www.ijcrt.

org © 2024 IJCRT | Volume 12, Issue 5 May 2024 | ISSN: 2320-2882

Whatsapp Analyzer
Rizwana S, Shivraj M, Sidhesh M, Shakthivel A, Arsh P
SIES Graduate School of Technology, Nerul, Navi Mumbai.

Abstract: The proposed system is a whatsapp message analyzer that performs the users and group chat
analysis. Analyzing the user behavior with the given messages will be needed in many situations whether it
could for extracting the user interest, taking or picking up the point of discussion, understanding user attitude
and behavior. By extracting the meaningful text from conversation, a summary of data can be generated to
get the statics and summary of the conversation. With the application of machine learning algorithms,
semantic analysis is done to get the meaning and summary of the messages. the system provides a valuable
tool for users to gain insights into their WhatsApp chat history and understand their social interactions and
communication patterns better. The project implementation is user-friendly and efficient, making it accessible
to a wide range of users.
Keyword: whatsapp analyzer, text analysis, semantic analysis, chat summarization.

1 Introduction

Millions of people use the well-known instant messaging service WhatsApp globally. The app is a useful tool
for both personal and professional communication because it enables users to share messages, voice notes,
images, and videos with one another. With WhatsApp's rising fame, there is a growing demand for research
into the conversations that take place on the app. A software programme called WhatsApp Analyzer employs
data analysis methods to glean insights from WhatsApp conversations. By extracting the meaningful text
from conversation, a summary of data can be generated to get the statics and summary of the conversation.
These summary and extractions can be useful for analyzing the behaviors of a user or a group of users in the
conversations. These analysis is useful for many applications. The variety of applications include recalling of
chat summary, any key points discussed in the chat and focused point of interest etc. which can be useful for
social as well as security concerns.
WhatsApp analyzers can use various data analysis techniques such as natural language processing, sentiment
analysis, and network analysis to extract insights from WhatsApp conversations. These techniques allow
WhatsApp analyzer to identify key topics, track the sentiment of conversations, and visualize the social
network of users involved in a conversation.

2 Literature Review

There are other similar systems available that can analyze WhatsApp chat data and
provide insights. Some examples of such systems [1-6] are discussed as follows.
Chat Visualizer: Chat Visualizer is a web-based tool that allows users to upload their WhatsApp chat history
and analyze it to gain insights. The tool generates various visualizations, such as word clouds, message
frequency charts, and sentiment analysis graphs.
WAToolkit: WAToolkit is an open-source project that allows users to analyze their WhatsApp chat data using
Python. The project includes various scripts that can extract data from a chat file and generate visualizations.
Chatistics: Chatistics is a Python package that provides tools for analyzing WhatsApp chat data. It can extract
data from a chat file and generate visualizations such as word clouds, message frequency graphs, and more.
IJCRT24A5655 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org o563
www.ijcrt.org © 2024 IJCRT | Volume 12, Issue 5 May 2024 | ISSN: 2320-2882
These systems use similar techniques and libraries to analyze WhatsApp chat data, such as Pandas, Matplotlib,
and Seaborn. However, the specific insights and visualizations that they provide may differ based on their
implementation and the preferences of their users.

3 Proposed System

The proposed system consists of various phases of implementation.

Fig.1 Flowchart of steps to be followed

Fig.2 system implementation phases

Data Collection: To begin the analysis, the first step is to collect the data. In this project, the data is in the
form of a text file that contains the WhatsApp chat conversation. To export the chat conversation from the
WhatsApp application, follow these steps:

Open the chat you want to export in WhatsApp.

Tap the three-dot menu button in the upper right corner and select "More."

Select "Export Chat" from the menu.

Choose whether to include media or not, and then select "Email Chat" or "Export Without Media" to save the
chat as a text file.

Data Preprocessing: After the data has been collected, it needs to be preprocessed to make it usable for
analysis. The preprocessing step involves cleaning and formatting the data to remove unwanted characters,
such as emojis and special characters, and standardise the format of the chat conversation. This step is
necessary to ensure that the data can be analysed accurately and effectively. In the WhatsApp Chat Analysis
IJCRT24A5655 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org o564
www.ijcrt.org © 2024 IJCRT | Volume 12, Issue 5 May 2024 | ISSN: 2320-2882
project, the preprocessing step is done using Python's regular expressions (regex) module to extract and clean
the chat conversation.

Data Analysis: Once the data has been preprocessed, the next step is to analyse the data using Python. The
sample code provided in the repository uses the pandas library to read the text file into a DataFrame, which
is a two-dimensional table-like data structure. The DataFrame can then be used to perform various analyses,
such as calculating message counts, generating word clouds, and creating visualisations. Some of the common
types of analyses that can be performed on the chat conversation include:

Message count analysis: This involves counting the number of messages sent by each participant in the chat
conversation. It can help identify the most active participants in the conversation.

Word frequency analysis: This involves counting the frequency of words used in the chat conversation. It can
help identify the most common words used in the conversation.

Sentiment analysis: This involves analysing the tone and sentiment of the chat conversation. It can help
identify the overall mood and sentiment of the conversation.

Data Visualization: Once the analysis is complete, the results can be visualised using Python's matplotlib
library. The sample code in the repository provides examples of how to create various types of visualisations,
such as line graphs, bar charts, and scatter plots. The visualisations can be customised to fit the specific needs
of the analysis and to help communicate the results of the analysis to others. Data visualisation is an important
step in the analysis process because it allows for easy interpretation and communication of the results.

Interpretation: The final step in the analysis process is to interpret the results. This involves looking at the
data and the visualisations to gain insights into the chat conversation. For example, the analysis could reveal
which participants in the chat were the most active, which words were used most frequently, or which times
of day were the most active. These insights can then be used to make decisions or draw conclusions about the
chat conversation. The interpretation step is important because it allows the analysis to be used for decision-
making or to gain a deeper understanding of the chat conversation.

4 SYSTEM IMPLIMENTATION

1-Data Collection
a) Open chat in WhatsApp
b) Tap three-dot menu button and select "More"
c) Select "Export Chat"
d) Choose to include media or not
e) Select "Email Chat" or "Export Without Media" to save as text file

2-Data Preprocessing
a) Use Python's regex module to extract and clean chat conversation
b) Remove unwanted characters and standardize format

3-Data Analysis
a) Use pandas library to read text file into a DataFrame
b) Perform message count, word frequency, and sentiment analysis

4-Data Visualization
a) Use matplotlib library to create visualizations, such as line graphs, bar charts, and scatter plots

5-Interpretation
a) Analyze the results of the analysis to gain insights into the chat conversation
b) Use insights for decision-making or deeper understanding.
IJCRT24A5655 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org o565
www.ijcrt.org © 2024 IJCRT | Volume 12, Issue 5 May 2024 | ISSN: 2320-2882

Fig.3 System implementation flowchart

Fig.5 Visualisations of data

Fig.6 Visualisations of data

5 Conclusion and Future Work

The project implementation involves extracting data from a WhatsApp chat text file, cleaning the data,
analyzing the data to provide insights, generating visualizations of the data, providing user interaction options,
generating output files, and providing a user-friendly interface for the user to interact with the program.
The project allows users to gain various insights into their chat history, such as identifying the most active
users in the chat, the most used emojis, and the most frequent words and phrases. The program provides
visualizations of the data, including line charts, bar charts, and pie charts, to help users understand the data
better.
The project implementation uses various Python libraries such as Pandas, Matplotlib, and Seaborn to create
visualizations of the data and provide interactive user options. The program generates output files in various
formats such as CSV, PDF, and PNG for the user to view and save.
Overall, the "WhatsApp Chat Analysis" project provides a valuable tool for users to gain insights into their
IJCRT24A5655 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org o566
www.ijcrt.org © 2024 IJCRT | Volume 12, Issue 5 May 2024 | ISSN: 2320-2882
WhatsApp chat history and understand their social interactions and communication patterns better. The
project implementation is user-friendly and efficient, making it accessible to a wide range of users.
The proposed web development platform has a lot of potential for future growth and expansion. Some possible
future directions for the platform include:
Integration with other web development tools and platforms, such as content management systems (CMS) or
web hosting services, to provide a more seamless and comprehensive learning experience.
Addition of more advanced and specialized projects, such as e-commerce websites, web applications, and
mobile-responsive designs, to help learners develop more advanced skills and stay up-to-date with the latest
trends in web development.
Incorporation of social learning features, such as discussion forums or peer review, to facilitate collaboration
and community-building among learners.
Development of a certification program or badge system to recognize and reward learners for their
achievements and skills.
Expansion of the platform to include other programming languages and frameworks, such as JavaScript,
React, or Angular, to cater to a broader audience of learners.
By pursuing these and other future directions, the proposed web development platform has the potential to
become a leading resource for learners looking to build their web development skills and stay up-to-date with
the latest trends and technologies in this field.

References

1. Elbagir, S. and Yang, J., 2020. Sentiment analysis on Twitter with Python’s natural language toolkit
and VADER sentiment analyzer. In IAENG Transactions on Engineering Sciences: Special Issue for the
International Association of Engineers Conferences 2019
2. Le, H.T. and Tran, N.T., 2018. A Sentiment Analyzer for Informal Text in Social Media. Journal of
Science and Technology, 131.
3. Suryawanshi, R., Rajput, A., Kokale, P. and Karve, S.S., 2020. Sentiment analyzer using machine
learning. International Research Journal of Modernization in Engineering Technology and
Science, 2(06), pp.1-12.Czajkowski, K., Fitzgerald, S., Foster, I., Kesselman, C.: Grid Information
Services for Distributed Resource Sharing. In: 10th IEEE International Symposium on High Performance
Distributed Computing, pp. 181–184. IEEE Press, New York (2001)
4. Kothandan, J. and Murugesan, P., 2021. ML based social media data emotion analyzer and sentiment
classifier with enriched preprocessor. Journal of Information Technology Management, 13(Special Issue:
Big Data Analytics and Management in Internet of Things),.
5. Garay, J., Yap, R. and Sabellano, M.J., 2019, February. An analysis on the insights of the anti-vaccine
movement from social media posts using k-means clustering algorithm and VADER sentiment analyzer.
In IOP Conference Series: Materials Science and Engineering (Vol. 482, No. 1, p. 012043). IOP
Publishing.
6. Bandi, A. and Fellah, A., 2019, September. Socio-analyzer: A sentiment analysis using social media
data. In Proceedings of 28th International Conference

IJCRT24A5655 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org o567