Unsupervised feature learning for sentiment classification of short documents

Abstract

The rapid growth of Web information led to an increasing amount of user-generated content, such as customer reviews of products, forum posts and blogs. In this paper we face the task of assigning a sentiment polarity to user-generated short documents to determine whether each of them communicates a positive or negative judgment about a subject. The method we propose exploits a Growing Hierarchical SelfOrganizing Map to obtain a sparse encoding of user-generated content. The encoded documents are subsequently given as input to a Support Vector Machine classifier that assigns them a polarity label. Unlike other works on opinion mining, our model does not use a priori hypotheses involving special words, phrases or language constructs typical of certain domains. Using a dataset composed by customer reviews of products, the experimental results we obtain are close to those achieved by other recent works.