Learning Sentence Representation for Emotion Classification on Microblogs

Abstract. This paper studies the emotion classification task on microblogs. Given a message, we classify its emotion as happy, sad, angry or surprise. Ex-isting methods mostly use the bag-of-word representation or manually designed features to train supervised or distant supervision models. However, manufactur-ing feature engines is time-consuming and not enough to capture the complex linguistic phenomena on microblogs. In this study, to overcome the above prob-lems, we utilize pseudo-labeled data, which is extensively explored for distant su-pervision learning and training language model in Twitter sentiment analysis, to learn the sentence representation through Deep Belief Network algorithm. Exper-imental results in the supervised learning framework show that using the pseudo-labeled data, the representation learned by Deep Belief Network outperforms the Principal Components Analysis based and Latent Dirichlet Allocation based rep-resentations. By incorporating the Deep Belief Network based representation into basic features, the performance is further improved