Sentiment polarity detection in bengali tweets using multinomial Naïve Bayes and support vector machines

Abstract

Sentiment analysis is an area of study that deals with extraction, identification or otherwise characterization of the sentiment content of written text units. Sentiment is meant by feelings-attitudes, emotions and opinions. Sentiment polarity detection is one of most popular sentiment analysis tasks. Now-a-days, blog posts, tweets and comments in Indian languages are available on the web in a large number. Sentiment analysis in Indian languages is relatively new area and research on sentiment analysis in Indian language domain is at the early stage. In this paper, we present a sentiment polarity detection approach that detects sentiment polarity of Bengali tweets using machine learning algorithms. Our proposed approach has been tested on the Bengali tweet dataset released for SAIL contest 2015. The experimental results show that performance of our proposed system is better than the best system participated in SAIL 2015 sentiment analysis contest.