Employing Emotion Keywords to Improve Cross-Domain Sentiment Classification

Abstract

Cross-domain classification is a challenging problem in the research of sentiment classification. In this study, we propose a novel approach to cross-domain sentiment classification by exploiting the classification knowledge from some emotion keywords. First, our approach uses some emotion keywords to extract the automatically-labeled samples with a high precision from the target area. Then, both the automatically-labeled samples from the target domain and the real labeled samples from the source domain are combined to be a new labeled data set. Third, all the labeled data and the unlabeled data in the target domain are used to perform cross-domain sentiment classification with a standard label-propagation algorithm. The empirical results demonstrate the effectiveness of our approach.