Modèle d'accès personnalisé à l'information basé sur les Diagrammes d'Influence intégrant un profil utilisateur évolutif
Nesrine Zemirli · HAL (Le Centre pour la Communication Scientifique Directe) · 2008
The goal of personalization in information retrieval is to tailor the search engine results to the specific goals, preferences and general interests of the users. This thesis presents a novel IR model able to integrate the user in the process of information access. Our contribution is particularly based on the belief that personalized retrieval is a decision making problem. For this reason, we propose to apply influence diagrams which are an extension of Bayesian networks to such problems, in order to solve the hard problem of user based relevance estimation. The basic underlying idea is to substitute the traditional relevance function which measures the degree of matching document-query, a function indexed by the user. In our approach, the user is profiled using his long-term interests. More precisely the user profiling is performed by managing the user search history using statistical based operators in order to highlight the user short-term interests seen as surrogates for building the long-term ones. The method focuses on the use of both user relevance point of view on familiar words in order to infer and express his interests and the use of a correlation metric measure in order to update them. In order to validate our model, we propose furthermore a novel evaluation protocol suitable for the personalized retrieval task. The test collection is an expansion of the standard TREC test data with user's profiles, obtained using a learning scenario of the user's interests. The experimental results show that our personalized retrieval model is effective.