Learning Bilingual Embedding Model for Cross-Language Sentiment Classification

Cross-lingual sentiment classification aims to leverage the rich sentiment resources in one language for sentiment classification in a different language. The biggest challenge of this task is how to eliminate the sentimental semantic gap between two languages. The use of machine translation cannot address this challenge very well due to the translation noises and the different expressions in different languages. In this study, we propose a Bilingual Sentiment Embedding model (BSE) to jointly embed the review texts in different languages into a joint sentimental semantic space. After embedding the reviews texts into the sentimental semantic space, the reviews texts in different languages can be easily classified with a classifier. Moreover, our proposed model can find in both languages the words with similar sentiment orientation or opposite sentiment orientation for a given word. Experimental results on a benchmark dataset show that our proposed model can outperform the state-of-the-art SCL method.