Graph-based semi-supervised learning for cross-lingual sentiment classification

Abstract

Cross-lingual sentiment classification aims to use labelled sentiment data in one language for sentiment classification of text documents in another language. Most existing research works rely on automatic machine translation services to directly transfer information from one language to another. However, different term distribution between translated data and original data can lead to low performance in cross-lingual sentiment classification. Further, due to the existence of differing structures and writing styles between different languages, using only information of labelled data from a different language cannot show a good performance in this classification task. To overcome these problems, we propose a new model which uses sentiment information of unlabelled data as well as labelled data in a graph-based semi-supervised learning approach so as to incorporate intrinsic structure of unlabelled data from the target language into the learning process. The proposed model was applied to book review datasets in two different languages. Experiments have shown that our model can effectively improve the cross-lingual sentiment classification performance in comparison with some baseline methods.