Sentiment Classification on Twitter Data Using Support Vector Machine

Abstract

Sentiment analysis in Twitter has really engaged interest in field of research. Sentiment classification in Twitter deals with analyzing the tweets in terms of their sentiment polarity. The proposed method deals with twitter sentiment classification by employing a classification model of machine learning domain which makes use of different textual features viz. n-grams of twitter data. Also, we have used three different weighting schemes to understand the impact of weighting on classifier accuracy. Furthermore, a sentiment score vector of tweets is used to provide external knowledge in order to improve the performance of SVM classifier.