Decoding Digital Conversations: A Hybrid Sentiment Analysis Framework for WhatsApp Chat Behavioral Intelligence

Authors

  • Gaurav Pandey, N.K. Gupta, Binnu Paul, Mohit Paul

Keywords:

Sentiment Analysis, Rule-Based Method

Abstract

Everyone has a curiosity about what the one person thinks about the any other person, product or services while having a conversation and judging the other person can’t be done perfectly, so this work provides a way to use sentiment analysis between conversations. When talking with someone always has a question about the picture in the other person’s mind. The first step in this process is pre- processing of the data downloaded from the WhatsApp chat which is exported to a server. After that, sentiment analysis is performed on a single message and the sentiment of all messages is normalized for overall sentiment in the way it is suggested. In this work, we conduct an in-depth analysis of WhatsApp group chat dynamics using an advanced versatility of a hybrid sentiment analysis framework that can manifest the minimum steps of preprocess- ing, lexicon-based, generative AI, and ensemble scoring analysis. This research analyzes group communication patterns using a multifaceted methodology, examining the most active days, volumes of messages, contributions of users, influences from admins, group membership, frequency of individual postings, and frequent. Combining traditional rule-based sentiment techniques with sophisticated generative AI algorithms, the study gives an independent analysis of digital group dynamics and sheds light on more intricate group behaviour patterns and usage patterns. The approach utilizes a novel ensemble scoring framework that harmonizes lexicon-based sentiment analysis with contextually- aware AI mechanisms, producing unparalleled insights into the qualitative and quantitative aspects of group communication on the web.

Downloads

Download data is not yet available.

References

B. N. Iduh, “WhatsApp Network Group Chat Analysis Using Python Programming,” Int. J. of Latest Technology in Engineering, Management & Applied Science (IJLTEMAS), vol. 9, no. 2, pp. 1–5, 2020.

L. Anne, T. Nandan, M. Kunj, S. A. Kumar, G. Mahesh, and R. Sangeetha, “MQTT Based Android Chat Application for IoT,” SN Computer Science, vol. 3, no. 5, p. 402, 2022.

S. Elbagir and J. Yang, “Twitter sentiment analysis using natural language toolkit and VADER sentiment,” in Proc. Int. Multiconf. of Engineers and Computer Scientists, vol. 122, no. 16, 2019.

S. Zeb, U. Qamar, and F. Hussain, “Sentiment analysis on user reviews through lexicon and rule-based approach,” in Web Technologies and Applications: APWeb 2016 Workshops, Suzhou, China, Sept. 2016, pp. 55–63, Springer.

R. Khanam and A. Sharma, “Sentiment analysis using different machine learning techniques for product review,” in Proc. Int. Conf. on Compu- tational Performance Evaluation (ComPE), Dec. 2021, pp. 646–650, IEEE.

R. Haji, K. Daanyaal, G. Deval, and G. Rushikesh, “Rating prediction based on textual review: machine learning approach lexicon approach and the combined approach,” Int. Res. J. of Eng. and Technology (IRJET), vol. 6, no. 3, pp. 5437–5443, 2019.

C. Chandra and A. Kumar, “Sentiment Analysis Text Type Feedback System Using Artificial Intelligence,” 2020.

B. Liu, Sentiment Analysis and Opinion Mining. Springer Nature, 2022.

S. M. Mohammad and P. D. Turney, “Crowdsourcing a word–emotion association lexicon,” Computational Intelligence, vol. 29, no. 3, pp. 436–465, 2013.

W. Medhat, A. Hassan, and H. Korashy, “Sentiment analysis algorithms and applications: A survey,” Ain Shams Eng. J., vol. 5, no. 4, pp. 1093–1113, 2014.

M. Taboada, J. Brooke, M. Tofiloski, K. Voll, and M. Stede, “Lexicon- based methods for sentiment analysis,” Computational Linguistics, vol. 37, no. 2, pp. 267–307, 2011.

M. Mozafari, R. Farahbakhsh, and N. Crespi, “A BERT-based transfer learning approach for hate speech detection in online social media,” in Proc. Complex Networks and Their Applications VIII, Springer, 2020,

pp. 928–940.

S. Kiritchenko, X. Zhu, and S. M. Mohammad, “Sentiment analysis of short informal texts,” J. of Artif. Intell. Res., vol. 50, pp. 723–762, 2014.

A. T. Mahmood, S. S. Kamaruddin, R. K. Naser, and M. M. Nadzir, “A combination of lexicon and machine learning approaches for sentiment analysis on Facebook,” J. of System and Management Sciences, 2020.

G. Kaur and A. Sharma, “A deep learning-based model using hybrid feature extraction approach for consumer sentiment analysis,” J. of Big Data, vol. 10, no. 1, p. 5, 2023.

T. Islam et al., “Lexicon and Deep Learning-Based Approaches in Sen- timent Analysis on Short Texts,” J. of Computer and Communications, vol. 12, no. 1, pp. 11–34, 2024.

P. K. Novak, J. Smailovic´, B. Sluban, and I. Mozeticˇ, “Sentiment of emojis,” PLOS ONE, vol. 10, no. 12, e0144296, 2015.

Z. Ahmad, R. Jindal, A. Ekbal, and P. Bhattachharyya, “Borrow from rich cousin: transfer learning for emotion detection using cross-lingual embedding,” Expert Syst. with Appl., vol. 139, p. 112851, 2020.

S. Hassan, S. Shaar, and K. Darwish, “Cross-lingual emotion detection,”

arXiv preprint arXiv:2106.06017, 2021.

M. Agarla et al., “Semi-supervised cross-lingual speech emotion recog- nition,” Expert Syst. with Appl., vol. 237, p. 121368, 2024.

L. Wei et al., “A Lightweight Sentiment Analysis Framework for a Micro-Intelligent Terminal,” Sensors, vol. 23, no. 2, p. 741, 2023.

B. Paul, D. Rudrapal, K. Chakma, and A. Jamatia, “Multimodal Ma- chine Translation Approaches for Indian Languages: A Comprehensive Survey,” Journal of Universal Computer Science (JUCS), 2024.

Downloads

Published

05.05.2024

How to Cite

Gaurav Pandey. (2024). Decoding Digital Conversations: A Hybrid Sentiment Analysis Framework for WhatsApp Chat Behavioral Intelligence. International Journal of Intelligent Systems and Applications in Engineering, 12(21s), 4953 –. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/7503

Issue

Section

Research Article