VCU-TSA at SemEval-2016 Task 4: Sentiment analysis in Twitter

Abstract

The aim of this paper is to produce a methodology for analyzing sentiments of selected Twitter messages, better known as Tweets. This project elaborates on two experiments carried out to analyze the sentiment of Tweets from SemEval-2016 Task 4 Subtask A and Subtask B. Our method is built from a simple unigram model baseline with three main feature enhancements incorporated into the model: 1) emoticon retention, 2) word stemming, and 3) token saliency calculation. Our results indicate an increase in classification accuracy with the addition of emoticon retention and word stemming, while token saliency shows mixed performance. These results elucidate a possible classification feature model that could aid in the sentiment analysis of Twitter feeds and other microblogging environments.