User Interest Modeling and Self-Adaptive Update Using Relevance Feedback Technology

AbstractUser interest modeling is the core component of personalized service system. To improve the accuracy of the resulting model, this paper presents a method for modeling user's interest by collecting information of interactive behaviors and combining with implicit feedback techniques. This method also applies explicit feedback and Timeattenuation to self-adaptively update the interest model. It improves the accuracy of the model and will be pretty useful for personalized searching and filtering systems