Recommandation par combinaison de filtrage collaboratif et d'analyse de sentiments

Sentiment classification and recommender systems were until recently completely disjoint domains. Recommender systems exploit the users/items/rates matrix with omitting the available text information. Sentiment classification exploits text reviews and consumers rates to build models for document analysis. In this article we propose an unified model exploiting both text and user, items and rates to build a new and efficient recommender system. MOTS-CLÉS : Recommandation, Classification de Sentiments