Learning Users Interests for Providing Relevant Information

Abstract

In this paper we present a system that attempts to learn the surfing user's interests without asking him for any feedback. The system uses the the user profile to conducts an independent search of the Internet, trying to find pages that the user have not read yet and might find interesting. The system consists of 3 modules: (1) The data-collection module, which collects the data to be processed into the user's profile. The collected data is URLs the user reads and e-mail messages the user authorizes the system to process. (2) The user profiling module, which processes the collected data into a user profile, using the clustering method Dynamic Suffix Tree Clustering (DSTC). (3) The search module, which explores the Internet, searching for web sites the profiled user might be interested in.