Consensus vote models for detecting and filtering neutrality in sentiment analysis

Recently, interest in sentiment analysis has grown exponentially. Many studies have developed a wide variety of algorithms capable of classifying texts according to the sentiment conveyed in them. Such sentiment is usually expressed as positive, neutral or negative. However, neutral reviews are often ignored in many sentiment analysis problems because of their ambiguity and lack of information. In this paper, we propose to empower neutrality by characterizing the boundary between positive and negative reviews, with the goal of improving the model's performance. We apply different sentiment analysis methods to different corpora extracting their sentiment and, hence, detecting neutral reviews by consensus to filter them, i.e., taking into account different models based on weighted aggregation. We finally compare classification performance on single and aggregated models. The results clearly show that aggregation methods outperform single models in most cases, which led us to conclude that neutrality is key for distinguishing between positive and negative and, then, for improving sentiment classification.