An Approach of Re-Ranking Search Results based on a Dynamic and Hybrid Modeling of User Profile

The volume of data on the web grew in recent years. Then it becomes increasingly difficult for a user to access the right information in a short time. However, several works have been carried out with the aim of proposing algorithms to re-rank the user’s search results on the web by taking into account their profile. In this paper, we propose specific approach of re-ranking user search results based on a dynamic and hybrid modeling of user profile. Our approach takes into account the user interets identified during his browsing session and the history of his search on the web. We use a multi agent system to collect both explicitly and implicitly user data and to process this data to detect the user interets represented as ontological concepts. The experimentation of our model shows that it is able to re-rank user search results with a high accuracy than that given by the google search engine.