《A Time Influence Analysis for Web Page Recommender System》.pdf

A Time Influence Analysis for Web Page Recommender System Chen-Chung Chi, Nai-Lung Tsao, Chin-Hwa Kuo Department of Computer Science and Information Engineering, Tamkang University ryanjih@.tw, beaktsao@, chkuo@.tw Abstract these browsing behavior models to fit in users’ demand. The design of the WPRS not only can save the time for In this paper, we propose a time weighting model to the users to searching some information they need in a generate a webpage recommendation list in a single website, but also can provide a personalized website for the visitors. We use this proposed model to information service for individual users based on their analyze the trend of users’ behavior, then generates a different browsing behavior models. webpage recommendation list depend on it. The time Most of the WPRS use some web usage mining weighting model provides a solution for a web page technique, such as association rules or its variants [4]. recommender system, find a better time interval to Association rules method can be used to extract generate a webpage recommendation list, therefore traversal patterns from a web server log and use the enhance the recommendation precision based on a traversal patterns to recommend web pages. However, given time interval. The experimental result shows if association rules is frequency sensitive, which means it we choose an appropriate time inter