A new method of information filtering for the digital library is presented in this paper. The method has three outstanding merits: Firstly,it accommodates hybrid model of information filtering which conquer the disadvantages of content based and collaborative filtering; Secondly,Ontology-driven user profiles have been constructed in order to get user interests; Thirdly, information resources are organized with ontologies so as to reach the goal of semantically querying and high performance matching mechanisms.
刘柏嵩. 信息过滤研究*[J]. 现代图书情报技术, 2003, 19(6): 23-26.
Liu Baisong. A Study on Information Filtering for the Digital Library. New Technology of Library and Information Service, 2003, 19(6): 23-26.
[2]Perschner,A.Ontology based personalized search [MS.Thesis].Lawrence,KS:University of Kansas,1999:4-17
[3]Prem Melville.Content-boosted collaborative filtering for improved recommendations.In Proceedings of AAAI-2002,Edmonton,Canada,July 2002:187-192
[4]Wu,Y.H.etal.Enabling personalized recommendation on the web based user interests and behaviors.In proceedings of the 11th international workshop on research issues in data engineering,Heidelberg,GERMANY,April2001:17-24
[5]Claypool,M.,Le et al.Implicit interest indicators.In Proceedings of the ACM intelligent user interfaces conference(IUI),SantaFe,NM,USA,January 2001:14-17
[6]Andrew I.Schein et al.Methods and metrics for cold-start recommendations.In Proceedings the 25th annual International ACM SIGIR Conference on Research and Development in Information Retrieval,August2002:37-46
[7]Middleton et al..Exploiting Synergy between Ontologies and Recommender Systems.In Proceedings Semantic Web Workshop of WWW2002,Hawaii,USA,May2002:34-43