JudithJeyafreeda@Dravidian-CodeMix-FIRE2020: Sentiment Analysis of YouTube Comments for Dravidian Languages

Judith Jeyafreeda Andrew

Abstract: Sentiment Analysis is a process of identifying the tone of a given sentiment/opinion. It focuses on the polarity of the sentiments - positive, negative or neutral. In this paper, the goal is to identify sentiment polarity of a dataset of comments/posts in Dravidian Languages (Malayalam-English and Tamil-English) collected from social media. A new gold standard corpus for sentiment analysis for Dravidian languages (Malayalam-English and Tamil-English) is used in this paper. The analysis is performed as a multi-class classification problem. For this purpose, several well known machine learning models have been used. Based on the accuracy of each model obtained from the development set, the best model is chosen for prediction.