A Comparative study on sentimental analysis of messages in a WhatsApp group using VADER , textblob and hybrid ensemble model

Computer Engineering

The social landscape changes on a regular basis due to the rapid growth in the usage of social media platforms like Facebook, Instagram and X. WhatsApp has become an integral part of our daily lives. WhatsApp is a messaging application that facilitates the transmission of text messages, audio messages, video messages and other compatible files. Schools and colleges are increasingly using WhatsApp as a primary communication tool. The purpose of this study is to analyse WhatsApp group chats among students to evaluate the emotional messages sent and received by college students. Machine learning ensemble algorithms are more suitable for analysing such kind of data when compared to lexicon based VADER (Valence Aware Dictionary and sentiment Reasoner) and textblob. In the present paper, we suggest a ensemble technique that is based on Random forest with Adaboost and SVM with Adaboost using a pre-trained embedding approach. This ensemble method learns to automatically extract features for sentiment analysis and classifies WhatsApp messages or chats into two polarity of positive or negative. The model we propose to implement the result provides better performance on the benchmark dataset. Compared to the baseline machine learning methods, the performance of the ensemble method based on Adaboost has improved.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.