Improved Sentiment Classification by Multi-Modal Fusion

摘要

Sentiment Analysis (SA) is the task of detecting people's emotions from their written text. Many algorithms have been studied for that purpose, with different authors claiming one or the other as better by a given metric. In recent years, the focus of SA has shifted to online text and microblog text, messages so short that good analysis becomes difficult that the choice of algorithm becomes critical. In this paper, we propose that a choice is not necessary at all. Instead, we show that a fusion of multiple algorithms to create a multi-modal SA system is a preferable approach.