SubLex: Generating subjectivity lexicons using genetic algorithm for subjectivity classification of big social data

摘要

Web 2.0 enabled users to share their experiences, views, and opinions. One of the key products of Web 2.0 is Twitter, a social media site with hundreds of millions of users. These users tweet whatever they want to share with other people. The aim of this paper is to classify the tweets into subjective and objective tweets. We group words people use in Twitter into objective and subjective words, creating a subjectivity lexicon. We extract two meta-level features from tweets, which show their count of objective and subjective words. Then we classify the tweets by using these metafeatures. We use genetic algorithm for creating subjectivity lexicons from training datasets. Then we compare the results with baselines. The results show that genetic algorithm outperforms all the baselines in terms of accuracy in two assessed datasets. The created lexicons give insight about the objectivity and subjectivity of words and may be used to build sentiment lexicons.