Lokesh-kanna-18/Emotion-Analysis

# Emotion-Analysis This project aims to perform an emotion analysis of social media comments in Tamil. The emotional analysis is the classification task of mining emotions in texts, which finds use in various natural language applications such as reviews analysis in e-commerce, public opinion analysis, extensive search, personalized recommendation, healthcare, and online teaching. The goal of this task is to identify whether a given comment contains which emotions. In this project, we report the analysed findings in the "Emotion Analysis in Tamil." from the dataset collected The task aims to detect and recognize types of feelings through the expression of texts like Joy, Anger, Trust, Disgust, etc. We implemented transformer-based models like MuRIL, XLM-R and M-BERT to tackle the problem. MuRIL performed the best with a macro-averaged f1 score of 0.31.