Sentiment Lexicon-Based Features for Sentiment Analysis in Short Text

Abstract

Sentiment lexicon-based features have proved their performance in recent work concerning sentiment analysis in Twitter. Automatic constructed lexicon features seem to be enough influential to attract the attention. In this paper, we propose a new metric to estimate the word polarity score, called natural entropy (ne), in order to construct a new sentiment lexicon based on Sentiment140 corpus. We derive six features from the new lexicon and show that (ne) metric outperforms the PMI metric which has been used for the same purpose. For evaluation, we build a state-of-the-art system for sentiment analysis in short text using a supervised classifier trained on several groups of features including n-gram, sentiment lexicons, negation, Z score and semantic features. This system has been one of the best systems in both tasks of SemEval-2015: Sentiment Analysis in Twitter and Aspect-Based Sentiment Analysis. We investigate the impact of the lexicon-based features extracted from existing manual and automatic constructed lexicons on the system performance and also the impact of the proposed metric (ne).