Using Latent Fine-Grained Sentiment for Cross-Domain Sentiment Analysis

Abstract

The authors investigate the problem task of multi-source cross-domain sentiment classification under the constraint of little labeled data. The authors propose a novel model which is capable of capturing both sentiment terms with strong or weak polarity from various source domains which are useful for knowledge transfer to unlabeled target domain. The authors propose a two-step training strategy with different granularities helping the model to identify sentiment terms with different degrees of sentiment polarity. Specifically, the coarse-grained training step captures the strong sentiment terms from the whole review while the fine-grained training step focuses on the latent fine-grained sentence sentiment which are helpful under the constraint of little labeled data. Experiments on a real-world product review dataset show that the proposed model has a good performance even under the little labeled data constraint.