Gradual Adaption Model for Information Recommendation Based on User Access Behavior

Jian Chen, Roman Shtykh, Qun Jin
In this study, we propose a gradual adaption model for information recommendation. This model is based on a set of concept classes that are extracted from Wikipedia categories and pages. Using the extracted information, data representing the users' information access behavior is collected by a unit of one day for each user, and analyzed in terms of short, medium, long periods, and by remarkable and exceptional categories. The proposed model is then established by analyzing the pre-processed
more » ... based on Full Bayesian Estimation. We further present experimental simulation results, and show the operability and effectiveness of the proposed model.