Using Custom Fuzzy Thesaurus to Incorporate Semantic and Reduce Data Sparsity for Twitter Sentiment Analysis

Abstract

Considerable research efforts have been devoted to Twitter sentiment analysis in recent years. Given the informal writing style of Twitter, there exists an endless variety of sound vocabulary, slogans, emoticons and special characters that can be used to express one's opinion in a maximum of 140-characters. This results in a sparsity problem making the training of machine learning classifiers from Twitter data a highly challenging task. In this work we propose using sentiment replacement of Twitter slogans and incorporating a fuzzy thesaurus for twitter sentiment classification in order to incorporate semantic as well as solve the sparsity problem. The experimental results show that the proposed method consistently outperforms the baselines in addition to some methods in the literature.