Auteurs
Résumé
Dans cet article nous proposons une approche de recherche d’information (RI) qui
Abstract
In this paper we propose an information retrieval (IR) approach which takes into account the social content associated with a resource to measure its a priori relevance to a query. We show how these characteristics, which are of the form of actions (social signals) such as the number of ’like’ and ‘share’, can be combined to quantify social properties such as popularity and reputation. We propose to model these properties as a priori probabilities that we integrate into a language model. We evaluated the effectiveness of our approach on the IMDb dataset containing 32706 documents and their social characteristics collected from several social networks. Our experimental results are very promising and show the interest of integrating social properties in search model to enhance IR.