A A
Project Report on
AI BASED AUTOMATIC EXAMINATION
PAPER EVALUATION SYSTEM
Submitted in partial fulfillment of the requirement
for the award of the degree of
BACHELOR OF TECHNOLOGY
IN
CSE(ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING)
Submitted by
Mutyala Vanitha 20A31A4219
Anaparthi Vineela 20A31A4202
Angara Navya Sri Alekhya 20A31A4203
Godavarthi Srujana 20A31A4209
Merugu Bhuvana Naga Priya 20A31A4218
Under the esteemed guidance of
Mrs. L. Yamuna M.Tech.,
Assistant Professor of CSE(AI&ML)
DEPARTMENT OF CSE(ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING)
PRAGATI ENGINEERING COLLEGE
(AUTONOMOUS)
(Approved by AICTE, Permanently Affiliated to JNTUK, KAKINADA, Accredited by NBA)
ADB Road, Surampalem, Near Peddapuram, Kakinada District, AP- 533437
2020-2024
PRAGATI ENGINEERING COLLEGE
(AUTONOMOUS)
(Approved by AICTE, Permanently Affiliated to JNTUK, Kakinada, Accredited by NBA)
ADB Road, Surampalem, Near Peddapuram, Kakinada District, AP-533437
CERTIFICATE
DEPARTMENT OF CSE (ARTIFICIAL INTELLIGENCE AND MACHINE
LEARNING)
This is to certify that the project report entitled “AI BASED
AUTOMATIC EXAMINATION PAPER EVALUATION SYSTEM” is being
submitted by Mutyala Vanitha(20A31A4219), Anaparthi Vineela(20A31A4202), Angara
Navya Sri Alekhya(20A31A4203), Godavarthi Srujana(20A31A4209), Merugu Bhuvana
Naga Priya(20A31A4218) in partial fulfilment for the award of the Degree of
Bachelor of Technology, during the year 2020-2024 in CSE(Artificial
Intelligence and Machine Learning) of Pragati Engineering College, for the record
of a bonafide work carried out by them.
Project Supervisor: Head of the Department:
Mrs. L. Yamuna M.Tech Dr. A. Radha Krishna, Ph.D.
Assistant Professor Head of the Department
Department of CSE(AI&ML) Department of CSE(AI&ML)
Pragati Engineering College Pragati Engineering College
ACKNOWLEDGEMENT
We express our sincere gratitude to our Project Supervisor Mrs. L. Yamuna,
Assistant Professor in CSE ( AI & ML ) Department, who deserves a special note of
thanks, for having extended his full co-operation and guidance throughout the project
when needed, and to materialized the project successfully.
We express our sincere gratitude and special thanks to our college Chairman
Dr. P. Krishna Rao, and Director Management Sri. M. V. Haranatha Babu and Vice
President Sri, M. Satish for providing us all the facilities that were required to complete
the project successfully.
We even wish to express our special thanks to our beloved Principal Dr. K.
Satyanarayana and Vice Principal Dr. G. Naresh, for fostering an environment of
learning and creativity in our project to be done in the college.
We express our deep sense of gratitude to Dr. A. Radha Krishna, Head of the
Department, for having shown keen interest at every stage of development of our
project and for our project and for guiding us in every aspect.
We wish to express our sincere heartful thanks to all our faculty members of the
Department for their valuable suggestions when needed in the project. Even we thank
all the teaching and non-teaching faculty of our college.
We are thankful for the resources provided by our Organization that enabled the
successful execution of this project.
Finally we would like to thank our parents and family members who motivated
us and boosted our morale whenever we are in need. Even sincere thanks to all of our
friends who shared their thoughts whenever needed in this project work.
Mutyala Vanitha 20A31A4219
Anaparthi Vineela 20A31A4202
Angara Navya Sri Alekhya 20A31A4203
Godavarthi Srujana 20A31A4209
Merugu Bhuvana Naga Priya 20A31A4218
ABSTRACT
Subjective paper evaluation is a tricky and tiresome task to do by manual labor.
Insufficient understanding and acceptance of data are crucial challenges while analyzing
subjective papers using Artificial Intelligence (AI). Several attempts have been made to
score students’ answers using computer science. However, most of the work uses
traditional counts or specific words to achieve this task. Furthermore, there is a lack of
curated data sets as well. This paper proposes a novel approach that utilizes various
machine learning, natural language processing techniques, and tools such as Wordnet,
Word2vec, word mover’s distance (WMD), cosine similarity, multinomial naive bayes
(MNB), and term frequency-inverse document frequency (TF-IDF) to evaluate descriptive
answers automatically. Solution statements and keywords are used to evaluate answers,
and a machine learning model is trained to predict the grades of answers. Results show that
WMD performs better than cosine similarity overall. With enough training, the machine
learning model could be used as a standalone as well. Experimentation produces an
accuracy of 88% without the MNB model. The error rate is further reduced by 1.3% using
MNB
Key words : Subjective answer evaluation, big data, machine learning, natural language
processing,word2vec.
TABLE OF CONTENTS
ACKNOWLEDGMENT iii
ABSTRACT iv
LIST OF FIGURES vi
Chapter 1. Introduction 1
Chapter 2. Literature Survey 2
Chapter 3. System Analysis 5
3.1 Existing System 5
3.2 Proposed System 5
3.3 Modules 6
3.4 System Architecture 9
3.5 Software requirement Specification 10
3.5.1 System Study 10
3.5.2 External Interface Requirements 12
Chapter 4. System Design 13
Chapter 5. Implementation 10
5. 1 Python 18
5.2 Source Code 25
Chapter 6. Testing 39
Chapter 7. Descriptive Answer Evaluation 45
Chapter 8. Conclusion 55
