Within the information overload on the web and the diversity of the user interests, it is increasingly difficult for search engines to satisfy the user information needs. Personalized search tackles this problem by considering the user profile during the search. This paper describes a personalized search approach involving a semantic graph-based user profile issued from ontology. User profile refers to the user interest in a specific search session defined as a sequence of related queries. It is built using a score propagation that activates a set of semantically related concepts and maintained in the same search session using a graph-based merging scheme. We also define a session boundary recognition mechanism based on tracking changes in the dominant concepts held by the user profile relatively to a new submitted query using the Kendall rank correlation measure. Then, personalization is achieved by re-ranking the search results of related queries using the user profile. Our experimental evaluation is carried out using the HARD 2003 TREC collection and shows that our approach is effective.

No abstract

No abstract