the application of AI-powered technologies in foreign
language education. Journal of Language and Cultural Education, 7(3), 135–153. doi:10.2478/jol-
ace-2019-0025
Pratama, M. P., Sampelolo, R., & Lura, H. (2023). Revolutionizing education: Harnessing the power
of artificial intelligence for personalized learning. Klasikal: Journal of Education, Language Teaching
and Science, 5(2), 350–357. doi:10.52208/klasikal.v5i2.877
Ranalli, J. (2021, June). L2 student engagement with automated feedback on writing: Potential for learn-
ing and issues of trust. Journal of Second Language Writing, 52, 100816. Advance online publication.
doi:10.1016/j.jslw.2021.100816

339

Designing Language Learning Experiences With Generative AI Tools

Richardson, M., & Clesham, R. (2021). Rise of the machines? The evolving role of Artificial Intelligence
(AI) technologies in high stakes assessment. London Review of Education, 19(1), 1–13. doi:10.14324/
LRE.19.1.09
Sebesta, J., & Davis, V. L. (2023, June 30). Supporting instruction and learning through Artificial
Intelligence: A survey of institutional practices & policies. WICHE Cooperative for Educational Tech-
nologies. https://wcet.wiche.edu/resources/wcetreport-supporting-instruction-learning-through-artificial-
intelligence-a-survey-ofinstitutional-practices-policies
Underwood, J. (2017). Exploring AI language assistants with primary EFL students. In K. Borthwick,
L. Bradley, & S. Thouësny (Eds.), CALL in a climate of change: Adapting to turbulent global condi-
tions – short papers from EUROCALL 2017 (pp. 317–321). doi:10.14705/rpnet.2017.eurocall2017.733
U.S. Department of Education, Office of Educational Technology. (2023). Artificial Intelligence and
Future of Teaching and Learning: Insights and Recommendations. https://tech.ed.gov/ai-future-of-
teaching-and-learning
Wang, T., Lund, B. D., Marengo, A., Pagano, N. R., Mannuru, N. R., Teel, Z. A., & Pange, J. (2023).
Exploring the potential impact of Artificial Intelligence (AI) on international students in higher educa-
tion: Generative AI, chatbots, analytics, and international student success. Applied Sciences (Basel,
Switzerland), 13(11), 6716. doi:10.3390/app13116716
Wang, X., Liu, Q., Pang, H., Tan, S. C., Lei, J., Wallace, M. P., & Li, L. (2023). What matters in
AI-supported learning: A study of human-AI interactions in language learning using cluster analysis
and epistemic network analysis. Computers & Education, 194, 104703. Advance online publication.
doi:10.1016/j.compedu.2022.104703
Wang, X., Pang, H., Wallace, M. P., Wang, Q., & Chen, W. (2022). Learners’ perceived AI presences in
AI-supported language learning: A study of AI as a humanized agent from the community of inquiry.
Computer Assisted Language Learning, 1–27. doi:10.1080/09588221.2022.2056203
Warschauer, M., Tseng, W., Yim, S., Webster, T., Jacob, S., Du, Q., & Tate, T. (2023, December). The
Affordances and Contradictions of AI-Generated Text for Second Language Writers. Journal of Second
Language Writing, 62. Advance online publication. doi:10.1016/j.jslw.2023.101071
Wei, L. (2023). Artificial intelligence in language instruction: Impact on English learning achievement,
L2 motivation, and self-regulated learning. Frontiers in Psychology, 14, 1261955. Advance online pub-
lication. doi:10.3389/fpsyg.2023.1261955 PMID:38023040
Wilson, D. V., & Marcin, M. (2022). Building connections and critical language awareness between
learning communities collaborating across two distant States. Languages (Basel, Switzerland), 7(4),
257. doi:10.3390/languages7040257
WooJ. H.ChoiH. (2021). Systematic review for AI-based language learning tools. Ithaca: Cornell Uni-
versity Library. https://arxiv.org/abs/2111.04455v1
Zhao, X. (2023). Leveraging Artificial Intelligence (AI) Technology for English Writing: Intro-
ducing Wordtune as a Digital Writing Assistant for EFL Writers. RELC Journal, 54(3), 890–894.
doi:10.1177/00336882221094089

340

Designing Language Learning Experiences With Generative AI Tools

ADDITIONAL READING

Almelhes, S. A. (2023). A review of Artificial Intelligence adoption in second-language learning. Theory

and Practice in Language Studies, 13(5), 1259–1269. doi:10.17507/tpls.1305.21
Amin, M. Y. M. (2023). AI and Chat GPT in language teaching: Enhancing EFL classroom support
and transforming assessment techniques. International Journal of Higher Education Pedagogies, 4(4),
1–15. doi:10.33422/ijhep.v4i4.554
Geçkin, V., Kızıltaş, E., & Çınar, Ç. (2023). Assessing second-language academic writing: AI vs. Hu-
man raters. Journal of Educational Technology and Online Learning, 6(4), 1096–1108. doi:10.31681/
jetol.1336599
Liang, J.-C., Hwang, G.-J., Chen, M.-R. A., & Darmawansah, D. (2023). Roles and research foci of
artificial intelligence in language education: An integrated bibliographic analysis and systematic review
approach. Interactive Learning Environments, 31(7), 4270–4296. doi:10.1080/10494820.2021.1958348
Pokrivcakova, S. (2019). Preparing teachers for the application of AI-powered technologies in foreign
language education. Journal of Language and Cultural Education, 7(3), 135–153. doi:10.2478/jol-
ace-2019-0025
Song, C., & Song, Y. (2023). Enhancing academic writing skills and motivation: Assessing the efficacy
of ChatGPT in AI-assisted language learning for EFL students. Frontiers in Psychology, 14, 1260843–
1260843. doi:10.3389/fpsyg.2023.1260843 PMID:38162975
Yuan, Y. (2023). An empirical study of the efficacy of AI chatbots for English as a foreign language
learning in primary education. Interactive Learning Environments, 1–16. doi:10.1080/10494820.2023
.2282112

KEY TERMS AND DEFINITIONS

Artificial Intelligence (AI): Machines or software completing intellectual tasks usually completed
by humans.
Emerging Technology: A newly created technology or improvements in an old technology that are
being discovered or realized.
Generative AI: Multimodal artificial intelligence that can produce text, images, and other forms of
data.
Instructional Design: An applied field for designing, developing, and delivering learning experi-
ences using a systems approach.
Learning Experience Design (LXD): Method of creating learner-centered learning experiences to
achieve learning outcomes.
Second Language (L2): A language spoken in addition to one’s native language.
Second Language Acquisition (SLA): Sometimes called, second language learning, SLA refers to
the process of a learning a new language.

341
342

Compilation of References

AbdAlgane, M., & Othman, K. A. J. (2023). Utilizing artificial intelligence technologies in Saudi EFL tertiary level class-
rooms. Journal of Intercultural Communication, 23(1), 92–99. Advance online publication. doi:10.36923/jicc.v23i1.124

Academic Integrity at UBC. (2023). CHATGPT Q&A. https://academicintegrity.ubc.ca/chatgpt-faq/

ACTFL. (2024). ACTFL performance descriptors for language learners. https://www.actfl.org/educator-resources/

actfl-performance-descriptors

Adipat, S., Laksana, K., Busayanon, K., Piatanom, P., Mahamarn, Y., Pakapol, P., & Ausawasowan, A. (2022). The world
of technology: Artificial intelligence in education. Special Education, 2(43), 2142–2146.

Ahmed, M. A. (2023). ChatGPT and the EFL classroom: Supplement or substitute in Saudi Arabia’s eastern region.
Information Sciences Letters, 12(7), 2727–2734. doi:10.18576/isl/120704

Aikins, R., & Kuo, A. (2023). What Students Said About the Spring of ChatGPT. Inside Higher Ed. https://www.inside-
highered.com/opinion/views/2023/09/07/what-students-said-about-spring-chatgpt-opinion?fbclid=IwAR0vUM4HY5i
deFrvGVABp2sz8MZGuzEss4EH-YiXtaUZZ1_UsZA0xKar8kk_aem_AaflEkiAJcqt065wZj0M4DpuY4xmlkyGMn-
z6JBFWzOh8ZjZMuKvLmriGOa6Cr1rHDho&mibextid=Zxz2cZ

Ajzen, I. (1991). The theory of planned behavior. Organizational Behavior and Human Decision Processes, 50(2),
179–211. doi:10.1016/0749-5978(91)90020-T

Akgün, S., & Greenhow, C. (2021). Artificial intelligence in education: Addressing ethical challenges in K-12 settings.
AI and Ethics, 2(3), 431–440. doi:10.1007/s43681-021-00096-7 PMID:34790956

Compilation of References

Akter, S., McCarthy, G., Sajib, S., Michael, K., Dwivedi, Y. K., D’Ambra, J., & Shen, K. N. (2021). Algorithmic bias in
data-driven innovation in the age of AI. International Journal of Information Management, 60, 102387. doi:10.1016/j.
ijinfomgt.2021.102387

Al Darayseh, A. (2023). Acceptance of artificial intelligence in teaching science: Science teachers’ perspective. Comput-
ers and Education: Artificial Intelligence, 4, 100–132. doi:10.1016/j.caeai.2023.100132

Aldeman, N. L. S., Aita, K., Machado, V. P., da Mata Sousa, L. C. D., Coelho, A. G. B., da Silva, A. S., Mendes, A. P.
D., Neres, F. J. D., & do Monte, S. J. H. (2021). Smartpath (k): A platform for teaching glomerulopathies using machine
learning. BMC Medical Education, 21(1), 248. doi:10.1186/s12909-021-02680-1 PMID:33926437

Alhalangy, A., & AbdAlgane, M. (2023). Exploring the impact of AI on the EFL context: A case study of Saudi universi-
ties. Journal of Intercultural Communication, 23(2), 41–49. doi:10.36923/jicc.v23i2.125

Alharbi, W. (2023). AI in the foreign language classroom: A pedagogical overview of automated writing assistance tools.
Education Research International, 2023, 1–15. doi:10.1155/2023/4253331

Allen Interactions. (2021). E-Learning development with SAM. Allen Interactions. https://www.alleninteractions.com/
services/custom-learning/sam/elearning-development

Almelhes, S. A. (2023). A Review of Artificial Intelligence Adoption in Second-Language Learning. Theory and Practice
in Language Studies, 13(5), 1259–1269. doi:10.17507/tpls.1305.21

Almutairi, A., Gegov, A., Adda, M., & Arabikhan, F. (2020). Conceptual artificial intelligence framework to im-
proving English as second language. WSEAS Transactions on Advances in Engineering Education, 17, 87–91.
doi:10.37394/232010.2020.17.11

Alshumaimeri, Y. A., & Alshememry, A. K. (2023). The extent of AI applications in EFL learning and teaching. IEEE
Transactions on Learning Technologies. Advance online publication. doi:10.1109/TLT.2023.3322128

Alzahrani, F. K., & Alhalafawy, W. S. (2023). Gamification for Learning Sustainability in the Blackboard System: Moti-
vators and Obstacles from Faculty Members’ Perspectives. Sustainability (Basel), 15(5), 4613. doi:10.3390/su15054613

American Council on the Teaching of Foreign Languages (ACTFL). (2017). NCSSFL-ACTFL Can-Do Statements.
Retrieved from https://www.actfl.org/resources/ncssfl-actfl-can-do-statements

Andersen, R., & Shirai, Y. (1994). Discourse motivations for some cognitive acquisition principles. Studies in Second
Language Acquisition, 16(2), 133–156. doi:10.1017/S0272263100012845

Annamalai, N., Elmagzoub, E. M., Zyoud, S. H., Soundrarajan, D., Zakarneh, B., & Al Salhi, N. R. (2023). Exploring
English language learning via Chabot: A case study from a self-determination theory perspective. Computers and Educa-
tion: Artificial Intelligence, 5, 100148. Advance online publication. doi:10.1016/j.caeai.2023.100148

343
Compilation of References

An, X., Chai, C. S., Li, Y., Zhou, Y., Shen, X., Zheng, C., & Chen, M. (2023). Modeling English teachers’ behavioral
intention to use artificial intelligence in middle schools. Education and Information Technologies, 28(5), 5187–5208.
doi:10.1007/s10639-022-11286-z

‎ andem: Language exchange. https://apps.apple.com/us/app/tandem-language-exchange/id959001619

App Store. (2015). T

Arnold, K., & Pistilli, M. (2012). Course signals at Purdue: Using learning analytics to increase student success. Pro-
ceedings of the 2nd international conference on learning analytics and knowledge (pp. 267–270). New York: ACM.
10.1145/2330601.2330666

Asiksoy, G. (2018). ELT students’ attitudes and awareness towards the use of Web 2.0 technologies for language learn-
ing. Journal of Language and Linguistic Studies, 14(2), 240–251.

Auer, M. E., Pester, A., & May, D. (Eds.). (2022). Learning with Technologies and Technologies in Learning: Experi-
ence, Trends and Challenges in Higher Education (Vol. 456). Springer International Publishing. https://link.springer.
com/10.1007/978-3-031-04286-7

Awad, A. (2023). Interview by author. MESA.

Aziz, R. (2023). Creativity in higher education: The effect of personality on students’ creative thinking skills. Thinking
Skills and Creativity Journal, 6(1), 44–51. doi:10.23887/tscj.v6i1.54916

Azzo, A. (2023). Teaching Artificial Intelligence Literacy: ‘AI Is for Everyone.’ Artificial Intelligence at Northwestern.
https://ai.northwestern.edu/news-events/articles/2023/teaching-artificial-intelligence-literacy-ai-is-for-everyone.html

Bacon-Shone, J., Bolton, K., & Luke, K. K. (2015). Language use, proficiency and attitudes in Hong Kong. Social Sci-
ences Research Centre, HKU.

Baha, T. A., Hajji, M. E., Es-Saady, Y., & Fadili, H. (2023). The impact of educational chatbot on student learning
experience. Education and Information Technologies. Advance online publication. doi:10.1007/s10639-023-12166-w

Bai, B., Wang, J., & Zhou, H. (2020). An intervention study to improve primary school students’ self-regulated strategy
use in English writing through e-learning in Hong Kong. Computer Assisted Language Learning, 35(9), 2265–2290. do
i:10.1080/09588221.2020.1871030

Bai̇doo-Anu, D., & Ansah, L. O. (2023). Education in the era of generative artificial intelligence (AI): Understanding the
potential benefits of ChatGPT in promoting teaching and learning. Journal of AI, 7(1), 52–62. doi:10.61969/jai.1337500

Bailey, D., Southam, A., & Costley, J. (2021). Digital storytelling with chatbots: Mapping L2 participation and perception
patterns. Interactive Technology and Smart Education, 18(1), 85–103. doi:10.1108/ITSE-08-2020-0170

Bardovi-Harlig, K. (1998). Examining the role of text type in L2 tense-aspect research: Broadening our horizons. En P.
Robinson y N. Jungheim (Eds.), Representation and process: Proceedings of the 3rd Pacific Second Language Research
Forum (pp. 139–150). Tokyo: Pacific SLRF.

Bardovi-Harlig, K. (2000). Tense and aspect in second language acquisition: Form, meaning, and use. Blackwell.,
doi:10.1111/0023-8333.50.s1.7

Barrot, J. S. (2023). Using ChatGPT for second language writing: Pitfalls and potentials. Assessing Writing, 57, 100745-.
doi:10.1016/j.asw.2023.100745

344
Compilation of References

Baskara, R., & Mukarto. (2023). Exploring the implications of ChatGPT for language learning in higher education. Indo-
nesian Journal of English Language Teaching and Applied Linguistics, 7(2), 343–358. https://eric.ed.gov/?id=EJ1391490

Baskara, R. (2023). Exploring the implications of ChatGPT for language learning in higher education. Indonesian Journal
of English Language Teaching and Applied Linguistics, 7(2), 343–358.

Basturkmen, H. (2023). Explicit versus implicit grammar instruction and knowledge. In J. I. Liontas (Ed.), The TESOL
encyclopedia of English language teaching (pp. 1–7). doi:10.1002/9781118784235.eelt0060

Behrens, H. (2021). Constructivist approaches to first language acquisition. Journal of Child Language, 48(5), 959–983.
doi:10.1017/S0305000921000556 PMID:34382923

Belda-Medina, J., & Calvo-Ferrer, J. R. (2022). Using chatbots as AI conversational partners in language learning. Ap-
plied Sciences (Basel, Switzerland), 12(17), 8427. doi:10.3390/app12178427

Bello, A. (1847). Gramática de la lengua castellana destinada al uso de los americanos. Edición digital a partir de obras
completas. Tomo Cuarto, 3ªed., Caracas, La Casa de Bello.

Bibauw, S., François, T., & Desmet, P. (2019). Discussing with a computer to practice a foreign language: Research
synthesis and conceptual framework of dialogue-based call. Computer Assisted Language Learning, 32(8), 827–877.
doi:10.1080/09588221.2018.1535508

Bilquise, G., & Shaalan, K. (2022). AI-based Academic Advising Framework: A Knowledge Management Perspective. In-
ternational Journal of Advanced Computer Science and Applications, 13(8), 193–203. doi:10.14569/IJACSA.2022.0130823

Bin-Hady, W. R. A., Al-Kadi, A., Hazaea, A., & Ali, J. K. M. (2023). Exploring the dimensions of ChatGPT in English
language learning: A global perspective. Library Hi Tech. Advance online publication. doi:10.1108/LHT-05-2023-0200

Birck, J. (2017). Zarah und Zottel: ein Pony auf vier Pfoten. Fischer Sauerländer Verlag.

Birdsell, B. (2022). Student Writings with DeepL: Teacher Evaluations and Implications for Teaching. JALT Postconfer-
ence Publication, 2021(1), 117. doi:10.37546/JALTPCP2021-14

Birks, M., Chapman, Y., & Francis, K. (2008). Memoing in qualitative research: Probing data and processes. Journal of
Research in Nursing, 13(1), 68–75. doi:10.1177/1744987107081254

Bolton, K., Bacon-Shone, J., & Lee, S.-l. (2020). Societal multilingualism in Hong Kong. In P. Siemund & J. Leimgruber
(Eds.), Multilingual global cities: Dubai, Hong Kong and Singapore (pp. 160–184). Routledge. doi:10.4324/9780429463860-
12

Bolton, K., & Lee, S.-l. (2020). A socio-historical approach to multilingualism in Hong Kong. In P. Siemund & J. Leimgruber
(Eds.), Multilingual global cities: Hong Kong, Singapore, and Dubai (pp. 38–62). Routledge. doi:10.4324/9780429463860-4

Bonner, E., Lege, R., & Frazier, E. (2023). Large Language Model-Based Artificial Intelligence in the Language Class-
room: Practical Ideas for Teaching. Teaching English with Technology, 2023(1). doi:10.56297/BKAM1691/WIEO1749

Bonner, E., Lege, R., & Frazier, E. (2023). Large language model-based artificial intelligence in the language classroom:
Practical ideas for teaching. Teaching English with Technology, 23(1).

Borenstein, J., & Howard, A. (2021). Emerging challenges in AI and the need for AI ethics education. AI and Ethics,
1(1), 61–65. doi:10.1007/s43681-020-00002-7

Bostrom, N., Yudkowsky, E., & Frankish, K. (2014). The Cambridge handbook of artificial intelligence. In K. Frankish
& W. M. Ramsey (Eds.), The ethics of artificial intelligence (Vol. 316, p. 334). Cambridge University Press.

345
Compilation of References

Bozkurt, A. (2023). Generative artificial intelligence (AI) powered conversational educational agents: The inevitable
paradigm shift. Asian Journal of Distance Education, 18(1).

Branson, R. K., Rayner, G. T., Cox, J. L., Furman, J. P., King, F. J., & Hannum, W. H. (1975). Interservice procedures
for instructional systems development.: Vol. 1-5. TRADOC Pam 350-30, NAVEDTRA 106A). U.S. Army Training and
Doctrine Command.

Braunmüller, K. (2007). Receptive multilingualism in northern Europe in the Middle Ages. In J. D. ten Thije & L.
Zeevaert (Eds.), Receptive multilingualism. Linguistic analyses, language policies and didactic concepts (pp. 25–47).
John Benjamins.

Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2), 77–101.
doi:10.1191/1478088706qp063oa

Braun, V., Clarke, V., Boulton, E., Davey, L., & McEvoy, C. (2020). The online survey as a qualitative research tool.
International Journal of Social Research Methodology, 00(00), 1–14. doi:10.1080/13645579.2020.1805550

Brena, R. F., Zuvirie, E., Preciado, A., Valdiviezo, A., Gonzalez-Mendoza, M., & Zozaya-Gorostiza, C. (2021). Auto-
mated evaluation of foreign language speaking performance with machine learning. [IJIDeM]. International Journal on
Interactive Design and Manufacturing, 15(2–3), 317–331. doi:10.1007/s12008-021-00759-z

Briggs, N. (2018). Neural Machine Translation Tools in the Language Learning Classroom: Students’ Use, Perceptions,
and Analyses. The JALT CALL Journal, 14(1), 3–24. Advance online publication. doi:10.29140/jaltcall.v14n1.221

Brownell, J., & Swaner, L. (2010). Five High-Impact Practices: Research on Learning Outcomes, Completion, and
Quality. Association of American Colleges and Universities.

Bruffee, K. A. (1984). Collaborative learning and the “Conversation of Mankind.”. College English, 46(7), 635.
doi:10.2307/376924

Buchanan-Shrader, H. (2023). Top 8 Ways Chinese Teachers Can Use ChatGPT to Create Lesson Plans. https://www.
thechairmansbao.com/blog/chatgpt-teach-chinese/

Burgsteiner, H., Kandlhofer, M., & Steinbauer, G. (2016). Irobot: Teaching the basics of artificial intelligence in high
schools. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1). Advance online publication. doi:10.1609/
aaai.v30i1.9864

Burkhard, M. (2022). Student Perceptions of Ai-Powered Writing Tools: Towards Individualized Teaching Strategies.
Proceedings of the 19th International Conference on Cognition and Exploratory Learning in the Digital Age, CELDA
2022, Celda, 73–81. 10.33965/CELDA2022_202207L010

Busch, W. (2015). Max und Moritz: eine Bubengeschichte in Sieben Streichen. Esslinger Verlag.

Byram, M. (2020). Teaching and assessing intercultural communicative competence: Revisited. Multilingual Matters.
doi:10.21832/BYRAM0244

Byrnes, H., & Manchón, R. M. (2014). Task-based language learning: Insights from and for L2 writing. An Introduction.
In H. Byrnes & R. M. Manchón (Eds.), Task-based language learning—Insights from and for L2 writing (pp. 1–23).
John Benjamins. doi:10.1075/tblt.7.01byr

Cai, W. (2023, February 24). ChatGPT can be powerful tool for language learning: The innovation offers multiple op-
portunities for language teaching and learning. University Affairs. https://www.universityaffairs.ca/career-advice/career-
advice-article/chatgpt-can-be-powerful-tool-for-language-learning/

346
Compilation of References

Camacho, A., Alves, R. A., & Boscolo, P. (2021). Writing motivation in school: A systematic review of empirical research
in the early twenty-first century. Educational Psychology Review, 33(1), 213–247. doi:10.1007/s10648-020-09530-4

Candelier, M. (2013). Janua linguarum – The gateway to languages – The introduction of language awareness into the
curriculum: Awakening to languages. Council of Europe.

Candelier, M., Daryai-Hansen, P., & Schröder-Sura, A. (2013). The framework of reference for pluralistic approaches
to languages and cultures–a complement to the CEFR to develop plurilingual and intercultural competences. Innovation
in Language Learning and Teaching, 6(3), 243–257. doi:10.1080/17501229.2012.725252

Cardona, M. A., Rodríguez, R. J., & Ishmael, K. (2023). Artificial Intelligence and the Future of Teaching and Learning:
Insights and Recommendations. U.S. Department of Education, Office of Educational Technology. https://policycom-
mons.net/artifacts/3854312/ai-report/4660267/

Carlson, M., Pack, A., & Escalante, J. (2023). Utilizing OpenAI’s GPT-4 for written feedback. TESOL Journal, 759,
e759. Advance online publication. doi:10.1002/tesj.759

Carrington, V. (2005). Txting: The end of civilization (again)? Cambridge Journal of Education, 35(2), 161–175.
doi:10.1080/03057640500146799

Carvalho, L., Martinez-maldonado, R., Tsai, Y., & Markauskaite, L. (2022). Computers and Education : Artificial In-
telligence How can we design for learning in an AI world ? Computers and Education: Artificial Intelligence, 3(July),
100053. doi:10.1016/j.caeai.2022.100053

Cavalcanti, A. P., Diego, A., Carvalho, R., Freitas, F., Tsai, Y. S., Gaˇsevi´c, D., & Mello, R. F. (2021). Automatic feedback
in online learning environments: A systematic literature review. Computers and Education: Artificial Intelligence, 100027.

Cavanagh, S. R. (2020). How to make your teaching more engaging. The Chronicle of Higher Education.

Celik, I., Dindar, M., Muukkonen, H., & Järvelä, S. (2022). The promises and challenges of artificial intelligence for
teachers: A systematic review of research. TechTrends, 66(4), 616–630. doi:10.1007/s11528-022-00715-y

Chan, C. K. Y. (2023). A comprehensive AI policy education framework for university teaching and learning. Interna-
tional Journal of Educational Technology in Higher Education, 2023(20), 38. doi:10.1186/s41239-023-00408-3

Chan, C. K. Y., & Hu, W. (2023). Students’ voices on generative AI: Perceptions, benefits, and challenges in higher educa-
tion. International Journal of Educational Technology in Higher Education, 20(1), 43. doi:10.1186/s41239-023-00411-8

Chang, D. H., Lin, M. P.-C., Hajian, S., & Wang, Q. Q. (2023). Educational Design Principles of Using AI Chatbot That
Supports Self-Regulated Learning in Education: Goal Setting, Feedback, and Personalization. Sustainability, 15(17),
12921-. doi:10.3390/su151712921

Chassignol, M., Khoroshavin, A., Klimova, A., & Bilyatdinova, A. (2018). Artificial Intelligence trends in education: A
narrative overview. Procedia Computer Science, 136, 16–24. doi:10.1016/j.procs.2018.08.233

Chaudhry, M., & Kazim, E. (2021). Artificial intelligence in education (AIEd): A high-level academic and industry note
2021. AI and Ethics, 2(1), 157–165. doi:10.1007/s43681-021-00074-z PMID:34790953

Chavez, M. (2016). Students’ accounts of grammatical forms of German that are difficult, unattainable, and irrelevant
for self-expression. Language Awareness, 25(3), 197–221. doi:10.1080/09658416.2016.1165238

Chavez, M. (2017). Hard rules and bad memories: College learner’s accounts of what makes learning German grammar
difficult. Die Unterrichtspraxis, 50(1), 1–21. doi:10.1111/tger.12018

347
Compilation of References

Chen, L. (2023, June 23). Hong Kong rolls out first AI curriculum for junior secondary students, including lessons on
ChatGPT, with ‘lives definitely affected by artificial intelligence’. South China Morning Post.

Chen, L., Chen, P., & Lin, Z. (2020). Artificial intelligence in education: A review. IEEE Access : Practical Innovations,
Open Solutions, 8, 75264–75278. doi:10.1109/ACCESS.2020.2988510

Chen, X., Xie, H., & Hwang, G. J. (2020). A multi-perspective study on Artificial Intelligence in Education: Grants,
conferences, journals, software tools, institutions, and researchers. Computers and Education: Artificial Intelligence,
1(October), 100005. doi:10.1016/j.caeai.2020.100005

Chen, X., Zhou, D., Xie, H., Cheng, G., & Liu, C. (2022). Two decades of artificial intelligence in education: Contribu-
tors, collaborations, research topics, challenges, and future directions. Journal of Educational Technology & Society,
25(1), 28–47.

Chen, X., Zou, D., Xie, H., & Cheng, G. (2021). Twenty years of personalized language learning. Journal of Educational
Technology & Society, 24(1), 205–222.

Chin, A. C. (2023). A corpus-based approach to learning and teaching Cantonese. In S. L. Lee (Ed.), The learning and
teaching of Cantonese as a second language (pp. 184–195). Routledge.

Chin, K. Y., Wu, C. H., & Hong, Z. W. (2011). A humanoid robot as a teaching assistant for primary education. In 2011
Fifth International Conference on Genetic and Evolutionary Computing (pp. 21-24). IEEE. 10.1109/ICGEC.2011.13

Chmarkh, M. (2021). “Writing to learn” research: A synthesis of empirical studies (2004-2019). European Journal of
Educational Research, 10(1), 85–96. doi:10.12973/eu-jer.10.1.85

Choi, Y., & Suh, K. H. (2022). Verifying the usefulness of the theory of planned behavior model for predicting illegal
use of online content: The role of outcome expectancies and social loafing. BMC Psychology, 10(1), 1–12. doi:10.1186/
s40359-022-00978-3 PMID:36371253

Cholij, M. (1994). Practice in Spanish Grammar. Mary Glasgow Publications.

Clark, D. (2020). Artificial intelligence for learning: How to use AI to support employee development. Kogan Page
Publishers.

Clark, D. (2021). Learning experience design: How to create effective learning that works. Kogan Page Limited.

Cohen, I. L., Liu, X., Hudson, M., Gillis, J., Cavalari, R. N., Romanczyk, R. G., Karmel, B. Z., & Gardner, J. M. (2017).
Level 2 Screening With the PDD Behavior Inventory: Subgroup Profiles and Implications for Differential Diagnosis.
Canadian Journal of School Psychology, 32(3-4), 299–315. doi:10.1177/0829573517721127

Cohen, M. D., & Téllez, K. (1994). Implementing cooperative learning for language minority students. Bilingual Research
Journal, 18(1–2), 1–19. doi:10.1080/15235882.1994.10162655

Collen, I. (2020). Language Trends 2020. Language Teaching in primary and secondary schools in England. British
Council.

Collen, I. (2021). Language Trends 2021. Language Teaching in primary and secondary schools in England. British
Council.

Collen, I. (2022). Language Trends 2022. Language Teaching in primary and secondary schools in England. British
Council.

348
Compilation of References

Collen, I. (2023). Language Trends Northern Ireland 2023: Language teaching in Primary and Post-Primary Schools.
British Council.

Coniam, D. (2014). The linguistic accuracy of chatbots: Usability from an ESL perspective. Text & Talk, 34(5), 545–567.
doi:10.1515/text-2014-0018

Connor, U. (1998). Contrastive rhetoric: Developments and challenges. Studia Anglica Posnaniensia, 33, 105–116.

Cope, B., Kalantzis, M., & Searsmith, D. (2021). Artificial intelligence for education: Knowledge and its assessment
in AI-enabled learning ecologies. Educational Philosophy and Theory, 53(12), 1229–1245. doi:10.1080/00131857.20
20.1728732

Council of Europe. (2001). Common European Framework of Reference for Languages: Learning, Teaching, Assess-
ment. Cambridge University Press.

Council of Europe. (2021). Common European Framework of Reference for Languages: Learning, Teaching, Assess-
ment—Companion Volume. Council of Europe Publishing.

Council of Europe. (n.d.). Common European Framework of Reference for Languages: Learning, teaching, assessment.
https://www.coe.int/en/web/common-european-framework-reference-languages

Creswell, J. W. (2012). Educational research. Pearson.

Critchley, M., Illingworth, J., & Wright, V. (2021). Survey of Language Provision in UK Universities in 2021. Report
no. 3, julio. University Council of Modern Languages (UCML), Association for University Language Communities in
the UK and Ireland (AULC), United Kingdom.

Crompton, H., & Burke, D. (2023). Artificial intelligence in higher education: The state of the field. International Journal
of Educational Technology in Higher Education, 20(1), 22. doi:10.1186/s41239-023-00392-8

Dakakni, D., & Safa, N. (2023). Artificial intelligence in the L2 classroom: Implications and challenges on ethics and
equity in higher education: A 21st century Pandora’s box, Computers and Education. Artificial Intelligence, 5, 100179.
Advance online publication. doi:10.1016/j.caeai.2023.100179

Dale, R. (2021). GPT-3: What’s it good for? Natural Language Engineering, 27(1), 113–118. doi:10.1017/
S1351324920000601

Dalton‐Puffer, C. (2011). Content-and-Language Integrated Learning: From Practice to Principles? Annual Review of
Applied Linguistics, 31, 182–204. Advance online publication. doi:10.1017/S0267190511000092

Danan, M. (2004). Captioning and subtitling: Undervalued language learning strategies. Meta, 49(1), 67–77.
doi:10.7202/009021ar

Davenport, T. H., & Ronanki, R. (2018). Artificial intelligence for the real world. Harvard Business Review, 96(1), 108–116.

De Oliveira, L. C., Jones, L., & Smith, S. L. (2019). Multimodal literacies in the english language arts classroom for
english language learners. In English language education (pp. 21–31). doi:10.1007/978-3-030-02245-7_2

Declerck, R. (2006). The grammar of the English verb phrase.: Vol. 1. The grammar of the English tense system. A
comprehensive analysis. De Gruyter. doi:10.1515/9783110199888

349
Compilation of References

Department for Education. (2014). The national curriculum in England. Key stages 3 and 4 framework document
[DFE-00183-2013]. Retrieved from: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/at-
tachment_data/file/840002/Secondary_national_curriculum_corrected_PDF.pdf

Dewey, J. (2023). Experiential Education: Complete Collection: Problem-Based Learning, Pragmatic Philosophy of
Scholarship, Democracy & Education. Sharp Ink Publisher.

Dewi, H. K., Putri, R. E., Rahim, N. A., Wardani, T. I., & Pandin, M. G. R. (2021). The use of AI (artificial intelligence)
in English learning among university student: Case study in English Department, Universitas Airlangga. https://doi.
org/ doi:10.31235/osf.io/x3qr6

Dick, W., & Carey, L. (1978). The systematic design of instruction. Scott, Foresman.

Dincer, S. (2018). Are preservice teachers really literate enough to integrate technology in their classroom practice?
Determining the technology literacy level of preservice teachers. Education and Information Technologies, 23(6),
2699–2718. doi:10.1007/s10639-018-9737-z

Dizon, G., & Gayed, J. M. (2021). Examining the Impact of Grammarly on the Quality of Mobile L2 Writing. The JALT
CALL Journal, 17(2), 74–92. doi:10.29140/jaltcall.v17n2.336

Dodigovic, M. (2007). Artificial intelligence and second language learning: An efficient approach to error remediation.
Language Awareness, 16(2), 99–113. doi:10.2167/la416.0

Dörnyei, Z., & Ushioda, E. (Eds.). (2009). Motivation, language identity and the L2 self. Multilingual Matters.
doi:10.21832/9781847691293

Dreibelbis, E. (2023). Google Translate vs. ChatGPT: Which One Is the Best Language Translator? PCMag UK. https://
uk.pcmag.com/ai/147242/google-translate-vs-chatgpt-which-one-is-the-best-language-translator#:~:text=AI Will Level
Up Web Translation&text=But as we saw with,Translate’s capabilities across the board.

Dwivedi, Y. K., Kshetri, N., Hughes, L., Slade, E. L., Jeyaraj, A., Kar, A. K., Baabdullah, A. M., Koohang, A., Raghavan,
V., Ahuja, M., Albanna, H., Albashrawi, M. A., Al-Busaidi, A. S., Balakrishnan, J., Barlette, Y., Basu, S., Bose, I., Brooks,
L., Buhalis, D., ... Wright, R. (2023). Opinion Paper: “So what if ChatGPT wrote it?” Multidisciplinary perspectives on
opportunities, challenges and implications of generative conversational AI for research, practice and policy. International
Journal of Information Management, 71, 102642. doi:10.1016/j.ijinfomgt.2023.102642

Educause. (2018). Horizon report: 2018 higher education edition. Author.

Eguchi, A. (2021). AI-powered educational robotics as a learning tool to promote artificial intelligence and computer
science education. In Advances in intelligent systems and computing (pp. 279–287). doi:10.1007/978-3-030-82544-7_26

Ehara, Y. (2023). Innovative Software to Efficiently Learn English Through Extensive Reading and Personalized Vo-
cabulary Acquisition. Academic Press.

350
Compilation of References

Ellis, R. (2009). Implicit and explicit learning, knowledge, and instruction. In R. Ellis, S. Loewen, C. Elder, H. Reinders,
R. Erlam, & J. Philp, J. (Eds.), Implicit and explicit knowledge in second language learning, testing, and teaching (pp.
3–26). Multilingual Matters. doi:10.21832/9781847691767-003

Ellis, N. C. (2015). Implicit AND explicit learning of language. In P. Rebuschat (Ed.), Implicit and explicit learning of
language (pp. 3–24). Benjamins. doi:10.1075/sibil.48.01ell

Ellis, R. (2006). Current issue in the teaching of grammar: An SLA perspective. TESOL Quarterly, 40(1), 83–107.
doi:10.2307/40264512

Ellis, R. (2016). Focus on form: A critical review. Language Teaching Research, 20(3), 405–428.
doi:10.1177/1362168816628627

El-Sabagh, H. A. (2021). Adaptive e-learning environment based on learning styles and its impact on development stu-
dents’ engagement. International Journal of Educational Technology in Higher Education, 18(1), 53. Advance online
publication. doi:10.1186/s41239-021-00289-4

Ennis, R. H. (2015). Critical thinking: A streamlined conception. In M. Davies & R. Barnett (Eds.), The Palgrave Hand-
book of Critical Thinking in Higher Education. doi:10.1057/9781137378057_2

Esplugas, M. (2023). The use of artificial intelligence (AI) to enhance academic communication, education and research:
A balanced approach. The Journal of Hand Surgery, 48(8), 819–822. doi:10.1177/17531934231185746 PMID:37417005

Eun, B. (2010). From learning to development: A sociocultural approach to instruction. Cambridge Journal of Educa-
tion, 40(4), 401–418. doi:10.1080/0305764X.2010.526593

EUROSTAT. (2016). Number of foreign languages known (self-reported) by sex [edat_aes_l21] Retrieved from: https://
appsso.eurostat.ec.europa.eu/nui/submitViewTableAction.do

EUROSTAT. (2022). Pupils by education level and number of modern foreign languages studied - absolute numbers
and % of pupils by number of languages studied [EDUC_UOE_LANG02] Retrieved from: https://ec.europa.eu/eurostat/
databrowser/view/educ_uoe_lang02/default/table?lang=en

Fan, Y., Saint, J., Singh, S., Jovanovic, J., & Gasevic, D. (2021). A learning analytic approach to unveiling self-regulatory
processes in learning tactics. LAK21: 11th international learning analytics and knowledge conference, 184–195.

Ferris, D., & Hedgcock, J. (2014). Teaching L2 composition: Purpose, process, and practice (3rd ed.). Routledge.

Fink, L. D. (2016). Creating significant learning experiences: An integrated approach to designing college courses.
John Wiley& Sons.

Fink, L. D. (2016). Five High-Impact Teaching practices (Vol. 9). Collected Essays on Learning and Teaching.

Fitria, T. N. (2021). Grammarly” as AI-powered English Writing Assistant. Journal of English Language Literature and
Teaching, 5(1), 65-78.

Flower, L., & Hayes, J. R. (1981). A cognitive process theory of writing. College Composition and Communication,
32(4), 365–387. doi:10.2307/356600

Foltýnek, T., Bjelobaba, S., Glendinning, I., Khan, Z. R., Santos, R., Pavletic, P., & Kravjar, J. (2023). ENAI Recom-
mendations on the Ethical Use of Artificial Intelligence in Education. International Journal for Educational Integrity,
19(1), 12. Advance online publication. doi:10.1007/s40979-023-00133-4

Fryer, L. K., Nakao, K., & Thompson, A. (2019). Chatbot learning partners: Connecting learning experiences, interest
and competence. Computers in Human Behavior, 93, 279–289. doi:10.1016/j.chb.2018.12.023

351
Compilation of References

Fryer, L., Coniam, D., Carpenter, R., & Lăpușneanu, D. (2020). Bots for language learning now: Current and future
directions. Language Learning & Technology, 24(2), 8–22.

Fulford, M. (2023). In the AI age, it’s time to change how we teach and grade writing: If we continue to treat the use of AI
as plagiarism, we’re doomed to fail. Here’s what we should be doing instead. Chalkbeat Colorado. https://co.chalkbeat.
org/2023/8/4/23820783/ai-chat-gpt-teaching-writing-grading?fbclid=IwAR2IuQa23f0M6dxmfay5nB_DlQgrJfMf-
Pmm9hMbrWYVMW3WKAaruL3XrNKE

Fu, S., Gu, H., & Yang, B. (2020). The affordances of AI‐enabled automatic scoring applications on learners’ continu-
ous learning intention: An empirical study in China. British Journal of Educational Technology, 51(5), 1674–1692.
doi:10.1111/bjet.12995

Gado, S., Kempen, R., Lingelbach, K., & Bipp, T. (2022). Artificial intelligence in Psychology: How can we en-
able psychology students to accept and use artificial intelligence? Psychology Learning & Teaching, 21(1), 37–56.
doi:10.1177/14757257211037149

Gagné, R. M. (1965). The conditions of learning. Holt, Rinehart, and Winston.

Gallacher, A., Thompson, A., Howarth, M., Taalas, P., Jalkanen, J., Bradley, L., & Thouësny, S. (2018). “My robot is
an idiot!”–Students’ perceptions of AI in the L2 classroom. Future-proof CALL: language learning as exploration and
encounters–short papers from EUROCALL, 70-76.

GaoC. A.HowardF. M.MarkovN. S.DyerE. C.RameshS.LuoY.PearsonA. T. (2022). Comparing scientific abstracts gener-
ated by ChatGPT to original abstracts using an artificial intelligence output detector, plagiarism detector, and blinded
human reviewers. doi:10.1101/2022.12.23.521610

Gartner, S., & Krašna, M. (2023). Artificial intelligence in education - Ethical framework. In 12th Mediterranean Con-
ference on Embedded Computing (MECO) (pp. 1-7). 10.1109/MECO58584.2023.10155012

Gaudioso, E., Montero, M., & Hernandez-del-Olmo, F. (2012). Supporting teachers in adaptive educational systems through
predictive models: A proof of concept. Expert Systems with Applications, 39(1), 621–625. doi:10.1016/j.eswa.2011.07.052

Ghali, M. A., Ayyad, A. A., Abu-Naser, S. S., & Abu, M. (2018). An Intelligent Tutoring System for Teaching English
Grammar. International Journal of Academic Engineering Research, 2(2), 1–6.

Gilakjani, A. P. (2012). The significant role of multimedia in motivating EFL learners’ interest in English language
learning. International Journal of Modern Education and Computer Science, 4(4), 57–66. doi:10.5815/ijmecs.2012.04.08

Gilmore, A. (2007). Authentic materials and authenticity in foreign language learning. Language Teaching, 40(2),
97–118. doi:10.1017/S0261444807004144

Ginn, J., Salas, C. B., Barlowe, S., & Lehman, W. (2021). A novel framework for integrating mobile machine learning
and L2 vocabulary acquisition. Journal of Computing Sciences in Colleges, 36(5), 47–56.

Giorgi, A., & Pianesi, F. (1997). Tense and aspect: from semantics to morphosyntax. Oxford University Press. doi:10.1093/
oso/9780195091922.001.0001

352
Compilation of References

Godwin-Jones, R. (2022). Partnering with AI: Intelligent writing assistance and instructed language learning. Language
Learning & Technology, 26(2), 5–24.

Golonka, E. M., Bowles, A. R., Frank, V. M., Richardson, D. L., & Freynik, S. (2014). Technologies for foreign language
learning: A review of technology types and their effectiveness. Computer Assisted Language Learning, 27(1), 70–105.
doi:10.1080/09588221.2012.700315

Gong, X., Tang, Y., Liu, X., Jing, S., Cui, W., Liang, J., & Wang, F. Y. (2020, October). K-9 artificial intelligence educa-
tion in qingdao: Issues, challenges and suggestions. IEEE international conference on networking, sensing, and control
(ICNSC), 1–6.

Graham, M., Milanowski, A., & Miller, J. (2012). Measuring and Promoting Inter-Rater Agreement of Teacher and
Principal Performance Ratings. Online Submission.

Grassini, S. (2023). Shaping the Future of Education: Exploring the Potential and Consequences of AI and ChatGPT in
Educational Settings. Education Sciences, 13(7), 692-. doi:10.3390/educsci13070692

Griffin, P., & Care, E. (Eds.). (2014). Assessment and teaching of 21st-century skills: Methods and approach. Springer.
doi:10.1007/978-94-017-9395-7

Grimes, D., & Warschauer, M. (2010). Utility in a fallible tool: A multi-site case study of automated writing evaluation.
Journal of Technology. Language, and Assessment, 8(6), 1–43.

Guo, K., & Wang, D. (2023). To resist it or to embrace it? Examining ChatGPT’s potential to support teacher feedback
in EFL writing. Education and Information Technologies. Advance online publication. doi:10.1007/s10639-023-12146-0

Haenlein, M., & Kaplan, A. (2019). A brief history of artificial intelligence: On the past, present, and future of artificial
intelligence. California Management Review, 61(4), 5–14. doi:10.1177/0008125619864925

Hagendorff, T. (2020). The ethics of AI ethics: An evaluation of guidelines. Minds and Machines, 30(1), 99–120.
doi:10.1007/s11023-020-09517-8

Haleem, A., Javaid, M., & Pratap, R. (2023). BenchCouncil Transactions on Benchmarks, Standards and Evaluations
An era of ChatGPT as a significant futuristic support tool : A study on features, abilities, and challenges. BenchCouncil
Transactions on Benchmarks. Standards and Evaluations, 2(4), 100089. doi:10.1016/j.tbench.2023.100089

Hall, S. (1996). Introduction: Who needs “identity”? In S. Hall & P. Du Gay (Eds.), Questions of Cultural Identity (pp.
1–17). Sage.

Hammerly, H. (1986). Synthesis in language teaching: An introduction to languistics. Second Language Publications.

Hang, N. T. T. (2023). EFL Teachers’ Perspectives toward the Use of ChatGPT in Writing Classes: A Case Study at Van
Lang University. International Journal of Language Instruction, 2(3), 1–47. doi:10.54855/ijli.23231

Hapsari, I. P., & Wu, T. T. (2022). AI chatbots learning model in English speaking skill: Alleviating speaking anxiety,
boosting enjoyment, and fostering critical thinking. In Innovative Technologies and Learning. ICITL 2022. Springer.
doi:10.1007/978-3-031-15273-3_49

Haristiani, N. (2019). Artificial Intelligence (AI) chatbot as language learning medium: An inquiry. In Journal of Physics:
Conference Series (Vol. 1387, No. 1, p. 012020). IOP Publishing. doi:10.1088/1742-6596/1387/1/012020

Harklau, L., & Pinnow, R. (2009). Adolescent Second-Language Writing. In L. Christenbury, R. Bomer, & P. Smago-
rinsky (Eds.), Handbook of Adolescent Literacy Research (pp. 126–134). Guilford Publications.

353
Compilation of References

Harvard Business School. (2023). 2.1 Academic Standards of Conduct. Harvard Business School MBA. https://www.
hbs.edu/mba/handbook/standards-of-conduct/academic/Pages/chatgpt-and-ai.aspx

Hasbún, L. (1995). The role of lexical aspect in the acquisition of the tense/aspct system in L2 Spanish [Doctoral dis-
sertation]. Indiana University, Bloomington.

Hassan Taj, I., Ali, F., Sipra, M., & Ahmad, W. (2017). Effect of technology enhanced language learning on EFL reading
comprehension at tertiary level. Arab World English Journal, 8.

Heffernan, N. T., & Heffernan, C. L. (2014). The ASSISTments ecosystem: Building a platform that brings scientists
and teachers together for minimally invasive research on human learning and teaching. International Journal of Artificial
Intelligence in Education, 24(4), 470–497. doi:10.1007/s40593-014-0024-x

Heil, C. R., Wu, J. S., Lee, J. J., & Schmidt, T. (2016). A review of mobile language learning applications: Trends, chal-
lenges, and opportunities. The EuroCALL Review, 24(2), 32–50. doi:10.4995/eurocall.2016.6402

Hejazi, S. Y., & Sadoughi, M. (2023). How does teacher support contribute to learners’ grit? The role of learning enjoy-
ment. Innovation in Language Learning and Teaching, 17(3), 593–606. doi:10.1080/17501229.2022.2098961

Hill, J., Ford, W. F., & Farreras, I. G. (2015). Real conversations with artificial intelligence: A comparison between
human-human online conversations and human–chatbot conversations. Computers in Human Behavior, 49, 245–250.
doi:10.1016/j.chb.2015.02.026

Hodges, C. B., Moore, S., Lockee, B. B., Trust, T., & Bond, M. A. (2020). The difference between emergency remote
teaching and online learning. Academic Press.

Hoffmann, H. (2005). Der Struwwelpeter. Loewe Verlag GmbH.

Holmes, W., Porayska-Pomsta, K., Holstein, K., Sutherland, E., Baker, T. T., Shum, S. B., Santos, O. C., Rodrigo, M. M.
T., Cukurova, M., Bittencourt, I. I., & Koedinger, K. R. (2021). Ethics of AI in education: Towards a community-wide
framework. International Journal of Artificial Intelligence in Education, 32(3), 504–526. doi:10.1007/s40593-021-00239-1

Hong, W. C. H. (2023). The impact of ChatGPT on foreign language teaching and learning: Opportunities in education
and research. Journal of Educ. Technol. Innov., 5, 37–45.

Hong, W. C. H. (2023). The impact of ChatGPT on foreign language teaching and learning: Opportunities in education and
research. Journal of Educational Technology and Innovation, 5(1). https://jeti.thewsu.org/index.php/cieti/article/view/103

Hooda, M., Rana, C., Dahiya, O., Rizwan, A., & Hossain, M. S. (2022). Artificial intelligence for assessment and feedback
to enhance student success in higher education. Mathematical Problems in Engineering, 2022, 1–19. Advance online
publication. doi:10.1155/2022/5215722

Hopkins, E. (2022). Machine learning tools, algorithms, and techniques. Journal of Self-Governance and Management
Economics, 10(1), 43–55.

Hou, Y. (2020). Foreign language education in the era of artificial intelligence. In Advances in Intelligent Systems and
Computing (pp. 937–944). doi:10.1007/978-981-15-2568-1_128

Howard, K. B. (2023). Supporting learners with special educational needs and disabilities in the foreign languages
classroom. Support for Learning, 38(3), 154–161. doi:10.1111/1467-9604.12449

Hsu, Y.-C., & Ching, Y.-H. (2023). Generative Artificial Intelligence in education, Part One: The dynamic frontier.
TechTrends: Linking Research & Practice to Improve Learning, 67(4), 603–607. doi:10.1007/s11528-023-00863-9

354
Compilation of References

Huang, W. (2023). Memes in Language Classrooms: From Traditional to AI-Generated. FLTMagazine. https://fltmag.
com/memes-in-language-classrooms-from-traditional-to-ai-generated/

Huang, W., Hew, K. F., & Fryer, L. K. (2022). Chatbots for language learning – are they really useful? A systematic review
of chatbot-supported language learning. Journal of Computer Assisted Learning, 38(1), 237–257. doi:10.1111/jcal.12610

Huang, X., Zou, D., Cheng, G., Chen, X., & Xie, H. (2023). Trends, Research Issues and Applications of Artificial
Intelligence in Language Education. Journal of Educational Technology & Society, 26(1), 112–131.

Huang, X., Zou, D., Cheng, G., Chen, X., & Xie, H. (2023). Trends, research issues and applications of artificial intel-
ligence in language education. Journal of Educational Technology & Society, 26(1), 112–131. https://www.jstor.org/
stable/48707971

Huang, Y., & Wilson, J. (2021). Using automated feedback to develop writing proficiency. Computers and Composition,
62, 102675. doi:10.1016/j.compcom.2021.102675

Hussherr, F.-X., & Hussherr, C. (2017). Construire le modèle éducatif du 21e siècle-Les promesses de la digitalisation
et les nouveaux modes d’apprentissage. FYP éditions.

Huttenlocher, J., Haight, W., Bryk, A., Seltzer, M., & Lyons, T. (1991). Early vocabulary growth: Relation to language
input and gender. Developmental Psychology, 27(2), 236–248. doi:10.1037/0012-1649.27.2.236

Ifelebuegu, A. O., Kulume, P., & Cherukut, P. (2023). Chatbots and AI in Education (AIEd) tools: The good, the bad,
and the ugly. Journal of Applied Learning and Teaching, 6(2).

Immordino-Yang, M. T. (2015). Emotions, Learning, and the Brain: Exploring the Educational Implications of Affective
Neuroscience. Norton Professional Books.

Incecay, V., & Dollar, Y. K. (2011). Foreign language learners’ beliefs about grammar instruction and error correction.
Procedia: Social and Behavioral Sciences, 15, 3394–3398. doi:10.1016/j.sbspro.2011.04.307

Indiana University Knowledge Base. (2023). Acceptable uses of generative AI services at IU. https://kb.iu.edu/d/biit

Instituto Cervantes. (2023). El español en el mundo 2023. Anuario del Instituto Cervantes.

Ironsi, C. S. (2022). Navigating learners towards technology-enhanced learning during post COVID-19 semesters. Trends
in Neuroscience and Education, 29, 100189. doi:10.1016/j.tine.2022.100189 PMID:36470617

Jaiswal, A., & Arun, C. J. (2021). Potential of artificial intelligence for transformation of the education system in India.
International Journal of Education and Development Using Information and Communication Technology, 17(1), 142–158.

Janisch, H., & Zwerger, L. (2008). Die Arche Noah. Minedition.

Jatzlau, S., Michaeli, T., Seegerer, S., & Romeike, R. (2019). It’s not magic after all–machine learning in snap! Using
reinforcement learning. Academic Press.

Jean, G., & Simard, D. (2011). Grammar teaching and learning in L2: Necessary, but boring? Foreign Language Annals,
44(3), 467–494. doi:10.1111/j.1944-9720.2011.01143.x

Jeon, J. (2021). Exploring AI chatbot affordances in the EFL classroom: Young learners’ experiences and perspectives.
Computer Assisted Language Learning, 1–26. doi:10.1080/09588221.2021.2021241

Jeon, J. H., & Lee, S. (2023). Large language models in education: A focus on the complementary relationship between
human teachers and ChatGPT. Education and Information Technologies, 28(12), 15873–15892. doi:10.1007/s10639-
023-11834-1

355
Compilation of References

Jia, F., Sun, D., Ma, Q., & Looi, C.-K. (2022). Developing an AI-based learning system for L2 learners’ authentic and
ubiquitous learning in English language. Sustainability (Basel), 14(23), 15527. doi:10.3390/su142315527

Jiang, R. (2022). How does artificial intelligence empower EFL teaching and learning nowadays? A review on artifi-
cial intelligence in the EFL context. Frontiers in Psychology, 13, 1049401. Advance online publication. doi:10.3389/
fpsyg.2022.1049401 PMID:36467167

Jiang, X., Rollinson, J., Plonsky, L., Gustafson, E., & Pajak, B. (2021). Evaluating the reading and listening outcomes
of beginning‐level Duolingo courses. Foreign Language Annals, 54(4), 974–1002. doi:10.1111/flan.12600

Jian, X., Wang, J., Jia, J., & Feng, C. (2016). Perform Suzhou: A course in intermediate to advanced spoken Mandarin.
Soochow University Press.

Ji, H., Han, I., & Ko, Y. (2023). A systematic review of conversational AI in language education: Focusing on the col-
laboration with human teachers. Journal of Research on Technology in Education, 55(1), 48–63. doi:10.1080/153915
23.2022.2142873

John, P., & Woll, N. (2020). Using grammar checkers in an ESL context: An investigation of automatic corrective feed-
back. CALICO Journal, 37(2), 169–172. doi:10.1558/cj.36523

Kaddari, Z., Mellah, Y., Berrich, J., Belkasmi, M. G., & Bouchentouf, T. (2020). Natural language processing: Challenges
and future directions. In Lecture Notes in Networks and Systems (pp. 236–246). doi:10.1007/978-3-030-53970-2_22

Kamarinou, D., Millard, C., Singh, J., & Leenes, R. (2017). Machine learning with personal data. In Data protection
and privacy: The age of intelligent machines. Hart Publishing.

Kanellopoulou, C. (2019). Film subtitles as a successful vocabulary learning tool. Open Journal of Modern Linguistics,
9(02), 145–152. doi:10.4236/ojml.2019.92014

Kang, B., & Kang, S. (2022). Construction of Chinese Language Teaching System Model Based on Deep Learning under
the Background of Artificial Intelligence. Scientific Programming, 2022, 1–10. doi:10.1155/2022/3960023

Kannan, J., & Munday, P. (2018). New trends in second language learning and teaching through the lens of ICT, net-
worked learning, and artificial intelligence. Círculo de Lingüística Aplicada a la Comunicación, 76, 13–30. doi:10.5209/
CLAC.62495

Karoui, A., Alvarez, L., Geoffre, T., Guin, N., Lefèvre, M., Lachand, V., & Ramalho, M. (2022). Towards an automated
adaptive learning web platform through personalization of language learning pathways. In Lecture Notes in Computer
Science (pp. 448–454). doi:10.1007/978-3-031-16290-9_35

Kasepalu, R., Prieto, L. P., Ley, T., & Chejara, P. (2022). Teacher artificial intelligence-supported pedagogical actions in
collaborative learning coregulation: A wizard-of-oz study. Frontiers in Education, 7, 736194. Advance online publica-
tion. doi:10.3389/feduc.2022.736194

Kashdan, T. (2009). Curious? Discover the Missing Ingredient to a Fulfilling Life. Harper Collins.

Kasneci, E., Sessler, K., Küchemann, S., Bannert, M., Dementieva, D., Fischer, F., Gasser, U., Groh, G., Günnemann,
S., Hüllermeier, E., Krusche, S., Kutyniok, G., Michaeli, T., Nerdel, C., Pfeffer, J., Poquet, O., Sailer, M., Schmidt, A.,
Seidel, T., ... Kasneci, G. (2023). ChatGPT for good? On opportunities and challenges of large language models for
education. Learning and Individual Differences, 103, 102274. doi:10.1016/j.lindif.2023.102274

KasneciE.SeßlerK.KüchemannS.BannertM.DementievaD.FischerF.NerdelC. (2023). Chatgpt for good? on opportunities

and challenges of large language models for education. https://doi.org/ doi:10.35542/osf.io/5er8f

356
Compilation of References

Kasper, G. (2006). Beyond Repair: Conversation Analysis as an Approach to SLA. AILA Review, 19, 83–99. doi:10.1075/
aila.19.07kas

Kataoka, S. (2023). Textbook Cantonese romanization. In S. L. Lee (Ed.), The learning and teaching of Cantonese as
a second language (pp. 196–216). Routledge.

Kattan-Ibarra, J., & Pountain, C. (2004). Modern Spanish Grammar: A Practical Guide. Taylor and Francis.
doi:10.4324/9780203428313

Kaufman, D. (2004). Constructivist issues in language learning and teaching. Annual Review of Applied Linguistics, 24.
Advance online publication. doi:10.1017/S0267190504000121

Keating, E., & Egbert, M. (2004). Conversation as a cultural activity. In A. Duranti (Ed.), A companion to linguistic
anthropology (pp. 169–188). Blackwell Publishing Ltd.

Kehoe, F. (2023). Leveraging generative ai tools for enhanced lesson planning in initial teacher education at post primary.
Irish Journal of Technology Enhanced Learning, 7(2), 172–182. doi:10.22554/ijtel.v7i2.124

Kelly, M. (Ed.). (2018). Languages after Brexit: How the UK speaks to the world. Springer International Publishing.

Kessler, G. (2017). Technology and the future of language teaching. Foreign Language Annals, 2018(51), 205–218.

Khan, I., Ahmad, A. R., Jabeur, N., & Mahdi, M. N. (2021). An artificial intelligence approach to monitor student
performance and devise preventive measures. Smart Learning Environments, 8(1), 17. Advance online publication.
doi:10.1186/s40561-021-00161-y

Kharb, L., & Singh, P. (2021). Role of machine learning in modern education and teaching. In Impact of AI Technologies
on Teaching, Learning, and Research in Higher Education (pp. 99–123). IGI Global. doi:10.4018/978-1-7998-4763-2.ch006

Kılıçkaya, F. (2020). Using a chatbot, Replika, to practice writing through conversations in L2 English: A case study.
In M. Kruk & M. Peterson (Eds.), New Technological Applications for Foreign and Second Language Learning and
Teaching (pp. 221–238). IGI Global. doi:10.4018/978-1-7998-2591-3.ch011

Kim, D.-E., Hong, C., & Kim, W. H. (2023). Efficient Transformer-based Knowledge Tracing for a Personalized Lan-
guage Education Application. Academic Press.

Kim, J. (2023). Leading teachers’ perspective on teacher-AI collaboration in education. Education and Information
Technologies. Advance online publication. doi:10.1007/s10639-023-12109-5

Kim, J., Lee, H., & Cho, Y. H. (2022). Learning design to support student-AI collaboration: Perspectives of leading teach-
ers for AI in education. Education and Information Technologies, 27(5), 6069–6104. doi:10.1007/s10639-021-10831-6

Kim, N.-Y., Cha, Y., & Kim, H.-S. (2019). Future English learning: Chatbots and artificial intelligence. Multimedia-
Assisted Language Learning, 22(3), 32–53.

King, I. (2016, July 29). E-learning is the way forward for quality education. South China Morning Post.

Kitamura, F. C. (2023). ChatGPT Is Shaping the future of medical writing but still requires human judgment. Radiology,
230171(2). Advance online publication. doi:10.1148/radiol.230171 PMID:36728749

Klimova, B. (2021). An insight into online foreign language learning and teaching in the era of COVID-19 pandemic.
Procedia Computer Science, 192, 1787–1794. doi:10.1016/j.procs.2021.08.183 PMID:34630743

Klímová, B., Pikhart, M., & Kacetl, J. (2023). Ethical issues of the use of AI-driven mobile apps for education. Frontiers
in Public Health, 10, 1118116. Advance online publication. doi:10.3389/fpubh.2022.1118116 PMID:36711343

357
Compilation of References

Knox, J. (2020). Artificial intelligence and education in China. Learning, Media and Technology, 45(3), 298–311. doi:
10.1080/17439884.2020.1754236

Koedinger, K. R., Corbett, A. T., & Perfetti, C. (2012). The Knowledge‐Learning‐Instruction framework: Bridging the
science‐practice chasm to enhance robust student learning. Cognitive Science, 36(5), 757–798. doi:10.1111/j.1551-
6709.2012.01245.x PMID:22486653

Kohnke, L. (2023). L2 Learners’ perception of a chatbot as a potential independent language learning tool. Int. J. Mobile
Learning and Organization, 17(1/2), 214–226. doi:10.1504/IJMLO.2023.128339

Kohnke, L., Moorhouse, B. L., & Zou, D. (2023). ChatGPT for language teaching and learning. RELC Journal, 54(2),
537–550. doi:10.1177/00336882231162868

Kolb, D. (1983). Experiential Learning: Experience as the Source of Learning and Development. Prentice Hall.

Kolovou, T. A. (2021). Recreating Cultural Immersion in an Online Environment. Journal of Teaching and Learning
with Technology, 10, 408–413.

König, J., Bremerich-Vos, A., Buchholtz, C., Fladung, I., & Glutsch, N. (2019). Pre–service teachers’ generic and subject-
specific lesson-planning skills: On learning adaptive teaching during initial teacher education. European Journal of
Teacher Education, 43(2), 131–150. doi:10.1080/02619768.2019.1679115

Koraishi, O. (2023). Teaching English in the age of AI: Embracing ChatGPT to optimize EFL materials and assessment.
Language Education and Technology, 3(1).

Korkmaz, G., & Toraman, Ç. (2020). Are we ready for the post-COVID-19 educational practice? An investigation into
what educators think as to online learning. International Journal of Technology in Education and Science, 4(4), 293–309.
doi:10.46328/ijtes.v4i4.110

Kormos, J. (2023). The role of cognitive factors in second language writing and writing to learn a second language.
Studies in Second Language Acquisition, 45(3), 622–646. doi:10.1017/S0272263122000481

Kostka, I., & Toncelli, R. (2023). Exploring applications of ChatGPT to English language teaching: Opportunities, chal-
lenges, and recommendations. TESL-EJ, 27(3). Advance online publication. doi:10.55593/ej.27107int

Krathwohl, D. R. (2002). A revision of Bloom’s taxonomy: An overview. Theory into Practice, 41(4), 212–218.
doi:10.1207/s15430421tip4104_2

Kuh, G. D. (2008). High-impact educational practices: What they are, who has access to them, and why they matter.
Washington, DC: Association of American Colleges and Universities.

Kuh, G. D., & O’Donnell, K. (2013). Ensuring Quality & Taking High-Impact Practices to Scale. Washington, DC:
Association of American Colleges and Universities.

Kuh, G., O’Donnell, K., & Schneider, C. (2017). HIPs at Ten. Change, 49(5), 8–16. doi:10.1080/00091383.2017.1366805

Kukulska-Hulme, A., Bossu, C., Charitonos, K., Coughlan, T., Deacon, A., Deane, N., Ferguson, R., Herodotou, C.,
Huang, C.-W., Mayisela, T., Rets, I., Sargent, J., Scanlon, E., Small, J., Walji, S., Weller, M., & Whitelock, D. (2023).
Innovating Pedagogy 2023: Open University Innovation Report 11. The Open University.

358
Compilation of References

Kuleto, V., Ilić, M. P., Bucea-Manea-Țoniş, R., Ciocodeică, D. F., Mihălcescu, H., & Mindrescu, V. (2022). The Attitudes
of K–12 Schools’ Teachers in Serbia towards the Potential of Artificial Intelligence. Sustainability (Basel), 14(14), 8636.
doi:10.3390/su14148636

Kurni, M., Mohammed, M. S., & Srinivasa, K. G. (2023). Natural language processing for education. In Springer eBooks
(pp. 45–54). doi:10.1007/978-3-031-32653-0_3

Kwon, S. K., Shin, D., & Lee, Y. (2023). The application of chatbot as an L2 writing practice tool. Language Learning
& Technology, 27(1), 1–19.

Lai, V. D., Ngo, N. T., Veyseh, A. P. B., Man, H., Dernoncourt, F., Bui, T., & Nguyen, T. H. (2023). ChatGPT Beyond
English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning. /arxiv.2304.05613
doi:10.18653/v1/2023.findings-emnlp.878

Lai, Y., Saab, N., & Admiraal, W. (2022). University students’ use of mobile technology in self-directed language
learning: Using the integrative model of behavior prediction. Computers & Education, 179, 104413. doi:10.1016/j.
compedu.2021.104413

Lakkala, M., Toom, A., Kangasharju, A., & Ilom, L. (2022). Computers and Education : Artificial Intelligence Lower
secondary students ’ poetry writing with the AI-based Poetry Machine. doi:10.1016/j.caeai.2022.100048

Lameras, P., & Arnab, S. (2021). Power to the teachers: An exploratory review on artificial intelligence in education.
Information (Basel), 13(1), 14. doi:10.3390/info13010014

Langran, E., Searson, M., Knezek, G., & Christensen, R. (2020, April). AI in teacher education. In Society for Informa-
tion Technology & Teacher Education International Conference (pp. 751-756). Association for the Advancement of
Computing in Education (AACE).

Larsen-Freeman, D., & DeCarrico, J. (2019). Grammar. In An introduction to applied linguistics (pp. 19–34). Routledge.
doi:10.4324/9780429424465-2

Last, R. W. (1989). Artificial intelligence techniques in language learning. Halsted Press.

Leavy, S., Meaney, G., Wade, K., & Greene, D. (2020). Mitigating gender bias in machine learning data sets. Bias and
Social Aspects in Search and Recommendation: First International Workshop, BIAS 2020, Lisbon, Portugal, April 14.
Proceedings, 1, 12–26.

Lee, E., Lee, Y., Kye, B., & Ko, B. (2008). Elementary and middle school teachers’, students’, and parents’ perception
of robot-aided education in Korea. In EdMedia+ Innovate Learning (pp. 175-183). Association for the Advancement of
Computing in Education (AACE).

Lee, D., Kim, H., & Sung, S. (2022). Development research on an AI English learning support system to facilitate learner-
generated-context-based learning. Educational Technology Research and Development, 71(2), 629–666. doi:10.1007/
s11423-022-10172-2 PMID:36533222

Lee, H., Ahn, H., Nguyen, T. G., Choi, S. M., & Kim, D. J. (2017). Comparing the Self-Report and Measured Smart-
phone Usage of College Students: A Pilot Study. Psychiatry Investigation, 14(2), 198–204. doi:10.4306/pi.2017.14.2.198
PMID:28326119

Lee, I., & Perret, B. (2022). Preparing high school teachers to integrate AI methods into STEM classrooms. Proceedings
of the AAAI Conference on Artificial Intelligence, 36(11), 12783–12791. doi:10.1609/aaai.v36i11.21557

Lee, N. T. (2018). Detecting racial bias in algorithms and machine learning. Journal of Information. Communication
and Ethics in Society, 16(3), 252–260. doi:10.1108/JICES-06-2018-0056

359
Compilation of References

Lee, S. L. (2011). 高班閱讀課的網上課件 [Online components for advanced Chinese reading classes]. Journal of
Technology and Chinese Language Teaching, 2, 1–22.

Lee, S. L. (2016). E-Learning Readiness in Language Learning: Students’ Readiness Survey and Normalization Process.
Journal of Technology and Chinese Language Teaching, 7(2), 23–37.

Lee, S. L. (2018). Modular approaches in eLearning design. Journal of Technology and Chinese Language Teaching,
9, 48–61.

Lee, S. L. (2022). Synchronous online language teaching: a reflection from Hong Kong. In S. Liu (Ed.), Teaching the
Chinese language remotely: Global cases and perspectives (pp. 235–251). Palgrave Macmillan. doi:10.1007/978-3-
030-87055-3_10

Leow, R. P. (2019). ISLA: How implicit or how explicit should it be? Theoretical, empirical, and pedagogical/curricular
issues. Language Teaching Research, 23(4), 476–493. doi:10.1177/1362168818776674

Lew, R. (2004). Which dictionary for whom? Receptive use of bilingual, monolingual and semi-bilingual dictionaries
by Polish learners of English. Robert Lew.

Liang, W., Yuksekgonul, M., Mao, Y., Wu, E., & Zou, J. (2023). GPT detectors are biased against non-native English
writers. A Cell Press Journal, 4(7). doi:10.1016/j.patter.2023.100779

Li, B., Bonk, C. J., & Kou, X. (2023). Exploring the multilingual applications of ChatGPT: Uncovering language learning
affordances in YouTuber videos. International Journal of Computer-Assisted Language Learning and Teaching, 13(1),
1–22. Advance online publication. doi:10.4018/IJCALLT.326135

Lidén, A., & Nilros, K. (2020). Perceived benefits and limitations of chatbots in higher education (Dissertation). Retrieved
from https://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-96327

Limna, P., Kraiwanit, T., Jangjarat, K., Klayklung, P., & Chocksathaporn, P. (2023). The use of ChatGPT in the digital
era: Perspectives on chatbot implementation. Journal of Applied Learning and Teaching, 6(1).

Lim, W. M., Gunasekara, A., Pallant, J. L., Pallant, J. I., & Pechenkina, E. (2023). Generative AI and the future of
education: Ragnarök or reformation? A paradoxical perspective from management educators. International Journal of
Management Education, 21(2), 100790. doi:10.1016/j.ijme.2023.100790

Lin, Z., Zhang, D., Tao, Q., Shi, D., Haffari, G., Wu, Q., He, M., & Ge, Z. (2023). Medical visual question answering: A
survey. Artificial Intelligence in Medicine, 143, 102611. Advance online publication. doi:10.1016/j.artmed.2023.102611
PMID:37673579

Li, P., & Yu, L. (2021). Digital Language Learning (DLL): Insights from behavior, cognition, and the brain. Bilingual-
ism: Language and Cognition, 25(3), 361–378. doi:10.1017/S1366728921000353 PMID:35669733

Li, R. (2020). Using artificial intelligence in learning English as a foreign language: An examination of IELTS Liulishuo as
an online platform. Journal of Higher Education Research, 1(2). Advance online publication. doi:10.32629/jher.v1i2.178

Li, S. (2010). The effectiveness of corrective feedback in SLA: A meta‐analysis. Language Learning, 60(2), 309–365.
doi:10.1111/j.1467-9922.2010.00561.x

Liu, O., & Yau, C. (2023, March 22). Who needs a teacher? As ChatGPT takes off in Hong Kong, educationists worry
about impact on teaching, learning. South China Morning Post.

360
Compilation of References

Liu, G., & Ma, C. (2023). Measuring EFL learners’ use of ChatGPT in informal digital learning of English based on
the technology acceptance model. Innovation in Language Learning and Teaching, 0(0), 1–14. doi:10.1080/17501229
.2023.2240316

Liu, Y., & Quan, Q. (2022). AI recognition method of pronunciation errors in oral English speech with the help of big
data for personalized learning. Journal of Information & Knowledge Management, 21(Supp02), 2240028. doi:10.1142/
S0219649222400287

Li, W., Zhang, H., Zhang, C., Luo, J., Wang, H., Wang, H., Zhu, Y., Cui, H., Wang, J., Li, H., Zhu, Z., Xu, Y., & Li,
C. (2021). The Prevalence of Psychological Status During the COVID-19 Epidemic in China: A Systemic Review and
Meta-Analysis. Frontiers in Psychology, 12, 614964. Advance online publication. doi:10.3389/fpsyg.2021.614964
PMID:34017278

Li, X., Li, B., & Cho, S. J. (2023). Empowering Chinese language learners from low-income families to improve their
Chinese writing with ChatGPT’s assistance afterschool. Languages (Basel, Switzerland), 8(4), 238. doi:10.3390/lan-
guages8040238

Lobel, O. (2022). The equality machine: Harnessing digital technology for a brighter, more inclusive future. Hachette UK.

Lochtman, K. (2002). Oral corrective feedback in the foreign language classroom: How it affects interaction in analytic
foreign language teaching. International Journal of Educational Research, 37(3–4), 271–283. doi:10.1016/S0883-
0355(03)00005-3

Loder, C., Minadeo, L., Jiménez, L. E. C., Luna, Z., Ross, L. J., Rosenbloom, N., Stalburg, C. M., & Harris, L. H. (2019).
Bridging the expertise of advocates and academics to identify reproductive justice learning outcomes. Teaching and
Learning in Medicine, 32(1), 11–22. doi:10.1080/10401334.2019.1631168 PMID:31293184

Loewen, S. (2018). Focus on form versus focus on forms. In J. I. Liontas (Ed.), The TESOL encyclopedia of English
language teaching (pp. 1–6). doi:10.1002/9781118784235.eelt0062

Loewen, S., Li, S., Fei, F., Thompson, A., Nakatsukasa, K., Ahn, S., & Chen, X. (2009). Second language learners’
beliefs about grammar instruction and error correction. Modern Language Journal, 93(1), 91–104. doi:10.1111/j.1540-
4781.2009.00830.x

Lowe, R., & Leike, J. (2022). Aligning language models to follow instructions. OpenAI. https://openai.com/research/
instruction-following

Lu, X. (2018). Natural Language processing and intelligent computer‐assisted language learning (ICALL). The TESOL
encyclopedia of English language teaching, 1-6. doi:10.1002/9781118784235.eelt0422

Luan, H., Geczy, P., Lai, H., Gobert, J., Yang, S. J., Ogata, H., Baltes, J., Guerra, R., Li, P., & Tsai, C. C. (2020). Chal-
lenges and future directions of big data and artificial intelligence in education. Frontiers in Psychology, 11, 580820.
doi:10.3389/fpsyg.2020.580820 PMID:33192896

Luckin, R., Holmes, W., Griffiths, M., & Forcier, L. B. (2016). Intelligence unleashed: An argument for AI in education.
Pearson Education.

Lusin, N., Peterson, T., Sulewski, C., & Zafer, R. (2023). Enrollments in languages other than English in US institu-
tions of higher education: Fall 2021. Modern Language Association of America. Retrieved from: https://www.mla.org/
content/download/191324/file/Enrollments-in-Languages-Other-Than-English-in-US-Institutions-of-Higher-Education-
Fall-2021.pdf

361
Compilation of References

Lys, F. (2013a). Computer-mediated grammar teaching and its effect on different language tasks. In P. Hubbard, M.
Schulze, & B. Smith (Eds.), Learner-computer interaction in language education: CALICO Journal: A Festschrift in
Honor of Robert Fischer (Vol. 30, pp. 166–186). Academic Press.

Lys, F. (2013b). The development of advanced learner oral proficiency using iPads. Language Learning & Technology,
17(3), 94–116.

Machwate, S., Bendaoud, R., Henze, J., Berrada, K., & Burgos, D. (2021). Virtual exchange to develop cultural, language,
and digital competencies. Sustainability (Basel), 13(11), 5926. doi:10.3390/su13115926

Mackenzie, D. (2023). Surprising Advances in Generative Artificial Intelligence Prompt Amazement — And Worries.
Engineering (Beijing), xxxx, 4–6. doi:10.1016/j.eng.2023.04.004

Mageira, K., Pittou, D., Papasalouros, A., Kotis, K., Zangogianni, P., & Daradoumis, A. (2022). Educational AI chatbots
for content and language integrated learning. Applied Sciences (Basel, Switzerland), 12(7), 3239. doi:10.3390/app12073239

Malik, G., Tayal, D. K., & Vij, S. (2019). An analysis of the role of artificial intelligence in education and teaching. In
Recent Findings in Intelligent Computing Techniques: Proceedings of the 5th ICACNI 2017, Volume 1 (pp. 407-417).
Springer Singapore. 10.1007/978-981-10-8639-7_42

Manyika, J., Lund, S., Chui, M., Bughin, J., Woetzel, J., Batra, P., Ko, R., & Sanghvi, S. (2017, December). Jobs lost,
jobs gained: Workforce transitions in a time of automation. McKinsey Global Institute.

Maria, G., Sousa, B. De, Cardoso, L., & Toassi, P. (2018). Duolingo As a Tool to Improve Vocabulary Writing in English
as a No Inglês Como Língua Estrangeira. Academic Press.

Marzuki, W., Widiati, U., Rusdin, D., Darwin, & Indrawati, I. (2023). The impact of AI writing tools on the content
and organization of students’ writing: EFL teachers’ perspective. Cogent Education, 10(2), 2236469. Advance online
publication. doi:10.1080/2331186X.2023.2236469

McGee, R. W. (2023). Is Chat Gpt biased against conservatives? An empirical study. SSRN Electron. J. doi:10.2139/
ssrn.4359405

McGill Library. (2023). AI Literacy Guide. https://libraryguides.mcgill.ca/ai/literacy

Meng, N., Dhimolea, T. K., & Ali, Z. (2022). AI-enhanced education: Teaching and learning reimagined. In Educational
Communications and Technology (pp. 107–124). Issues and Innovations. doi:10.1007/978-3-030-84729-6_7

Merrill, M. D. (2002). First principles of instruction. Educational Technology Research and Development, 50(3), 43–59.
doi:10.1007/BF02505024

Meyer, J. G., Urbanowicz, R. J., Martin, P. C. N., O’Connor, K., Li, R., Peng, P.-C., Bright, T. J., Tatonetti, N., Won, K.
J., Gonzalez-Hernandez, G., & Moore, J. H. (2023). ChatGPT and large language models in academia: Opportunities and
challenges. BioData Mining, 16(20), 20. Advance online publication. doi:10.1186/s13040-023-00339-9 PMID:37443040

Miller, T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267,
1–38. doi:10.1016/j.artint.2018.07.007

Mills, A., Bali, M., & Eaton, L. (2023). How do we respond to generative AI in education? Open educational practices
give us a framework for an ongoing process. Journal of Applied Learning and Teaching, 6(1), 16–30. doi:10.37074/
jalt.2023.6.1.34

362
Compilation of References

Ministry of National Education. (2018). Ortaöğretim İngilizce dersi (9, 10, 11 ve 12. sınıflar) öğretim programı [Secondary
school English course (grades 9, 10, 11 and 12) curriculum]. http://mufredat.meb.gov.tr/ProgramDetay.aspx?PID=342

Misiejuk, K., Ness, I. J., Gray, R. M., & Wasson, B. (2023). Changes in Online Course Designs: Before, During, and
After the Pandemic. Frontiers in Education, 7, 996006. Advance online publication. doi:10.3389/feduc.2022.996006

Mittal, A. (2023, July 26). The essential guide to prompt engineering in ChatGPT [Blog post] Retrieved from https://
www.unite.ai/prompt-engineering-in-chatgpt/

Modern Language Association. (2007). Foreign languages and higher education: New structures for a changed world.
https://www.mla.org/Resources/Guidelines-and-Data/Reports-and-Professional-Guidelines/Foreign-Languages-and-
Higher-Education-New-Structures-for-a-Changed-World

Moeller, A., & Catalano, T. (2015). Foreign language teaching and learning. In J. D. Wright (Ed.), International Encyclopedia
of the Social & Behavioral Sciences (2nd ed., Vol. 9, pp. 327–332). Elsevier. doi:10.1016/B978-0-08-097086-8.92082-8

Mohamed, A. M. (2023). Exploring the potential of an AI-based Chatbot (ChatGPT) in enhancing English as a foreign
language (EFL) teaching: Perceptions of EFL faculty members. Education and Information Technologies. Advance
online publication. doi:10.1007/s10639-023-11917-z

Mohan, D. D., Jawade, B., Setlur, S., & Govindaraju, V. (2023) Chapter 4 - Deep metric learning for computer vision:
A brief overview. Handbook of Statistics, 48, 59–79. doi:10.1016/bs.host.2023.01.003

Montrul, S., and Slabakova, R. (2003). Competence similarities between Native and Near-Native speakers: An investiga-
tion of the Preterit/Imperfect contrast in Spanish. Studies in Second Language Acquisition, 25, 351–398. doi:10.1017/
S0272263103000159

Moorhouse, B. L., Wong, K. M., & Li, L. (2023). Teaching with Technology in the Post-Pandemic Digital Age: Techno-
logical Normalisation and AI-Induced Disruptions. RELC Journal, 54(2), 311–320. doi:10.1177/00336882231176929

Moser, K. M., Wei, T., & Brenner, D. (2021). Remote teaching during COVID-19: Implications from a national survey
of language educators. System, 97, 102431. doi:10.1016/j.system.2020.102431

Nagata, N. (1996). Computer vs. workbook instruction in second language acquisition. CALICO Journal, 53–75.

Nash, B. L., Hicks, T., Garcia, M., Fassbender, W., Alvermann, D., Boutelier, S., McBride, C., McGrail, E., Moran, C.,
O’Byrne, I., Piotrowski, A., Rice, M., & Young, C. (2023). Artificial Intelligence in English education: Challenges and
opportunities for teachers and teacher educators. English Education, 55(3), 201–206.

Nazaretsky, T., Ariely, M., Cukurova, M., & Alexandron, G. (2022). Teachers’ trust in AI‐powered educational technol-
ogy and a professional development program to improve it. British Journal of Educational Technology, 53(4), 914–931.
doi:10.1111/bjet.13232

Nazari, N., Shabbir, M. S., & Setiawan, R. (2021). Application of Artificial Intelligence powered digital writing assistant in
higher education: Randomized controlled trial. Heliyon, 7(5), e07014. doi:10.1016/j.heliyon.2021.e07014 PMID:34027198

Ng, D.T.K., Luo, W., Chan, H.M.Y., & Chu, S.K.W. (2022). Using digital story writing as a pedagogy to develop AI
literacy among primary students. Computers and Education: Artificial Intelligence, 100054.

Ng, D. T. K., Lee, M., Tan, R. J. Y., Downie, J. S., & Chu, S. K. W. (2023). A review of AI teaching and learning from
2000 to 2020. Education and Information Technologies, 2023(28), 8445–8501. doi:10.1007/s10639-022-11491-w

363
Compilation of References

Ng, D. T. K., Leung, J. K. L., Chu, S. K. W., & Qiao, M. S. (2021). Conceptualizing AI literacy: An exploratory review.
Computers and Education: Artificial Intelligence, 2, 100041.

Nguyen, A., Ngo, H. N., Hong, Y., Dang, B., & Nguyen, B. T. (2022). Ethical principles for artificial intelligence in edu-
cation. Education and Information Technologies, 28(4), 4221–4241. doi:10.1007/s10639-022-11316-w PMID:36254344

Niepel, C., Burrus, J., Greiff, S., Lipnevich, A. A., Brenneman, M. W., & Roberts, R. D. (2018). Students’ beliefs and
attitudes toward mathematics across time: A longitudinal examination of the theory of planned behavior. Learning and
Individual Differences, 63(June), 24–33. doi:10.1016/j.lindif.2018.02.010

Nikitina, L. (2011). Creating an authentic learning environment in the foreign language classroom. International Journal
of Instruction, 4(1).

Noda, M. (2007). Performed culture: Cataloguing culture gains during study abroad. Japanese Language and Literature,
41(2), 297–314.

Nunes, A., Cordeiro, C., Limpo, T., & Castro, S. L. (2021). Effectiveness of automated writing evaluation systems
in school settings: A systematic review of studies from 2000 to 2020. Journal of Computer Assisted Learning, 38(2),
599–620. doi:10.1111/jcal.12635

O’Brien, P. (1993). eL: AI in CALL. In M. Yazdani (Ed.), Multilingual multimedia. Bridging the language barrier with
intelligent systems (pp. 85–139). Intellect.

O’Malley, J. M., Chamot, A. U., & Küpper, L. (1989). Listening comprehension strategies in second language acquisi-
tion. Applied Linguistics, 10(4), 418–437. doi:10.1093/applin/10.4.418

Okada, A., Whitelock, D., Holmes, W., & Edwards, C. (2019). e‐Authentication for online assessment: A mixed‐method
study. British Journal of Educational Technology, 50(2), 861–875. doi:10.1111/bjet.12608

Open, A. I. (2023b). ChatGPT - Release Notes. OpenAI. https://help.openai.com/en/articles/6825453-chatgpt-release-notes

OpenA. I. (2023a). ChatGPT. https://chat.openai.com/c/02af3cf9-1598-4fa1-882b-f543a27b21cc

Paas, F., & Van Merriënboer, J. J. G. (2020). Cognitive-load theory: Methods to manage working memory load in the
learning of complex tasks. Current Directions in Psychological Science, 29(4), 394–398. doi:10.1177/0963721420922183

Pace-Sigge, M., & Sumakul, D. T. (2021). What teaching an algorithm teaches when teaching students how to write
academic texts. Linguistic, Educational and Intercultural Research 2021 (LEIC Research 2021), 78.

Pack, A., & Maloney, J. (2023). Using generative artificial intelligence for language education research: Insights from
using OpenAI’s ChatGPT. TESOL Quarterly, 57(4), 1571–1582. doi:10.1002/tesq.3253

Palermo, C., & Wilson, J. (2020). Implementing automated writing evaluation in different instructional contexts: A
mixed-methods study. Journal of Writing Research, 12(1), 63–108. doi:10.17239/jowr-2020.12.01.04

Paltridge, B. (2018). Graduate student writing. In D. Belcher & A. Hirvela (Eds.), The TESOL Encyclopedia of English
Language Teaching (pp. 1–6). Wiley Blackwell. doi:10.1002/9781118784235.eelt0516

Paribakht, T. S., & Wesche, M. (1997). Vocabulary enhancement activities and reading for meaning in second language
vocabulary acquisition. Second Language Vocabulary Acquisition: A Rationale for Pedagogy, 55(4), 174–200.

364
Compilation of References

Paschal, M. J., & Melly, I. K. (2023). Ethical Guidelines on the Use of AI in Education. In Creative AI Tools and Ethical
Implications in Teaching and Learning (pp. 230–245). IGI Global. doi:10.4018/979-8-3693-0205-7.ch013

Pasden, J. (2023). Using ChatGPT to learn Chinese [Blog post]. Retrieved from https://www.sinosplice.com/life/ar-
chives/2023/02/03/using-chatgpt-to-learn-chinese

Pawlak, M. (2021). Implicit versus explicit grammar learning and teaching. In E. Macaro & R. Woore (Eds.), Debates
in second language education (1st ed., pp. 165–182). Routledge., doi:10.4324/9781003008361-12

Pedró, F., Subosa, M., Rivas, A., & Valverde, P. (2019). Artificial Intelligence and Language Learning: Opportunities
and Challenges. Working Paper on Language Policy. UNESCO. Retrieved from https://unesdoc.unesco.org/ark:/ 48223/
pf0000366994

Pedró, F., Subosa, M., Rivas, A., & Valverde, P. (2019). Artificial intelligence in education: Challenges and opportuni-
ties for sustainable development. UNESCO.

Pérez-Núñez, A. (2023). Exploring the Potential of Generative AI (ChatGPT) for Foreign Language Instruction: Ap-
plications and Challenges. Hispania, 106(3), 355–362. doi:10.1353/hpn.2023.a906568

Pike, K. L. (1967). Language in relation to a unified theory of the structure of human behavior (2nd, revised edition).
Mouton & Co., Publishers.

Pikhart, M. (2020). Intelligent information processing for language education: The use of artificial intelligence in lan-
guage learning apps. Procedia Computer Science, 176, 1412–1419. doi:10.1016/j.procs.2020.09.151 PMID:33042299

Piotrowska, M., Czyżewski, A., Ciszewski, T., Korvel, G., Kurowski, A., & Kostek, B. (2021). Evaluation of aspiration
problems in L2 English pronunciation employing machine learning. The Journal of the Acoustical Society of America,
150(1), 120–132. doi:10.1121/10.0005480 PMID:34340465

Pokrivčáková, S. (2019). Preparing teachers for the application of ai-powered technologies in foreign language education.
Journal of Language and Cultural Education, 7(3), 135–153. doi:10.2478/jolace-2019-0025

Polisca, E., Wright, V., Álvarez, I., & Montoro, C. (2019). Language Provision in UK Modern Foreign Languages De-
partments 2019 Survey. University Council of Modern Languages.

Pouresmaeil, A., & Vali, M. (2023). The effects of incidental focus on form on learning vocabulary, grammar, and pro-
nunciation. Language Teaching Research, 0, 1–24. doi:10.1177/13621688231185419

Prasad, B. N., & Jaheer, B. (2023). The Use of AI (artificial Intelligence) in English Learning Among Engineering Students:
A Case Study. International Journal of English Learning & Teaching Skills, 5(4), 3500–3508. doi:10.15864/ijelts.5410

Pratama, M. P., Sampelolo, R., & Lura, H. (2023). Revolutionizing education: Harnessing the power of artificial intel-
ligence for personalized learning. Klasikal: Journal of Education, Language Teaching and Science, 5(2), 350–357.
doi:10.52208/klasikal.v5i2.877

Preis, R., Bećirović, S., & Geyer, B. (2023). EFL Teaching in a Digital Environment. Map Education and Humanities.
doi:10.53880/2744-2373.2023.3.1.56

Preussler, O., Preussler-Bitch, S., & Napp, D. (2017). Die kleine Hexe: Ausflug mit Abraxas. Thienemann Verlag.

Pujiani, T., Sukmawati, I. D., & Indrasari, N. (2022). Teachers’ Readiness Toward the New Paradigm of English Lan-
guage Teaching: A Narrative Inquiry. Uc Journal Elt Linguistics and Literature Journal. doi:10.24071/uc.v3i2.5363

Puspitasari, E., & Tsara, E. (2022). Learning Tools for EFL Writing: What and How based on Upper Secondary School
Students’ Perspectives. VELES: Voices of English Language Education Society, 6(2), 488–499. doi:10.29408/veles.v6i2.5878

365
Compilation of References

Qadir, J. (2022). Engineering Education in the Era of ChatGPT: Promise and Pitfalls of Generative AI for Education.
TechRxiv xiv. 21789 434. v1 doi:10. 36227/ techr

Qin, F., Li, K., & Yan, J. (2020). Understanding user trust in artificial intelligence‐based educational systems: Evidence
from China. British Journal of Educational Technology, 51(5), 1693–1710. doi:10.1111/bjet.12994

Radić, N., Atabekova, A., Freddi, M., & Schmied, J. (2021). The world universities’ response to COVID-19: Remote
online language teaching. Research-publishing. net.

Ramirez-Anormaliza, R., Sabaté, F., & Guevara-Viejo, F. (2015). Evaluating Student Acceptance Level of E-Learning
Systems. 8th Annual International Conference of Education, Research and Innovation, 2393–2399. https://library.iated.
org/view/RAMIREZANORMALIZA2015EVA

Ramsay, V. (1990). Developmental stages in the acquisition of the perfective and the imperfective aspects by classroom
L2 learners of Spanish [Tesis doctoral]. University of Oregon, Eugene.

Ranalli, J. (2021). L2 student engagement with automated feedback on writing: Potential for learning and issues of trust.
Journal of Second Language Writing, 52, 100816. doi:10.1016/j.jslw.2021.100816

Ray, P. P. (2023). ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations
and future scope. Internet of Things and Cyber-Physical Systems, 3(March), 121–154. doi:10.1016/j.iotcps.2023.04.003

Rebolledo Font De La Vall, R., & González Araya, F. (2023). Exploring the benefits and challenges of AI-language
learning tools. International Journal of Social Sciences and Humanities Invention, 10(01), 7569–7576. doi:10.18535/
ijsshi/v10i01.02

Reichelt, M., Lefkowitz, N., Rinnert, C., & Schultz, J. M. (2012). Key issues in foreign language writing. Foreign Lan-
guage Annals, 45(1), 22–41. doi:10.1111/j.1944-9720.2012.01166.x

Reid, J. (2006). “Eye” learners and “ear” learners: Identifying the language needs of international student and US resident
writers. In P. K. Matsuda, M. Cox, J. Jordan, & C. Ortmeier-Hooper (Eds.), Second-language writing in the composition
classroom: A critical sourcebook (pp. 76–88). St. Martin’s.

Reigeluth, C. M., & An, Y. (2019). Merging the instructional design process with learner-centered theory: The holistic
4d model. Taylor & Francis Group.

Reiss, M. J. (2021). The use of AI in education: Practicalities and ethical considerations. London Review of Education,
19(1). doi:10.14324/LRE.19.1.05

Republic of Türkiye Ministry of National Education. (2018). English Curriculum for Primary and Secondary Schools.
Retrieved from: https://mufredat.meb.gov.tr/Dosyalar/201812411191321-%C4%B0NG%C4%B0L%C4%B0ZCE%20
%C3%96%C4%9ERET%C4%B0M%20PROGRAMI%20Klas%C3%B6r%C3%BC.pdf

Rettberg, J. W. (2022, December 6). ChatGPT is multilingual but monocultural, and it’s learning your values [Blog post].
https://jilltxt.net/right-now-chatgpt-is-multilingual-but-monocultural-but-its-learning-your-values/

Richardson, M., & Clesham, R. (2021). Rise of the machines? The evolving role of Artificial Intelligence (AI) technolo-
gies in high stakes assessment. London Review of Education, 19(1), 1–13. doi:10.14324/LRE.19.1.09

366
Compilation of References

Roche, C., Wall, P. J., & Lewis, D. (2022). Ethics and diversity in artificial intelligence policies, strategies and initiatives.
AI and Ethics, 3(4), 1095–1115. doi:10.1007/s43681-022-00218-9 PMID:36246014

Roe, J., Renandya, W. A., & Jacobs, G. M. (2023). A review of AI-powered writing tools and their implications for academic
integrity in the language classroom. Journal of English and Applied Linguistics, 2(1), 22–30. doi:10.59588/2961-3094.1035

Rojo, G. (1990). Relaciones entre temporalidad y aspecto en el verbo español. Tiempo y aspecto en español. Cátedra.

Roll, I., & Wylie, R. (2016). Evolution and revolution in artificial intelligence in education. International Journal of
Artificial Intelligence in Education, 26(2), 582–599. doi:10.1007/s40593-016-0110-3

Roschelle, J., Lester, J., & Fusco, J. (Eds.). (2020). AI and the future of learning: Expert panel report [Report]. Digital
Promise. https://circls.org/reports/ai-report

Roumeliotis, K. I., & Tselikas, N. D. (2023). ChatGPT and open-AI models: A preliminary review. Future Internet,
15(6), 192. doi:10.3390/fi15060192

Rudolph, J., Tan, S., & Tan, S. (2023). ChatGPT: Bullshit spewer or the end of traditional assessments in higher educa-
tion? Journal of Applied Learning & Teaching, 6(1), 342–363.

Rudolph, J., Tan, S., & Tan, S. (2023). ChatGPT: Bullshit spewer or the end of traditional assessments in higher educa-
tion? Journal of Applied Learning and Teaching, 6(1).

Rundell, K. (2023, July 11). Why adults should read children’s books. https://www.bbc.com/culture/article/20230711-
why-adults-should-read-childrens-books?mibextid=Zxz2cZ

Rundell, K. (2019). Why you should read children’s books, even though you are so old and wise. Bloomsbury Publishing.

Ryan, J., & Viete, R. (2009). Respectful interactions: Learning with international students in the English-speaking
academy. Teaching in Higher Education, 14(3), 303–314. doi:10.1080/13562510902898866

Sabuncuoglu, A. (2020). Designing one year curriculum to teach artificial intelligence for middle school. In Proceedings
of the 2020 ACM Conference on Innovation and Technology in Computer Science Education (ITiCSE ’20). Association
for Computing Machinery. 10.1145/3341525.3387364

Sahami, M. (1999). Using machine learning to improve information access. Stanford University.

Salaberry, M. R. (1996). A theoretical foundation for the development of pedagogical tasks in computer-mediated com-
munication. CALICO Journal, 14(1), 5–34. doi:10.1558/cj.v14i1.5-34

Salaberry, M. R. (1997). The development of past tense verbal morphology in L2 Spanish classroom instruction. Cornell
University.

Salas‐Pilco, S. Z., Xiao, K., & Hu, X. (2022). Artificial intelligence and learning analytics in teacher education: A sys-
tematic review. Education Sciences, 12(8), 569. doi:10.3390/educsci12080569

Samea Qoura, A., & Moustafa Elmansi, H. (2023). Artificial intelligence in language education: Implementations and
policies required [Conference presentation]. The first national conference for the educational studies sector. 10.21608/
foej.2022.180319.1169

Samochowiec, J. (2020). Future skills: Four scenarios for the world of tomorrow. Jacobs Foundation. doi:10.59986/
WGTT6117

Sari, S. N., & Aminatun, D. (2021). Students’ perception on the use of English movies to improve vocabulary mastery.
Journal of English Language Teaching and Learning, 2(1), 16–22. doi:10.33365/jeltl.v2i1.757

367
Compilation of References

Schieffelin, B. B., & Ochs, E. (Eds.) (1986). Language socialization across cultures: Studies in the social and cultural
foundations of language. Cambridge University Press.

Schiff, D. (2021) Out of the laboratory and into the classroom: the future of artificial intelligence in education. AI &
Soc, 331–348. doi:10.1007/s00146-020-01033-8

Schmidt, R. (2010). Attention, awareness, and individual differences in language learning. In Handbook of language
teaching (pp. 27-63). Academic Press.

Schmidt, R. (1994). Implicit learning and the cognitive unconscious: Of artificial grammars and SLA. Second Language
Research, 10(2), 93–119.

Schmidt, T., & Strasser, T. (2022). Artificial Intelligence in Foreign Language Learning and Teaching: A CALL for
Intelligent Practice. Anglistik: International Journal of English Studies, 33(1), 165–184. doi:10.33675/ANGL/2022/1/14

Schreiber-Wicke, E., & Holland, C. (2017). Zwei Papas für Tango. Thienemann Verlag.

Schuengel, C., & van Heerden, A. (2023). Editorial: Generative artificial intelligence and the ecology of human develop-
ment. Journal of Child Psychology and Psychiatry, and Allied Disciplines, 64(9), 1261–1263. doi:10.1111/jcpp.13860
PMID:37528517

Schulhoff, S., Khan, A., & Yanni, F. (2023). Your guide to communicating with artificial intelligence. Retrieved from
https://learnprompting.org/

Scottish Government. (2016). Children, Education and Skills. Attitudes Towards Language Learning in Schools in Scot-
land. Social Research. Cabinet Secretary for Education and Skills. Learning Directorate, Education.

Scottish Government. (2020). 1+2 Languages Implementation Findings from the 2019 local authority survey. Cabinet
Secretary for Education and Skills. Learning Directorate, Education.

Scottish Government. (2022). 1+2 languages policy - local authority survey 2021: findings. Cabinet Secretary for Edu-
cation and Skills. Learning Directorate, Education.

Scottish Qualifications Authority. (2014). National 3 English Course Specification [C72473]. Retrieved from: https://
www.sqa.org.uk/files/nq/CfE_CourseSpec_N3_Languages_English.pdf

Sebesta, J., & Davis, V. L. (2023, June 30). Supporting instruction and learning through Artificial Intelligence: A survey
of institutional practices & policies. WICHE Cooperative for Educational Technologies. https://wcet.wiche.edu/resources/
wcetreport-supporting-instruction-learning-through-artificial-intelligence-a-survey-ofinstitutional-practices-policies

Seedhouse, P. (2004). The organization of turn taking and sequence in language classrooms. Language Learning: A
Journal of Research in Language Studies.

Seemiller, C., & Grace, M. (2019). Generation Z: A century in the making. Routledge.

Self, J. (1998). The defining characteristics of intelligent tutoring systems research: ITSs care, precisely. International
Journal of Artificial Intelligence in Education, 10, 350–364.

Sellar, S., & Gulson, K. N. (2021). Becoming information centric: The emergence of new cognitive infrastructures in
education policy. Journal of Education Policy, 36(3), 309–326. doi:10.1080/02680939.2019.1678766

Selwyn, N. (2019). Should robots replace teachers? AI and the future of education. John Wiley & Sons.

Selwyn, N. (2019). Should robots replace teachers?: AI and the future of education. John Wiley & Sons.

368
Compilation of References

Selwyn, N. (2019). What’s the problem with learning analytics? Journal of Learning Analytics, 6(3), 11–19. doi:10.18608/
jla.2019.63.3

Selwyn, N., & Gasevic, D. (2020). The datafication of higher education: Discussing the promises and problems. Teach-
ing in Higher Education, 25(4), 527–540. doi:10.1080/13562517.2019.1689388

Seo, K., Tang, J., Roll, I., Fels, S., & Yoon, D. (2021). The impact of artificial intelligence on learner–instructor interac-
tion in online learning. International Journal of Educational Technology in Higher Education, 18(1), 54. Advance online
publication. doi:10.1186/s41239-021-00292-9 PMID:34778540

Shadiev, R., Liu, T., & Hwang, W. (2020). Review of research on mobile‐assisted language learning in familiar, authentic
environments. British Journal of Educational Technology, 51(3), 709–720. doi:10.1111/bjet.12839

Shadiev, R., & Yang, M. (2020). Review of studies on technology-enhanced language learning and teaching. Sustain-
ability (Basel), 12(2), 524. doi:10.3390/su12020524

Shaikh, S., Yayilgan, S. Y., Klimova, B., & Pikhart, M. (2023). Assessing the usability of ChatGPT for formal Eng-
lish language learning. European Journal of Investigation in Health, Psychology and Education, 13(9), 1937–1960.
doi:10.3390/ejihpe13090140 PMID:37754479

Shortt, M., Tilak, S., Kuznetcova, I., Martens, B., & Akinkuolie, B. (2023). Gamification in mobile-assisted language
learning: A systematic review of Duolingo literature from public release of 2012 to early 2020. Computer Assisted
Language Learning, 36(3), 517–554. doi:10.1080/09588221.2021.1933540

Shumin, K. (2002). Factors to consider: Developing adult EFL students’ speaking abilities. Methodology in Language
Teaching: An Anthology of Current Practice, 12(35), 204–211. doi:10.1017/CBO9780511667190.028

Singer, N. (2023). Ban or embrace? Colleges wrestle with A.I.-generated admissions essays. The New York Times. https://
www.nytimes.com/2023/09/01/business/college-admissions-essay-ai-chatbots.html

Singha, R., & Singha, S. (2023a). Economic sustainability, mindfulness, and diversity in the age of artificial intelligence
and machine learning. In P. Raj, P. B. Soundarabai, & P. Augustine (Eds.), Machine Intelligence: Computer Vision and
Natural Language Processing (pp. 273–285). Taylor & Francis Group. doi:10.1201/9781003424550-15

Singha, S., & Singha, R. (2023). Protecting data and privacy: Cloud-based solutions for intelligent transportation ap-
plications. Scalable Computing: Practice and Experience, 24(3), 257–276. doi:10.12694/scpe.v24i3.2381

SlimiZ. (2021). The impact of AI implementation in higher education on educational process future: A systematic review,
Research Square. doi:10.21203/rs.3.rs-1081043/v1

Sok, S., Kang, E. Y., & Han, Z. (2019). Thirty-five years of ISLA on form-focused instruction: A methodological syn-
thesis. Language Teaching Research, 23(4), 403–427. doi:10.1177/1362168818776673

Soomro, S. A., Kazemian, B., & Mahar, I. H. (2015). The Importance of Culture in Second and Foreign Language
Learning. SSRN Electronic Journal, 15(1), 1–10. doi:10.2139/ssrn.2656713

Southern, M. G. (2023, February 8). Google Launches Ai-Powered Contextual Translations. Search Engine Journal.
https://www.searchenginejournal.com/google-launches-ai-powered-contextual-translations/478863/#close

Steenbergen-Hu, S., & Cooper, H. (2014). A meta-analysis of the effectiveness of intelligent tutoring systems on college
students’ academic learning. Journal of Educational Psychology, 106(2), 331–347. doi:10.1037/a0034752

Stephenson, B., & Harvey, A. (2022). Student equity in the age of AI-enabled assessment: Towards a politics of inclusion.
In Assessment for Inclusion in Higher Education (pp. 120–130). Routledge. doi:10.4324/9781003293101-14

369
Compilation of References

Sternberg, R. J. (2014). Most vocabulary is learned from context. In The nature of vocabulary acquisition (pp. 89–105).
Psychology Press.

Street, B. V. (1993). Culture is a verb: Anthropological aspects of language and cultural process. In D. Graddol, L.
Thompson, & M. Byran (Eds.), Language and Culture (pp. 23–44). BAAL and Multiple Matters.

Su, J., & Yang, W. (2023). Unlocking the power of ChatGPT: A framework for applying generative AI in education.
ECNU Review of Education.

Su, J., Tsz, D., Ng, K., Kai, S., & Chu, W. (2023). Computers and Education : Artificial Intelligence Artificial Intelligence
(AI) Literacy in Early Childhood Education : The Challenges and Opportunities. Computers and Education: Artificial
Intelligence, 4(January), 100124. doi:10.1016/j.caeai.2023.100124

Sumakul, D. T. (2019). When robots enter the classrooms: Implications for teachers. In International Conference on
Embedding Artificial Intelligence (AI) in Educational Policy and Practice for Southeast Asia, Jakarta, Indonesia.
SEAMEO SEAMOLEC.

Sun, Z., Anbarasan, M., & Kumar, D. (2020). Design of online intelligent English teaching platform based on artificial
intelligence techniques. Computational Intelligence, 37(3), 1166–1180. doi:10.1111/coin.12351

Sun, Z., Yu, Z. C., & Xu, F. Y. (2023). Analysis and improvement of classroom teaching based on artificial intelligence. In
H. Niemi, R. D. Pea, & Y. Lu (Eds.), AI in Learning: Designing the Future. Springer. doi:10.1007/978-3-031-09687-7_7

Suresh, A., Jacobs, J., Lai, V., Tan, C., Ward, W., Martin, J. H., & Sumner, T. (2021). Using transformers to provide teachers
with personalized feedback on their classroom discourse: The TalkMoves application. arXiv Preprint arXiv:2105.07949.

Sütçü, S. S., & Sütçü, E. (2023). English Teachers’ Attitudes and Opinions Towards Artificial Intelligence. International
Journal of Research in Teacher Education, 14(3).

Sutton, R. S., & Barto, A. (1998). Reinforcement Learning: An Introduction. IEEE Transactions on Neural Networks,
9(5), 1054. Advance online publication. doi:10.1109/TNN.1998.712192

Sweller, J. (2012). Cognitive load theory. In Springer eBooks (pp. 601–605). doi:10.1007/978-1-4419-1428-6_446

Swiecki, Z., Ruis, A. R., Gautam, D., Rus, V., & Williamson Shaffer, D. (2019). Understanding when students are ac-
tive‐in‐thinking through modeling‐in‐context. British Journal of Educational Technology, 50(5), 2346–2364. doi:10.1111/
bjet.12869

Tafazoli, D., María, E. G., & Abril, C. H. (2019). Intelligent language tutoring system. International Journal of Informa-
tion and Communication Technology Education, 15(3), 60–74. doi:10.4018/IJICTE.2019070105

Tan, S. (2023). Harnessing artificial intelligence for innovation in education. In Learning Intelligence (pp. 335–363).
Innovative and Digital Transformative Learning Strategies. doi:10.1007/978-981-19-9201-8_8

Teubner, T., Flath, C. M., Weinhardt, C., van der Aalst, W., & Hinz, O. (2023). Welcome to the Era of ChatGPT et al.
Business & Information Systems Engineering, 65(2), 95–101. doi:10.1007/s12599-023-00795-x

The Chinese University of Hong Kong. (2021, 24 August). A 30-minute EEG Test Forecasts Children’s Language De-
velopment. CUHK in Touch. Retrieved from https://cuhkintouch.cpr.cuhk.edu.hk/2021/08/7463/

The Chinese University of Hong Kong. (2023). Use of Artificial Intelligence Tools in Teaching, Learning and Assess-
ments: A Guide for Students. Hong Kong: The Chinese University of Hong Kong. Retrieved from https://www.aqs.cuhk.
edu.hk/documents/A-guide-for-students_use-of-AI-tools.pdf

370
Compilation of References

The Hong Kong Polytechnic University. (2023). Guidelines for Students on the Use of Generative Artificial Intelligence.
Hong Kong: The Hong Kong Polytechnic University of Hong Kong. Retrieved from https://www.polyu.edu.hk/ar/ doc-
drive/polyu-students/Student-guide-on-the-use-GenAI.pdf

Tinsley, T. (2019). Language Trends 2019: Language Teaching in Primary and Secondary Schools in England. Survey
report. British Council.

Tinsley, T., & Board, K. (2013). Languages for the future: What languages the UK needs most and why. British Council
and Alcantara Communications.

Toncic, J. (2020). Teachers, AI Grammar Checkers, and the Newest Literacies: Emending Writing Pedagogy. Digital
Culture & Education, 12(1), 26–51.

Toquero, C. M. D. (2020). Challenges and Opportunities for Higher Education Amid the COVID-19 Pandemic: The
Philippine Context. Pedagogical Research. doi:10.29333/pr/7947

Towle, B., & Halm, M. J. (2006). Designing adaptive learning environments with learning design. In Springer eBooks
(pp. 215–226). doi:10.1007/3-540-27360-3_12

Tseng, W., & Warschauer, M. (2023). AI-writing tools in education: If you can’t beat them, join them. Journal of China
Computer-Assisted Language Learning, 3(2), 258–262. Advance online publication. doi:10.1515/jccall-2023-0008

Tumbal, S., Liando, N. V., & Olii, S. T. (2021). Students’ perceptions toward the use of Google Translate in translating.
Kompetensi, 1(02), 313–320. doi:10.53682/kompetensi.v1i02.1853

Tuomi, I. (2018). The Impact of Artificial Intelligence on Learning, Teaching, and Education Policies. Science for Policy.
doi:10.2760/12297

U.S. Department of Education, Office of Educational Technology. (2023). Artificial Intelligence and Future of Teaching
and Learning: Insights and Recommendations. https://tech.ed.gov/ai-future-of-teaching-and-learning

UBC. (n.d.). Generative AI Resources. The University of British Columbia: Generative AI. https://genai.ubc.ca/resources/

Ünal, E., & Güngör, F. (2021). The continuance intention of users toward mobile assisted language learning: The case
of DuoLingo. Asian Journal of Distance Education, 16(2).

Underwood, J. (2017). Exploring AI language assistants with primary EFL students. In K. Borthwick, L. Bradley, & S.
Thouësny (Eds.), CALL in a climate of change: Adapting to turbulent global conditions – short papers from EUROCALL
2017 (pp. 317–321). doi:10.14705/rpnet.2017.eurocall2017.733

UNESCO. (2003). Education in a multilingual world. UNESCO Education Position Paper. Paris: UNESCO. Retrieved
from: https://unesdoc.unesco.org/ark:/48223/pf0000129728

UNESCO. (2021). Education: Outbound internationally mobile students by host region. Institute of Statistics.

UNESCO. (2023). UNESCO survey: Less than 10% of schools and universities have formal guidance on AI. UNESCO.
https://www.unesco.org/en/articles/unesco-survey-less-10-schools-and-universities-have-formal-guidance-ai

University of Toronto. (n.d.a). ChatGPT and Generative AI in the Classroom. Office of the Vice-Provost, Innovations
in Undergraduate Education. https://www.viceprovostundergrad.utoronto.ca/strategic-priorities/digital-learning/special-
initiative-artificial-intelligence/

University of Toronto. (n.d.b). Using ChatGPT or Other Generative AI Tools on a Marked Assessment. https://www.
academicintegrity.utoronto.ca/perils-and-pitfalls/using-chatgpt-or-other-ai-tool-on-a-marked-assessment/

371
Compilation of References

Urlaub, P., & Dessein, E. (2022). From Disrupted Classrooms to Human-Machine Collaboration? The Pocket Calculator,
Google Translate, and the Future of Language Education. Journal of Linguistics and Language Teaching, 14(1). Advance
online publication. doi:10.5070/L214151790

UW–Madison Information Technology. (2023, August 24). Generative AI @ uw–madison: Use & policies. https://it.wisc.
edu/generative-ai-uw-madison-use-policies/

van den Berg, G., & du Plessis, E. (2023). ChatGPT and Generative AI: Possibilities for Its Contribution to Lesson Planning,
Critical Thinking and Openness in Teacher Education. Education Sciences, 13(10), 998. doi:10.3390/educsci13100998

Van Dijk, T. A. (1977). Context and cognition: Knowledge frames and speech act comprehension. Journal of Pragmatics,
1(3), 211–231. doi:10.1016/0378-2166(77)90035-2

van Dis, E. A., Bollen, J., Zuidema, W., van Rooij, R., & Bockting, C. L. (2023). ChatGPT: five priorities for research.
Nature, 614, 224–226. doi: m10.1038/d41586-023-00288-7

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Atten-
tion Is All You Need. https://doi.org//arxiv.1706.03762 doi:10.48550

Vazhayil, A., Shetty, R., Bhavani, R. R., & Akshay, N. (2019, December). Focusing on teacher education to introduce
AI in schools: Perspectives and illustrative findings. In 2019 IEEE tenth international conference on technology for
education (pp. 71–77). IEEE.

Verdegem, P. (2021). Introduction: Why We Need Critical Perspectives on AI. In P. Verdegem (Ed.), AI for Everyone?:
Critical Perspectives (pp. 1–18). University of Westminster Press. doi:10.16997/book55.a

Vij, S., Tayal, D., & Jain, A. (2020). A machine learning approach for automated evaluation of short answers using text
similarity based on WordNet graphs. Wireless Personal Communications, 111(2), 1271–1282. doi:10.1007/s11277-
019-06913-x

Wahyuni, D. S. (2022). Integrated classroom-chatbot experience: An alternative solution for English as foreign language
learners. English Language Education and Current Trends, 1(1), 63–68. doi:10.37301/elect.v1i1.36

Walker, G. (2010). Performed culture: Learning to participate in another culture. In G. Walker (Ed.), The pedagogy of
performing a culture (pp. 1–21). National East Asian Languages Resource Center.

Walker, G. (2021). Why we perform. In X. Zhang & X. Jian (Eds.), The third space and Chinese language pedagogy:
Negotiating intentions and expectations in another culture (pp. 139–158). Routledge.

Walker, G., & Noda, M. (2010). Remembering the future: Compiling knowledge of another culture. In G. Walker (Ed.),
The pedagogy of performing a culture (pp. 22–48). National East Asian Languages Resource Center.

Walsh, M. (2017). Multiliteracies, Multimodality, New Literacies and…. What Do These Mean for Literacy Education?
Inclusive Principles and Practices in Literacy Education, 11, 19–33. doi:10.1108/S1479-363620170000011002

Wang, J. (2016). Ecology of literacy: A context-based inter-disciplinary curriculum for Chinese as a foreign language
(Doctoral dissertation). Retrieved from https://rave.ohiolink.edu/etdc/view?acc_num=osu1461251633

Wang, J. (2023a, March 25). Xiang ChatGPT qingjiao “ba” zi ju – xisijikong de liangge quehan向ChatGPT请教“把”
字句——细思极恐的两个缺憾 [Consulting ChatGPT on the “ba” sentence – Two terrifying deficiencies upon careful
reflection] [Blog post]. Retrieved from https://mp.weixin.qq.com/s/dXvedrVHrdtJKJ9Yda6qpQ

372
Compilation of References

Wang, T., & Cheng, E. C. K. (2021). An investigation of barriers to Hong Kong K-12 schools incorporating Artificial
Intelligence in education. Computers and Education: Artificial Intelligence, 2.

Wang, J., & Jia, J. (Eds.). (2022). Performed Culture in action to teach Chinese as a FL: Integrating PCA in curriculum,
pedagogy, and assessment. Routledge.

Wang, T., Lund, B. D., Marengo, A., Pagano, N. R., Mannuru, N. R., Teel, Z. A., & Pange, J. (2023). Exploring the
potential impact of Artificial Intelligence (AI) on international students in higher education: Generative AI, chatbots,
analytics, and international student success. Applied Sciences (Basel, Switzerland), 13(11), 6716. doi:10.3390/app13116716

Wang, X., Liu, Q., Pang, H., Tan, S. C., Lei, J., Wallace, M. P., & Li, L. (2023). What matters in AI-supported learning:
A study of human-AI interactions in language learning using cluster analysis and epistemic network analysis. Computers
& Education, 194, 104703. Advance online publication. doi:10.1016/j.compedu.2022.104703

Wang, X., Pang, H., Wallace, M. P., Wang, Q., & Chen, W. (2022). Learners’ perceived AI presences in AI-supported
language learning: A study of AI as a humanized agent from the community of inquiry. Computer Assisted Language
Learning, 1–27. doi:10.1080/09588221.2022.2056203

Warschauer, M., & Healey, D. (1998). Computers and language learning: An overview. Language Teaching, 31(2),
57–71. doi:10.1017/S0261444800012970

Warschauer, M., Tseng, W., Yim, S., Webster, T., Jacob, S., Du, Q., & Tate, T. (2023, December). The Affordances and
Contradictions of AI-Generated Text for Second Language Writers. Journal of Second Language Writing, 62. Advance
online publication. doi:10.1016/j.jslw.2023.101071

WarschauerM.TsengW.YimS.WebsterT.JacobS.DuQ.TateT. (2023, October 31). The affordances and contradictions of

AI-generated text for writers of English as a second or foreign language. doi:10.2139/ssrn.4404380

Webb, S. (2007). The effects of repetition on vocabulary knowledge. Applied Linguistics, 28(1), 46–65. doi:10.1093/
applin/aml048

Wei, L. (2023). Artificial intelligence in language instruction: Impact on English learning achievement, L2 motiva-
tion, and self-regulated learning. Frontiers in Psychology, 14, 1261955. Advance online publication. doi:10.3389/
fpsyg.2023.1261955 PMID:38023040

Westergaard, M., Mitrofanova, N., Mykhaylyk, R., & Rodina, Y. (2017). Crosslinguistic influence in the acquisition
of a third language: The Linguistic Proximity Model. The International Journal of Bilingualism, 21(6), 666–682.
doi:10.1177/1367006916648859

Willems, J. (2023). ChatGPT at Universities – The Least of Our Concerns (SSRN Scholarly Paper No. 4334162).
doi:10.2139/ssrn.4334162

Williams, J. (2012). The potential role(s) of writing in second language development. Journal of Second Language Writ-
ing, 21(4), 321–331. doi:10.1016/j.jslw.2012.09.007

Williamson, B., & Eynon, R. (2020). Historical threads, missing links, and future directions in AI in education. Learn-
ing, Media and Technology, 45(3), 223–235. doi:10.1080/17439884.2020.1798995

373
Compilation of References

Williamson, B., Eynon, R., Knox, J., & Davies, H. C. (2023). Critical perspectives on AI in education: Political economy,
discrimination, commercialization, governance and ethics. In B. du Boulay, A. Mitrovic, & K. Yacef (Eds.), The handbook
of artificial intelligence in education (pp. 555–573). Edward Elgar Publishing Ltd. doi:10.4337/9781800375413.00037

Wilson, D. V., & Marcin, M. (2022). Building connections and critical language awareness between learning communi-
ties collaborating across two distant States. Languages (Basel, Switzerland), 7(4), 257. doi:10.3390/languages7040257

Wilson, J., Ahrendt, C., Fudge, E. A., Raiche, A., Beard, G., & MacArthur, C. (2021). Elementary teachers’ perceptions
of automated feedback and automated scoring: Transforming the teaching and learning of writing using automated writ-
ing evaluation. Computers & Education, 168, 104208. doi:10.1016/j.compedu.2021.104208

Wittgenstein, L. (1958). Philosophical investigations (3rd ed.; G. E. M. Anscombe, Trans.). Prentice Hall. (Original
work published 1953)

Wong, J., & Waring, H. Z. (2020). Conversation analysis and second language pedagogy: A guide for ESL/EFL teachers.
Routledge. https://books.google.com/books?hl=en&lr=&id=fybxDwAAQBAJ&oi=fnd&pg=PP11&dq=conversation
+analysis+language+teaching+correction&ots=5gbus7JfWb&sig=-mgbXRuvOTp4vHDNcMaVDgQTAcs

WooJ. H.ChoiH. (2021). Systematic review for AI-based language learning tools. Ithaca: Cornell University Library.
https://arxiv.org/abs/2111.04455v1

Woo, J. H., & Choi, H. (2021). Systematic Review for AI-based Language Learning Tools. Journal of Digital Contents
Society, 22(11), 1783–1792. doi:10.9728/dcs.2021.22.11.1783

Wu, L., Wu, Y., & Zhang, X. (2021). L2 Learner Cognitive Psychological Factors About Artificial Intelligence Writing
Corrective Feedback. English Language Teaching, 14(10), 10. Advance online publication. doi:10.5539/elt.v14n10p70

Xi, X. (2010). Automated scoring and feedback systems: Where are we and where are we heading? Language Testing,
27(3), 291–300. doi:10.1177/0265532210364643

Xu, L. (2020, December). The dilemma and countermeasures of AI in educational application. In 2020 4th international
conference on computer science and artificial intelligence (pp. 289–294). ACM.

Yaacob, Z., & Saad, N. H. M. (2020). Acceptance of YouTube as a learning platform during the Covid-19 pandemic:
The moderating effect of subscription status. TEM Journal, 4, 1732–1739. doi:10.18421/TEM94-54

Yan, D. (2023). Impact of ChatGPT on learners in a L2 writing practicum: An exploratory investigation. Education
and Information Technologies, 28(11), 13943–13967. Advance online publication. doi:10.1007/s10639-023-11742-4

Yang, H., & Kyun, S. (2022). The current research trend of artificial intelligence in language learning: A systematic
empirical literature review from an activity theory perspective. Australasian Journal of Educational Technology, 38(5),
180–210. doi:10.14742/ajet.7492

Yau, K., Chai, C., Chiu, T., Meng, H., King, I., & Yam, Y. (2022). A phenomenographic approach on teacher conceptions
of teaching artificial intelligence (AI) in K-12 schools. Education and Information Technologies, 28(1), 1041–1064.
doi:10.1007/s10639-022-11161-x

Yeadon, W., Inyang, O.-O., Mizouri, A., Peach, A., & Testrow, C. (2022). The Death of the Short-Form Physics Essay
in the Coming AI Revolution. arXiv. . 2212. 11661 doi:10. 48550/arXiv

374
Compilation of References

Yeşilyurt, Y. E. (2023). AI-enabled assessment and feedback mechanisms for language learning. In Advances in Educa-
tional Technologies and Instructional Design book series (pp. 25–43). doi:10.4018/978-1-6684-9893-4.ch002

Yildirim, Y., Arslan, E. A., Yildirim, K., & Bisen, I. E. (2021). Reimagining education with artificial intelligence. Eur-
asian Journal of Higher Education, 2(4), 32–46. doi:10.31039/ejohe.2021.4.52

Yin, J., Goh, T. T., Yang, B., & Xiaobin, Y. (2021). Conversation technology with micro-learning: The impact of chatbot-
based learning on students’ learning motivation and performance. Journal of Educational Computing Research, 59(1),
154–177. doi:10.1177/0735633120952067

Young, J. C., & Shishido, M. (2023). Investigating OpenAI’s ChatGPT potentials in generating chatbot’s dialogue for
English as a foreign language learning. International Journal of Advanced Computer Science and Applications, 14(6),
65–72. doi:10.14569/IJACSA.2023.0140607

You, Z. J., Shen, C. Y., Chang, C. W., Liu, B. J., & Chen, G. D. (2006). A robot as a teaching assistant in an English
class. In Sixth IEEE International Conference on advanced learning technologies (ICALT’06) (pp. 87-91). 10.1109/
ICALT.2006.1652373

Yu, L. (2021). The Performed Culture Approach. In Z. Ye (Ed.), New trends in teaching Chinese as a foreign language
(pp.1–34). Singapore: Palgrave Macmillan. doi:10.1007/978-981-13-6844-8_7-1

Yuan, S., He, T., Huang, H., Hou, R., & Wang, M. (2020). Automated Chinese essay scoring based on deep learning.
CMC-Computers Materials & Continua, 65(1), 817-833. https://doi.org/.2020.010471 doi:10.32604/cmc

Yueng, P. (2019, 31 January). AI will be a game changer for Hong Kong education. China Daily Hong Kong.

Yu, H. (2023). Reflection on whether Chat GPT should be banned by academia from the perspective of education and
teaching. Frontiers in Psychology, 14, 1181712. doi:10.3389/fpsyg.2023.1181712 PMID:37325766

Yurtseven Avci, Z., O’Dwyer, L. M., & Lawson, J. (2020). Designing effective professional development for technology
integration in schools. Journal of Computer Assisted Learning, 36(2), 160–177. doi:10.1111/jcal.12394

Zai, X., Chu, X., Chai, C. S., Jong, M. S. Y., Istenic, A., & Spector, M. (2021). A review of artificial intelligence (AI) in
education from 2010 to 2020. Complexity, 2021, 1–18. Advance online publication. doi:10.1155/2021/8812542

Zawacki-Richter, O., Marín, V. I., Bondand, F., & Gouverneur, M. (2019). Systematic review of research on artificial
intelligence applications in higher education–Where are the educators? International Journal of Educational Technology
in Higher Education, 16(39), 39. Advance online publication. doi:10.1186/s41239-019-0171-0

Zeng, Z. (2023, February 25). Yu ChatGPT zuo pengyou!与ChatGPT做朋友! [Befriending ChatGPT] [Blog post].
Retrieved from https://mp.weixin.qq.com/s/LLruwI7bWpSuCkAUx5BkiA

Zhai, X. (2022). ChatGPT User Experience: Implications for Education (SSRN Scholarly Paper No. 4312418). doi:10.2139/
ssrn.4312418

Zhai, X. (2022). ChatGPT User Experience: Implications for Education. SSRN Scholarly Paper. . 43124 18 doi:10.
2139/ ssrn

Zhang, M., & Li, J. (2021). A commentary of GPT-3 in MIT Technology Review 2021. Fundamental Research, 1(6),
831–833. doi:10.1016/j.fmre.2021.11.011

375
Compilation of References

Zhao, J., Wu, M., Zhou, L., Wang, X., & Jia, J. (2022). Cognitive psychology-based artificial intelligence review. Fron-
tiers in Neuroscience, 16, 1024316. Advance online publication. doi:10.3389/fnins.2022.1024316 PMID:36278021

Zhao, X. (2023). Leveraging Artificial Intelligence (AI) Technology for English Writing: Introducing Wordtune as a
Digital Writing Assistant for EFL Writers. RELC Journal, 54(3), 890–894. doi:10.1177/00336882221094089

Zheng, L., Niu, J., Zhong, L., & Gyasi, J. F. (2021). The effectiveness of artificial intelligence on learning achievement
and learning perception: A meta-analysis. Interactive Learning Environments, 1–15. doi:10.1080/10494820.2021.2015693

Zhu, Y. (2020). The application of artificial intelligence in foreign language teaching. 2020 International Conference
on Artificial Intelligence and Education (ICAIE). 10.1109/ICAIE50891.2020.00024

Ziegler, N., & González-Lloret, M. (2022). The Routledge Handbook of Second Language Acquisition and Technology
(1st ed.). Routledge. doi:10.4324/9781351117586

Zou, B., Guan, X., Shao, Y., & Chen, P. (2023). Supporting speaking practice by social network-based interaction in
artificial intelligence (ai)-assisted language learning. Sustainability (Basel), 15(4), 2872. doi:10.3390/su15042872

Zou, D., Xie, H., & Wang, F. L. (2018). Future trends and research issues of technology-enhanced language learning: A
technological perspective. Knowledge Management & E-Learning, 10(4), 426–440.

376
377

About the Contributors

Fang Pan has a Master’s Degree in Chinese Language Pedagogy. The editor is an experienced teacher
of Mandarin in different settings. Before joining London School of Economics and Political Science (LSE),
the editor taught all levels of Chinese at Harvard University and won Teaching Distinction Certificates
in three consecutive years. The editor has experience in teaching a wide range of Mandarin courses in
different settings, including pre-school classes, high school summer programs and university intensive
programs. At the LSE, the editor is involved in teaching BSc International Relations and Chinese and
BSc Language, Culture and Society undergraduate degree programmes. He was awarded LSE Teach-
ing Excellence Awards several times. In addition to in-class teaching, the editor is one of the writers of
the book Cases on Audio-Visual Media in Language Education. The editor attended and presented at
several regional and international language conferences. The editor’s past presentation topics include
video project, grammar teaching, essay writing and curriculum design.

***

Samet Bal Samet Bal is an experienced educator and researcher who worked at Turkish Airforce
Academy, Yildiz Technical University, and currently studies at Turkish Airlines Flight Academy as an air
cadet. With a Master’s degree in English Language Education and ongoing pursuit of a Ph.D. in the same
field, he specializes in education technology and language teaching. His research and presentations have
revolved around these areas, exploring innovative approaches to enhance language learning experiences.

Lourdes Barquín Sanmartín is a Teaching Fellow at University College Dublin and holds a PhD in
Language Acquisition and Language Teaching from the University of Edinburgh. She is also a Fellow of
the Higher Education Academy (FHEA). Her research centers on Spanish acquisition by native English
speakers, particularly focusing on positive grammatical transfers between proximal languages. With a
background in British education, Lourdes specializes in students with English as their first language (L1),
French as their second language (L2), and Spanish as their third language (L3). Her work emphasizes
the similarities between French and Spanish to aid in learning past aspectual and modal contrasts. To
address this, Lourdes advocates for the pluralistic teaching approach of Inter-comprehension, which helps
students utilize their previously-acquired languages as a tool to enhance both their linguistic awareness
and comprehension, offering a holistic strategy for language learning.

About the Contributors

Dimaris Barrios-Beltran received her PhD in Language Sciences (with minors in General Linguis-
tics and Hispanic Linguistics) from Indiana University-Bloomington (IUB) in 2016. With over 16 years
of teaching experience, she has held positions at various institutions, including IUB, Amherst College,
and Mount Holyoke College. She has taught a range of courses, including Spanish language at various
levels, Spanish culture, and Latin American and Caribbean cultures and histories. Her areas of expertise
encompass Linguistics, Syntax-Semantics Interface, L1 and L2 Language Acquisition, Pedagogy, Span-
ish Heritage speakers, Communication Disorders, Specific Language Impairment, Autism, Disability-
Inclusive classrooms, and Technology in the classroom. She has also served as AP Spanish reader,
table leader and question leader for the College Board, and she has led several talks and workshops on
linguistic research, teaching practices, Caribbean culture, and improving classroom dynamic through
games, multimodal activities and technological tools.

Banu Çiçek Başaran Uysal works at the English Language Teaching Department within the Faculty
of Education at Eskisehir Osmangazi University, Turkey. She received her Ph.D. in ELT from Middle
East Technical University (2020). Currently, she is offering English teacher education courses at the
undergraduate level. Her research interests are pre-service teacher education, in-service teacher train-
ing, technology integration, online education, artificial intelligence in education, and corpus linguistics

Géraldine Bengsch is a language tutor for German in the Department of Language and Linguistic
Science at the University of York and a Visiting Lecturer in the Department of Sociology at City, Uni-
versity of London. She is passionate about technology in teaching and developing interactive educational
resources to make learning enjoyable and accessible to all students.

Yongyin Chen is an experienced language teacher. Her research interests include applied linguistics,
educational technology, and language education.

Betül Czerkawski is an instructional design and technology professor from the University of Arizona.
She is also a Second Language Acquisition and Teaching Program faculty member. Her research interests
include learning design, foreign language teaching and learning, and emerging learning technologies.

Nazmi Dinçer serves as an English Language Instructor at the Turkish National Defence University,
primarily within the Department of Foreign Languages. Presently, he is responsible for conducting
specialized courses designed to equip aspiring pilots with essential communication skills, specifically
tailored to adhere to the International Civil Aviation Organization (ICAO) standards.In addition to his
instructional duties, Mr. Dinçer is engaged in advanced academic pursuits as a Ph.D. candidate at the
Department of Educational Technology, Bahçeşehir University. His research ambitiously explores the
intersection of educational technology and foreign language education. His areas of focus include dis-
tance education, multimedia learning, the application of artificial intelligence in educational contexts,
and the integration of game-based learning. His scholarly work contributes significantly to the evolving
landscape of educational technology in language instruction.

378
About the Contributors

Sylvia Gaspari is a Ph.D candidate in the Department of Italian Studies at the University of Toronto.
She is finishing work on her thesis about the rhetoric of prayer within the invocations of Dante’s Divine
Comedy. She has also translated several Renaissance letters for a publication on Renaissance Grotesques,
and has contributed to a translation of a book on Aristotle’s peripatetic school.

Mohammad J. Jamali is a Ph.D. Candidate at the Department of Italian Studies of the University
of Toronto. Since 2016, he has worked on Mario Pratesi’s archives at the E.J. Pratt Library of Victoria
University in Toronto. In 2019, when he started his doctoral studies in the Department, he began a so-
ciolinguistic project focusing on the issue of gender disparity and gender identity in Italian, which he
continues to carry forward, parallel to his main thesis on Pratesi.

Elizabeth Jasmine is a highly regarded Professor of Psychology at the Indian Institute of Psychology
and Research (IIPR) in Bengaluru, Karnataka, India. Her distinguished academic career is marked by
significant contributions to psychology, evidenced by her extensive publication history in national and
international journals. As a dedicated educator and researcher, Dr. Jasmine imparts knowledge to the
next generation and conducts ground-breaking research, exploring various aspects of human behavior
and cognition. Her influence extends globally, with her work reaching international audiences through
reputable journals, reflecting a profound understanding of psychology and offering insights that could
shape the discipline’s future.

Natalie Khazaal, PhD, is Associate Professor in the School of Modern Languages, Georgia Insti-
tute of Technology who studies the links between disenfranchisement, media, and language. She is an
American Council of Learned Societies (ACLS) fellow for her work on Arab atheists. She has authored
the book “Pretty Liar: Television, Language, and Gender in Wartime Lebanon” and coedited the book
“‘Like an Animal’: Critical Animal Studies Perspectives on Borders, Displacement, and Othering.”

Siu-lun Lee is Senior Lecturer at the Chinese University of Hong Kong. His research interests include
applied linguistics, Cantonese studies, Chinese linguistics, sociolinguistics, language teaching pedagogy,
technology and language learning. He is the author of the book series Modern Cantonese and the editor
of The learning and teaching of Cantonese as a second language published by Routledge.

Sohyeon Lee is a graduate student in the Department of Second Language Studies at the University
of Hawaii at Manoa. With a background spanning two decades in teaching L2 English to adolescents
in various public schools in Seoul, Korea, she had the privilege of working extensively in curriculum
design, instructional development, and textbook publications through her employment with the Seoul
Metropolitan Office of Education. Her growing interest in Language Testing and Assessments has driven
her to explore the intricacies of evaluating L2 English productive skills, particularly in the domains of
writing. She is deeply committed to addressing validity and fairness issues in L2 English assessments
within EFL contexts, aiming to promote fairness and justification in language assessment practices. She
is also exploring how AI can be integrated into language teaching curricula and assessments.

379
About the Contributors

Weiming Liu holds the position of Assistant Professor in the School of Applied Language and In-
tercultural Studies at Dublin City University, Ireland. His scholarly pursuits revolve around language
teacher education and foreign language teaching and learning, with a particular focus on exploring the
intricacies of language pedagogy.

Teresa Lobalsamo is Associate Professor, Teaching Stream, of Italian Studies at the University of
Toronto Mississauga. Her current research includes curating a digital repository of archival materials
related to Italian Canadiana, pedagogical considerations on the effective delivery of online courses, and
work-integrated learning modules. In 2018, she received the University of Toronto Mississauga Teaching
Excellence Award for Junior Faculty.

Franziska Lys is Professor of German and Director of Undergraduate Studies in the department of
German as well as the Director of the MENA Languages program at Northwestern University. Dr. Lys
is an internationally recognized expert in the integration of culture in the language classroom and widely
published in that subject including a co-edited volume on the cultural integration of both Germanys 25
years after the “Wende.” She has co-produced four foreign documentaries which are the main educational
material for language learning software she designed.

Lee-Luan Ng obtained her PhD in Applied Linguistic from University of Otago, New Zealand. She
teaches postgraduate courses at the Faculty of Languages and Linguistics. She is also a certified trainer
for the software, NVivo. She has been invited to conduct workshops on using computer-assisted qualita-
tive data analysis software in deciphering research data at various public and private universities locally
and abroad. She was involved in international scholar exchange at Beijing Foreign Studies University
as well as participated in research projects with an interdisciplinary focus with organizations such as
the British Council. Her current research interest includes computer assisted language learning, online
learning, learning in higher education, the use of AI, VR and gaming in language learning. Lee Luan
has also been invited to review journal articles for overseas and local publications such as Frontiers
in Psychology - Language Sciences, Pertanika Journal, Malaysian Journal of ELT Research, and The
Malaysian Journal of Learning and Instruction.

Venosha Ravana, a distinguished academic at Tunku Abdul Rahman University of Management and
Technology, holds degrees from Universiti Sains Malaysia and the University of Malaya. Specializing
in instructional design and technology, language teaching, and teacher training, she actively contributes
to these fields. During her Bachelor’s degree, she volunteered at an INGO in Hanoi, Vietnam, teaching
English to underprivileged students, showcasing her commitment to inclusive education. As prolific
author, she penned two influential books in 2022 and 2023, providing practical insights for collabora-
tive learning approaches. Engaged in collaborative research, Venosha collaborates with researchers from
other institutions, fostering interdisciplinary contributions. As the coordinator of language courses at her
institution, she plays a vital role in enhancing language education. From her early volunteer work to her
current administrative and collaborative roles, Venosha’s contributions exemplify a holistic dedication
to education and community service. Her multifaceted approach makes her a respected and influential
figure in academia.

380
About the Contributors

Dellannia Segreti is a current graduate student at the University of Toronto. Her interests lie in
equitable and accessible pedagogies, with a focus on experiential learning, research, and technologies.

Ranjit Singha, a doctoral research fellow at Christ University and distinguished member of the
American Psychological Association (APA), excels in research and development across diverse domains:
Mindfulness, Addiction Psychology, Women Empowerment, UN Sustainable Development Goals, and
Data Science. Certified by IBM and The University of Oxford Mindfulness Centre, he also holds cre-
dentials as a Microsoft Innovative Educator, Licensed Yoga Professional, Certified Mindfulness Teacher,
and CBCT Teachers Training from Emory University, USA. With educational qualifications spanning
PGDBA (GM), MBA (IB), MSc in Counselling Psychology, and a Senior Diploma in Tabla, Mr. Ranjit
has an extensive publication record, mentors research projects, teaches diverse subjects, and actively
contributes to journals and publications, solidifying his impactful role in psychology.

Surjit Singha is an academician with a broad spectrum of interests, including UN Sustainable Devel-
opment Goals, Organizational Climate, Workforce Diversity, Organizational Culture, HRM, Marketing,
Finance, IB, Global Business, Business, AI, K12 and Higher Education, Gender and Cultural Studies.
Currently a faculty member at Kristu Jayanti College, Dr Surjit also serves as an Editor, reviewer, and
author for prominent global publications and journals, including being on the Editorial review board of
Information Resources Management Journal and contributor to various publications. With over 13 years
of experience in Administration, Teaching, and Research, Dr. Surjit is dedicated to imparting knowledge
and guiding students in their research pursuits. As a research mentor, Dr. Surjit has nurtured young minds
and fostered academic growth. Dr. Surjit has an impressive track record of over 75 publications, includ-
ing articles, book chapters, and textbooks, holds two US Copyrights, and has completed and published
two fully funded minor research projects from Kristu Jayanti College.

Jianfen Wang has a Ph.D. in Chinese Pedagogy and MA in TESOL from The Ohio State University.
She is currently an Associate Professor of Chinese and Asian Studies at Berea College. She has 20 years
of experience teaching and researching foreign language teaching and learning. She is a co-author of
“Perform Suzhou: A Course in Intermediate to Advanced Spoken Mandarin” and the primary editor
of “Performed Culture in Action to Teaching Chinese as a Foreign Language,” a volume on innovative
Chinese language pedagogy.

İlknur Yuksel works as an Associate Professor at the English Language Teaching Department
within the Faculty of Education at Eskisehir Osmangazi University, Turkey. She received her Ph.D. in
ELT from Anadolu University (2012). She offers several teacher training courses including Assessment
and Testing in English Language Teaching. Her research interests include vocabulary teaching, teacher
training, second language acquisition, instructional technologies in language teaching, and artificial
intelligence for teacher education.

381
382

Index

21st Century Education 165, 167 C

A CAGR 80, 99
ChatGPT 1-4, 6-16, 19, 23, 32-33, 44-47, 49-54, 57,
Academic Integrity 31, 36, 45, 47, 150, 153, 162, 167, 62-63, 70-72, 74, 83, 89, 101-107, 109, 111, 115,
174, 190, 195, 214, 269 119-121, 123, 128, 135-137, 139, 149, 155-158,
Academic Writing 7, 149, 269-278, 281, 283, 285 160, 173-186, 188-191, 222-224, 228-234, 237-
Adaptive Assessment 41 241, 243, 245, 249, 269-270, 272-278, 280-285,
AI Competence 128 289-291, 297-301, 304, 307-308, 311-313, 315-
AI Image Generator 243 316, 318, 324, 337
AI in Education 14, 27, 35, 44, 47, 53, 62, 74, 78, 81, ChatGPT in Education 3, 273
93, 99, 103, 120, 133, 135-136, 143-144, 152-153, ChatGPT Prompt 243, 276
168, 199, 270, 325 Computer-Assisted Language Learning (CALL) 134,
AI Literacy 47, 101-102, 121-122, 128, 245, 336-337 136, 142, 144, 148, 272
AI Technologies 14-16, 19, 25, 27, 36-37, 47, 72, 78, Content Analysis 8, 155
83, 88, 91, 93-94, 102-105, 136, 144, 249, 324- Cultural Competence 54, 57
325, 327, 335 Cultural Knowledge Compilation 179, 193
AI Tools 2, 14-16, 24, 35, 43-44, 47, 49-53, 57, 61-63, Culture-Focused 173-176, 178-179, 189-190, 193-194
66-67, 69-72, 74-75, 77, 82-83, 85, 87, 91-93,
120-123, 133, 135, 144, 150, 152-153, 156, 158- D
165, 170, 189, 191, 245-251, 260-261, 263-264,
270, 272-274, 281, 284-285, 315-316, 324-325, Digital Literacy 1, 46, 57, 64, 67, 167
327-331, 334-336
Application Programming Interface (API) 220 E
Application, App 220
Artificial Intelligence (AI) 1-2, 19, 22-25, 27-37, 41, EFL 3, 7-9, 11-12, 78-79, 81-85, 87-88, 90, 92-94,
43-45, 54, 57, 61, 64, 66, 74, 77-84, 88-89, 91, 99, 99, 101-103, 105-106, 108-109, 111, 115, 119,
101, 103, 105-106, 109, 121-122, 128, 133-136, 121-122, 152, 329, 332-333
143-144, 149, 168-169, 174, 195, 220-222, 227, Emerging Technology 61-62, 325, 327, 337, 341
235, 244, 267, 270, 307, 324, 341 Ethical Use of AI 48, 63, 71-72, 75, 199, 213, 284, 337
Evaluation Rubric 101, 107-108, 118
B Experiential Learning 48-50, 57, 104, 175, 193, 244,
246-247, 250, 260, 267, 276
Behavioral Culture 174, 184, 193 Explicit Grammar Learning 243
Blended Teaching and Learning 135, 148

Index

F Language Learning Skills 19, 61, 72, 77

Language Teaching 3-4, 14, 19, 22-23, 27, 42, 53, 71,
Flipped Curriculum 173-175, 193 89-90, 94, 101-103, 106-107, 119-120, 122-123,
Focus on Forms (FonFs) 224-225, 243 135-136, 138, 141-142, 144, 148, 152, 176, 224-
225, 240, 243, 300-301, 303-304, 322
G Language Teaching Materials 22-23, 27, 42
Large Language Models (LLM) 53, 57, 99, 194, 196,
Generative AI 44, 47, 49, 51-54, 57, 99, 101-102, 104- 199, 221, 245, 270
105, 121, 128, 135-144, 199, 220, 222, 227, 273, Learner Attitude 19
324-325, 327-330, 333-337, 341 Learner Engagement 19, 29, 80
Graphical User Interface (GUI) 220 Learning Experience Design (LXD) 324-326, 328,
337, 341
H Lesson Planning 101-102, 106-107, 111, 113, 121-
122, 128
Higher Education 47, 61-62, 64, 67, 74, 77, 89, 136, Linguistic Needs 62, 77
149, 302, 304, 314, 325, 333
HIPs 244, 246, 250, 267 M
I Machine Learning (ML) 3, 27-29, 32, 34, 103, 149,
168, 195-202, 209-210, 213-214, 221, 245, 272
Implicit Grammar Learning 243 Multidimensional Tools 77
Inclusive Education 77
Innovative Pedagogies 62, 77 N
Innovative Technology 77
Instructional Design 275, 325-326, 337, 341 Natural Language Processing (NLP) 9, 25-30, 32-34,
Inter-Comprehension 300-301, 305-308, 315, 322 103, 134, 199, 202, 221, 245, 272
Intercultural Communicative Competence (ICC) 173, Normalization Process 135, 148
194
Italian Cultural Studies 57 P
L Pedagogic Translation 322
Pedagogical Context 106, 128
L2 Classroom 61, 64, 69-71, 74, 77 Perceived Behavioral Control 153-154, 160-161,
L3 Acquisition 300 163, 165
Language Acquisition 25-26, 28-29, 32-33, 36-37, Performed Culture Approach (PCA) 174, 194
41-42, 63-64, 77, 81, 91, 103, 120-121, 193, Personalized Learning 2, 10, 26, 28-29, 33, 41-42,
198-199, 225, 228, 243, 247, 260, 301, 305, 307, 63-64, 74-75, 80, 90, 92, 94, 122, 169, 247, 249
315, 322, 341 Plagiarism 31, 45-47, 50, 61, 63, 74, 83, 142, 159, 162,
Language Education 1-4, 6-9, 11, 13-16, 19, 22-30, 168, 237, 273, 284, 331
32-37, 41, 45, 62, 65-67, 70-72, 75, 87-88, 94, Pluralistic Approaches 300-301, 303, 305-306, 318, 322
101, 103, 105, 121-123, 133-139, 141-144, 153, Positive or Facilitating Transfer 322
168, 170, 173-174, 176, 190, 194-199, 202, 206, Positive Transfer 307, 311, 322
213-215, 247, 249, 269, 285, 303, 336 Prompting Strategies 175, 194
Language Learning 2-4, 7-15, 19, 23-24, 26-30, 32-33, Putonghua 138, 140, 148
41, 44, 61-63, 65, 67, 69, 71-72, 74-75, 77, 79,
81, 83, 89-94, 101, 103-105, 121-122, 133-136, R
139-140, 142-144, 148-149, 153, 158, 160, 162,
165, 168, 176, 190, 193, 195-202, 206-207, 209- Reflective Assignments 50, 57
210, 212-215, 224-225, 229, 245-246, 248-249, Romance Languages 300-301, 307-310, 312-313, 322
251, 260, 272, 305-307, 316, 322, 324, 328-329, Rubric Assessment 128
334, 336, 341

383
Index

S T
SDGs 244, 246-248, 250, 257, 260-261, 268 Task-Based Language Teaching 224, 243
Second Language (L2) 3, 7-8, 15, 32, 61-66, 69-72, Teacher Training 101-102, 325, 336
77, 139, 224-226, 228-229, 241, 270-271, 301, Technological Proficiency 32, 84, 87, 92, 94, 99, 122
307, 313, 324-325, 341 Theory of Planned Behaviour 163
Second Language Acquisition (SLA) 63-64, 77, 341 Trilingualism and Biliteracy 138, 148
Semi-Structured Interviews 8, 78, 82, 84, 154-155
Standard Written Chinese 138, 148 W
Student Engagement 10, 30, 47-48, 79, 87, 91-92, 94,
105, 120-121, 247, 250-251, 261, 268, 274, 285 Writing-to-Learn Activities 222, 226, 243

384