IJETRM Journal
580 California St., Suite 400
San Francisco, CA, 94104
TIME-SERIES DATA DRIVEN CONVERSATIONAL CHAT ANALYTICS
2024, Journal ijetrm
Sign up for access to the world's latest research
Abstract
As of 2024, WhatsApp has over 2 billion monthly active users, making it one of the most widely used messaging platforms globally. In addition, more than 100 billion messages are sent daily on the app, highlighting its integral role in daily communication (K. Kaushik and Y. Katara, 2022 [4]) This project aims on innovating an approach for analyzing WhatsApp chat data, providing users with a powerful tool to upload their chat histories in text format and receive detailed analytical reports through interactive visualizations. The application serves as an engine for comprehensive data analysis, examining critical aspects of WhatsApp conversations. Users can access insights related to the total number of messages exchanged, the overall word count, and the number of media files and links shared within the chats. Moreover, the tool features timeline analyses that display chat activity on a daily, weekly, and monthly basis, allowing contributors to understand patterns in their communications over time. It identifies the busiest days and months, helping users pinpoint when their conversations are most active, as well as highlighting the most engaged users within their groups. Additional features include an exploration of common and top words used in conversations and detailed emoji analysis, which offers a fun yet insightful view of emotional expressions in chats. The project is to be built using Python for robust data analysis and MERN stack or creating a user-friendly, interactive web application. This platform is particularly advantageous for institutions and businesses that leverage WhatsApp as a communication channel, as it offers a clear and concise view of customer interactions, marketing efforts, and group dynamics. By providing valuable insights into chat patterns and user engagement, the project empowers users to make informed, data-driven decisions, for improving communication effectiveness with scope for enhancing their overall business strategies. Ultimately, this project not only addresses the need for analytical tools in WhatsApp but also opens up avenues for optimizing user interactions and driving better outcomes in a fast-paced digital environment across multiple conversational avenues.
References (8)
- N. Blabst and S. Diefenbach, "WhatsApp and Wellbeing: A study on WhatsApp usage, communication quality and stress," Ludwig-Maximilians-University Munich, (2017).
- P. Anand, R. Gupta, et al, "Determining the Polarity and Statistics of Chat based on Sentiment Analysis," Galgotias University, (2022).
- R. K. Ravishankara, Dhanush, Vaisakh, and S. I. Srajan, "WhatsApp Chat Analyzer," Srinivas Institute of Technology Mangalore, (2020).
- K. Kaushik and Y. Katara, "Forensic Analysis of WhatsApp chat data," University of Petroleum and Energy Studies, Dehradun, India, (2022).
- J. Pomenkova, P. Koráb, and D. Štrba, "Text Data Pre-Processing for Time-series Modeling," Brno University of Technology, Brno, and Zeppelin University, Friedrichshafen, Lentiamo Prague, (2023).
- P. Debnath, S. Haque, S. Bandyopadhyay, and S. Roy, "Post-disaster Situational Analysis from WhatsApp Group Chats of Emergency Response Providers," IIEST, Shibpur, Indian Institute of Management Calcutta and Heritage Institute of Technology, Kolkata, (2016).
- R. Sujatha and K. Nimala, "Text-based Conversation Analysis Techniques on Social Media using Statistical Methods" SRM Institute of Science and Technology, Kattankulathur (2022).
- P. Awatramani, R. Daware, H. Chouhan, A. Vaswani, and S. Khedkar, "Sentiment Analysis of Mixed- Case Language using Natural Language Processing" Department of Computer Engineering, Vivekanand Education Society's Institute of Technology, Mumbai (2021).