Exploring Reviews and Ratings on Reviews for Personalized Search

With the development of e-commerce, e-commerce websites become very popular. People write reviews on products and rate the helpfulness of reviews in these websites. Reviews written by a user and reviews rated by a user actually reflect a user's interests and disinterest. Thus, they are very useful for user profiling. In this paper, we explore users' reviews and ratings on reviews for personalized search and propose a review-based user profiling method. And we also propose a priority-based result ranking strategy. For evaluation, we conduct experiments on a real-life data set. The experimental results show that our method can significantly improve the retrieval quality.