Ontology-Based User Profiles for Personalized Search

Abstract

As the number of Internet users and the number of accessible Web pages grows, it is becoming increasingly difficult for users to find documents that are relevant to their particular needs. Users who submit a query to a publicly available search engine must wade through hundreds of results, most of them irrelevant. The core of the problem is that, whether they are an eighth grade student or a Nobel Prize winner, the identical Web pages are selected and they are presented in the same way. In this chapter, we report on research that is aimed at providing search results tailored to individual users. In order to provide these personalized search results, the search engine exploits information about the user captured in automatically created user profiles. We compare a variety of mechanisms for automatically creating the user profiles, and discuss open issues in user profile creation, representation, and use.