A time-aware hybrid recommendation scheme combining content-based and collaborative filtering

摘要

In this paper, a hybrid recommendation scheme is proposed. We propose the definition of the time impact factor and apply it to the user preference modeling to ensure that the change of user interest can be captured. A user feedback mechanism is proposed in this work, we use the user's feedback information on recommended items to establish positive and negative feedback libraries, and filter the recommendation results based on the feedback mechanism. Finally, the logistic regression algorithm is utilized to aggregate the results of our proposed collaborative filtering and content-based. Also, the proposed feedback mechanism is used to filter the recommendation results.