Feature Extraction for Sentiment Classification on Twitter Data

In the last couple of years, there has been a rapid growth in the use of social networking websites. It is a medium having a huge amount of information where users can view the other users opinion, that are classified into different sentiment classes, which are increasingly growing as a key component in decision making. In this paper, we take one such popular microblog called Twitter. These tweets sometimes express opinions about different topics. People post real time messages about their opinions on different topics, discuss current issues, complain, and express positive sentiment for products they use in daily life. In this paper, we introduce a novel approach for automatically classifying the sentiment of tweets into positive, negative and neutral sentiment. Experimental evaluations show that our proposed techniques are efficient and perform better than previously proposed methods. In our research, we worked with English language however, the proposed technique can be used with any other language.