科研成果详情

Traditional recommendation systems (RSs) aim to recommend items that are relevant to the user's interest. Unfortunately, the recommended items will soon become too familiar to the user and hence fail to arouse her interest. Discovery-oriented recommendation systems (DORSs) complement accuracy with discover utilities (DUs) such as novelty and diversity and optimize the tradeoff between the DUs and accuracy of the recommendations. Unfortunately, DORSs ignore an important fact that different users have different appetites for DUs. That is, highly curious users can accept highly novel and diversified recommendations whereas conservative users would behave in the opposite manner. In this paper, we propose a curiosity-based recommendation system (CBRS) framework which generates recommendations with a personalized amount of DUs to fit the user's curiosity level. The major contribution of this paper is a computational model of user curiosity, called Probabilistic Curiosity Model (PCM), which is based on the curiosity arousal theory and Wundt curve in psychology research. In PCM, we model a user's curiosity with a curiosity distribution function learnt from the user's access history and compute a curiousness score for each item representing how curious the user is about the item. CBRS then selects items which are both relevant and have high curiousness score, bounded by the constraint that the amount of DUs fits the user's DU appetite. We use joint optimization and co-factorization approaches to incorporate the curiosity signal into the recommendations. Extensive experiments have been performed to evaluate the performance of CBRS against the baselines using a music dataset from last.fm. The results show that compared to the baselines CBRS not only provides more personalized recommendations that adapt to the user's curiosity level but also improves the recommendation accuracy.