A Semantics-Based Approach Beyond Traditional Personalization Paradigms

The so-called recommender systems have become assistance tools indispensable to the users in domains where the information overload hampers manual searching processes. In literature, diverse personalization paradigms have been proposed to match the personal preferences of each user against the available items. All these paradigms are laid down on a common substratum that uses syntactic matching techniques, which greatly limit the quality of the offered recommendations due to their inflexible nature. To fight these limitations, this paper explores a novel approach based on reasoning about the semantics of both the users' preferences and considered items, by resorting to less rigid inference mechanisms borrowed from the Semantic Web. Our reasoning-based approach shape enhanced personalization strategies that migrate from the traditional syntactic proposals to the inference of semantic relationships between the users' interests and the available items. Thanks to the exploitation of semantics, the discovered relationships provide the recommender system with additional knowledge about the user's preferences, thus leading to more accurate suggestion processes.The flexibility and strength of our approach enable its application in multiple domains and personalization tools. Specifically, for testing and validation purposes, our semantics-based strategies have been incorporated and evaluated in several tools bound to the field of Digital TV, where viewers are exposed to overwhelming amounts of audiovisual contents and challenged by the plethora of interactive functionality provided by the current digital receivers. The achieved results have revealed both the scalable nature and the computational feasibility of our domain-independent personalization approach based on semantic reasoning.