Paper Info
Title
A Web Recommender System Based on Dynamic Sampling of User Information Access Behaviors
Abstract
Abstract — In this study, we propose a Gradual Adaption Model for a Web recommender system. This model is used to track users’ focus of interests and its transition by analyzing their information access behaviors, and recommend appropriate information. A set of concept classes are extracted from Wikipedia. The pages accessed by users are classified by the concept classes, and grouped into three terms of short, medium and long periods, and two categories of remarkable and exceptional for each concept class, which are used to describe users’ focus of interests, and to establish reuse probability of each concept class in each term for each user by Full Bayesian Estimation as well. According to the reuse probability and period, the information that a user is likely to be interested in is recommended. In this paper, we propose a new approach by which short and medium periods are determined based on dynamic sampling of user information access behaviors. We further present experimental simulation results, and show the validity and effectiveness of the proposed system.
Year
DOI
Venue
2009
10.1109/CIT.2009.119
CIT (2)
Keywords
Field
DocType
concept class,appropriate information,web recommender system,information access behavior,medium period,user information access behavior,proposed system,reuse probability,user information access behaviors,dynamic sampling,full bayesian estimation,gradual adaption model,web pages,recommender system,encyclopedias,wikipedia,estimation theory,probability,data mining,estimation,internet
Recommender system,Concept class,Web page,Information retrieval,Reuse,Computer science,Information access,User information,Encyclopedia,Artificial intelligence,Machine learning,The Internet
Conference
Citations 
PageRank 
References 
1
0.35
17
Authors
3
Name
Order
Citations
PageRank
Jian Chen1184.76
Roman Y. Shtykh2839.35
Qun Jin335146.82