Improving Review Representations with User Attention and Product Attention for Sentiment Classification
This work addresses sentiment classification for online reviews, offering an incremental improvement by better handling user and product influences.
The paper tackled the problem of sentiment classification in reviews by proposing a framework that separately encodes user and product information with individual attention mechanisms, resulting in improved performance over state-of-the-art methods on IMDB and Yelp datasets.
Neural network methods have achieved great success in reviews sentiment classification. Recently, some works achieved improvement by incorporating user and product information to generate a review representation. However, in reviews, we observe that some words or sentences show strong user's preference, and some others tend to indicate product's characteristic. The two kinds of information play different roles in determining the sentiment label of a review. Therefore, it is not reasonable to encode user and product information together into one representation. In this paper, we propose a novel framework to encode user and product information. Firstly, we apply two individual hierarchical neural networks to generate two representations, with user attention or with product attention. Then, we design a combined strategy to make full use of the two representations for training and final prediction. The experimental results show that our model obviously outperforms other state-of-the-art methods on IMDB and Yelp datasets. Through the visualization of attention over words related to user or product, we validate our observation mentioned above.