Intensive maximum entropy model for sentiment classification of short text

Abstract

The rapid development of social media services has facilitated the communication of opinions through microblogs/tweets, instant-messages, online news, and so forth. This article concentrates on the mining of emotions evoked by short text materials. Compared to the classical sentiment analysis from long text, sentiment analysis of short text is sometimes more meaningful in social media. We propose an intensive maximum entropy model for sentiment classification, which generates the probability of sentiments conditioned to short text by employing intensive feature functions. Experimental evaluations using real-world data validate the effectiveness of the proposed model on sentiment classification of short text.