Exploitation of user profile in the information retrieval based on Bayesian approach

摘要

To satisfy the user information needs, the use of his/her profile is adopted in the information retrieval process. Our goal is to build and exploit the user profile in search process. To achieve this goal, we adopt a Bayesian network as a strategy for personalized search since it provides a clear formalism to model qualitatively and quantitatively information types, namely, a user query, documents, index terms, and user's interests. In this paper, we present a Bayesian network model that captures the relationships between this information to evaluate the relevance as matching relationships between documents, user's interest and query concepts. An experimental evaluation was designed to appraise the exploitation impact of the user profile defined by his/her interests on the search results relevance.