Ensemble classifier for Twitter sentiment analysis

In this paper, we present a combination of different types of sentiment analysis approaches in order to improve the individual performance of them. These ones consist of (I) ranking algorithms for scoring sentiment features as bi-grams and skip-grams extracted from annotated corpora; (II) a polarity classifier based on a deep learning algorithm; and (III) a semi-supervised system founded on the combination of sentiment resources. By means assembling of the outputs of these approaches, we made a new evaluation in order to reach a complementation among them. The evaluations were based on the General Corpus of the TASS competition. The good results reached encourage us to continue studying the application of ensemble methods to resolve sentiment analysis problems.