Improving Personalized Search with Dual-Feedback Network

Personalized search improves the quality of search results by modeling historical user behavior. In recent years, many methods based on deep learning have greatly improved the performance of personalized search. However, most of the existing methods only focus on modeling positive user behavior signals, which leads to incomplete user interest modeling. At the same time, the user's search behavior hides much explicit or implicit feedback information. For example, clicking and staying for a certain period represents implicit positive feedback, and skipping behavior represents implicit negative feedback. Intuitively, this information can be utilized to construct a more complete and accurate user profile. In this paper, we propose a dual-feedback modeling framework, which integrates multi-granular user feedback information to model the user's current search intention. Specifically, we propose a feedback extraction network to refine the dual-feedback representation in multiple stages. For enhancing the user's real-time search quality, we design an additional dual-feedback feature gating module to capture the user's real-time feedback in the current session. We conducted a large number of experiments on two real-world datasets, and the experimental results show that our method can effectively improve the performance of personalized search.