INFORMATION FILTERING USING USERS CONTEXT ON BROWSING IN HYPERTEXT

Browsing is one of the most popular ways to gather information in data base with hypertext structure. In order to support a user to browse, m odeling of the user's interests is one of the most important issues. A lthough there are several promising methods to infer the interests fro m the user's browsing behavior, they assume that the interests are con sistent during the browsing. However, the user's interests are often s trongly dependent on the local context of the browsing. This paper des cribes a method to model the user's shifting interests from the browsi ng history. An information filtering method using the model of the int erests has been implemented. We call it 'context-sensitive filtering'. The results of an experimental evaluation, by real users' browsing fo r an encyclopedia in CD-ROM format, are also reported.