Joint Aspect Discovery, Sentiment Classification, Aspect-Level Ratings and Weights Approximation for Recommender Systems by Rating Supervised Latent Topic Model

抄録

Textual product reviews posted by previous shoppers have been serving as an important source of information that helps on-line shoppers to make their decisions. However, reading through all the reviews of a product is usually a time-demanding and frustrating task, especially when those reviews deliver conflicting information. Therefore, it is of great practical value to develop techniques to automatically generate brief but accurate summaries for the numerous reviews on shopping websites. There are currently two main research streams in review mining: one is joint aspect discovery and sentiment classification, the other one is aspect-level ratings and weights approximation. There exist a number of models in each of the two areas. However, no previous work that aims to solve the two problems simultaneously has been proposed. In this paper we propose Rating Supervised Latent Topic Model to integrate the two problems into an unified optimisation problem. In the proposed model, we employ a latent topic model for aspect discovery and sentiment classification and use a regression model to approximate aspect-level ratings and weights based on the output of the topic model. We test the proposed model on a review dataset crawled from Amazon.com. The preliminary experiment results show that the proposed model outperforms a number of state-of-the-art models by a considerable margin.