A Mini Project Report on
WhatsApp Chat Analysis
T.E. - I.T. Engineering
Submitted By
Kiran Suryawanshi - 19104035
Mayuresh Prabhu - 19104051
Tanmay Doshi - 19104024
Under The Guidance Of
Prof. Shafaque Syed
DEPARTMENT OF INFORMATION TECHNOLOGY
A. P. SHAH INSTITUTE OF TECHNOLOGY
G.B. Road, Kasarvadavali, Thane (W), Mumbai-400615
UNIVERSITY OF MUMBAI
Academic Year : 2021 - 22
CERTIFICATE
This to certify that the Mini Project report on WhatsApp Chat Analysis has been
submitted by Mayuresh Prabhu (19104051), Kiran Suryawanshi (19104035) and
Tanmay Doshi (19104024) who are a Bonafide students of A. P. Shah Institute of
Technology, Thane, Mumbai, as a partial fulfilment of the requirement for the degree
in Information Technology, during the academic year 2021-2022 in the satisfactory
manner as per the curriculum laid down by University of Mumbai.
Prof. Shafaque Syed
Guide
Prof. Kiran Deshpande Dr. Uttam D. Kolekar
Head of the Department - Information Technology Principal
External Examiner(s) : 1. ______________________________
2. ______________________________
Place: A. P. Shah Institute of Technology, Thane
Date:
TABLE OF CONTENTS
1. Introduction .......................................................................................................... 1
1.1. Purpose ........................................................................................................... 1
1.2. Objectives.......................................................................................................1
1.3. Scope .............................................................................................................. 1
2. Problem Definition .............................................................................................. 2
3. Proposed System .................................................................................................. 3
3.1. Features and Functionality ............................................................................ 3
4. Project Outcomes .................................................................................................. 4
5. Software Requirements ......................................................................................... 5
6. Project Design ....................................................................................................... 6
7. Project Scheduling…………………………….................................................7
8. Screenshot of Application.............................................................................. 8
9. Conclusion………………………………………………………………..….....14
References………………………………………………………………….………15
Acknowledgement………………………………………………………………………..…16
Chapter 1
Introduction
In the age of internet and socialization, communication and social media applications
like “WhatsApp” is common to be used by everybody. Often WhatsApp is the medium
where public use it to communicate with someone and also express their opinion on certain
topics. In the past it has become a key evidence in certain criminal cases and this application
can be use for marketing of product. So there is the necessity to develop an analytical report
on data transfers through chats which give answers to common question which is raised
during analysis.
Hence we are introducing a web application which can automate the process of
analysis of WhatsApp chats and gives the statistical report which will be contain plots and
sentimental prediction. In this application user can do analyse chats of a group, member
within the group and individual.
1.1 Purpose:
The purpose of this projects is to statistically analyze the whatsapp chat to answer
some of the common question which will help to develop the marketing strategy, helps in
investigation of the case and also automate the work of exploratory data analysis.
1.2 Objectives:
Following objectives of our project:
1. To provide user friendly interface for performing operations.
2. To pre-process the data in such a way that can be suitable to the model.
3. To automate the process of analysing the WhatsApp chat.
4. To have ability to analyse chats of group, individual participant within the group and
personal chats.
5. To develop a statistical and analytical report on WhatsApp chats.
6. To predict the sentiment of uploaded chats as positive, negative and neutral
1.3 Scope:
1. The application can be used by certain investigative officers to analyze skeptical
WhatsApp chats for investigation purpose.
2. It can also be used in digital marketing field which can help for making new
marketing strategy.
3. It can also make the job of exploratory analysis of chats much convenient as it
answers most of the common questions which arises during analysis which would be
feasible for data analyst and data scientist.
1
Chapter 2
Problem Definition:
● WhatsApp Chat Analyzer is a statistical analysis tool for WhatsApp chats.
● Working on the chat files that can be exported from WhatsApp it generates various plots
showing, for example: who is the busiest user in the group.
● We propose to employ dataset manipulation techniques to have a better understanding of
WhatsApp Chat present in our phones
2
Chapter 3
Proposed System
The system which have been proposed will get the WhatsApp Chat exported text file as
input which will than converted into dataframe. After converting into dataframe it will go
through some data manipulation and visualization process which will give all the
visualization and sentiment prediction as the output.
3.1 Features and functionality
3.2.1 Sidebar:
• It is only feature where user need to do some operations inorder to get output.
• It consist of text file uploader which will upload the data of chat into text file.
• After uploading user can genrate the statistical dashboard by clicking the button
“Show Analyses
• It will also contain a dropdown where user can analyse overall or individual
within the group chats
3.2.2 Statistical Dashboard:
It is the most important feature of our web app where user can see the
visualization of chats after the analyses.
Following are the visualisation which will be displayed:
a) Top Statistics – Displays the total count of messages, words , media files,
links shared.
b) Timeline Graph – It display the line graph which indicates activeness of
individual or group throughout year or daily.
c) Activity Map – It display the bar Graph of most busy day and month.
d) Weekly Activity Map – It visualize the heat map of days vs time.
e) Busy User Bar Graph – Displays top 5 most busy users.
f) Word Cloud
g) Emoji Analysis – Dataframe and Pie Chart
3.2.3 Sentiment Prediction:
• It is the part of statistical dashboard where it will be displayed at last.
• It will process all chats through natural language processing and give us the
prediction whether average nature of all chats are positive , negative or neutral
3
Chapter 4
Project Outcomes
User can upload the chats in .txt format as text file.
User can be able to analyse the chats of group, individual participant within the group and
personal chats.
User can generate the statistical and analytical report on WhatsApp Chat automatically.
User can also display the prediction sentimental nature of chats as positive, negative and
neutral.
4
Chapter 5
Software Requirements
We are using Python and it’s libraries for whole project. Python is a high-level,
general-purpose programming language. Its design philosophy emphasizes code
readability with the use of significant indentation. Its language constructs and object-
oriented approach aim to help programmers write clear, logical code for small- and large-
scale projects. It is the most preferred language used for Machine learning And Data
Science Projects.
Following are the Python libraries that we will be using:
• Streamlit : It is an open-source web application framework for Machine Learning
and Data Science Projects. We are using this library for developing our user
interface.
• Pandas: It is a software library written for the Python programming language for
data manipulation and analysis. In particular, it offers data structures and
operations for manipulating numerical tables and time series. We are using this
library for pre-processing the text file
• Matplotlib: It is a comprehensive library for creating static, animated, and
interactive visualizations in Python. We are using this library to visualize the the
graphs and pie charts
• Seaborn: It is a Python data visualization library based on matplotlib. It provides a
high-level interface for drawing attractive and informative statistical graphics. We
have used this library to visualize the modern and advanced heat map graph.
• Natural language tool kit : It is a leading platform for building Python programs to
work with human language data. It provides easy-to-use interfaces to over 50
corpora and lexical resources such as WordNet, along with a suite of text
processing libraries for classification, tokenization, stemming, tagging, parsing,
and semantic reasoning, wrappers for industrial-strength NLP libraries, and an
active discussion forum. We have used this library for calculating the polarity
scores of each chats and giving the sentimental prediction as positive, negative and
neutral.
5
Chapter 6
Project Design
Fig 6.1: Conceptual Block Diagram
Fig 6.2: Flow of Module
6
Chapter 7
Project Scheduling Template
Sr.
Group Member Time duration Work to be done
No
1st week of March
Preprocessing part
1
Mayuresh Prabhu
2nd week of March
Creating Visualiztion method and model
2 Tanmay Doshi 1st week of April
Creating User Interface
3 Kiran Suryawanshi 2nd week of April Integrating visualization methods and
model into application
7
Chapter 8
Screenshot of applications
Fig 7.1: Main User Interface
Fig 7.2: Top Statistics
8
Fig 7.3: Monthly Timeline
9
Fig 7.4: Daily Timeline
Fig 7.5: Activity Map
10
Fig 7.6: Weekly Activity Map
Fig 7.7: Most Busy User
11
Fig 7.8: Most Common Word
Fig 7.9: Word Cloud
12
Fig 7.10: Emoji Analysis
Fig 7.11: Sentiment Prediction
13
Chapter 9
Conclusion:
In Conclusion, it can be said that the capabilities of the WhatsApp
application and the power of the python programming language in implementing
whatever network data analysis intended, cannot be overemphasized.This project
was able to create an analysis of a WhatsApp group chat and visual representation
of chats(i.e which are most active participant,total count of messages, wordcloud
of chats).On Serious note, this System has the ability to analyze any WhatsApp
group data input into it.
The Application can be upgraded to perform Topic Modeling(i.e topic of the
chat can be decided using contents). It can also be upgraded to perform sentiment
analysis on images using image processing. Since our application is only
analyzing english text for sentiment prediction we can further upgrade it for
regional languages.
14
References
• https://chatilyzer.com/
• https://streamlit.io/
• https://www.analyticsvidhya.com/blog/2021/04/whatsapp-group-chat-analyzer-using-python/
15
ACKNOWLEDGEMENT
This project would not have come to fruition without the invaluable help of our guide
Prof. Shafaque Syed We express our gratitude towards our HOD Prof. Kiran
Deshpande, and the Department of Information Technology for providing us with the
opportunity as well as the support required to pursue this project. We would also like to
thank our teacher Prof. Nahid Shaikh who gave us her valuable suggestions and ideas
when we were in need of them. We would also like to thank our peers for their helpful
suggestions.
16
17
