Perceptible sentiment analysis of students' WhatsApp group chats in valence, arousal, and dominance space

Sentiment analysis is a vastly established domain for social media monitoring, feedback insights, and commercial or political campaigns. It allows us to gain an overview of the wider public opinion on certain topics. Nowadays, different platforms play crucial role in web-based sentiment emotion detection from distinct perspectives. Likewise, WhatsApp probably most popular messaging app, allowing users send messages, images, audio, videos. However, it still highly under-explored any type linguistic synthesis analysis. Like many other groups people, students use various purposes, even more since last two years pandemic phase, instance, class communication, study group etc. In this paper, we present novel approach analyze sentiments emotions valence, arousal, dominance space by classifying messages their chat. The emotional dimensions arousal (VAD) can derive person’s interest (attraction), level activation, perceived control particular situation textual communication. We propose vanilla SVM model fused with language classifier calculate each message's ratings. Finally, using classifier, classify ratings concerning degree VAD scale. data were analyzed qualitative content method. results form cumulative scale clustering reveal that students' mostly used sharing information, exchanging ideas, discussing issues, neutral positive viewpoints provided topics discussions.