An Ontology-Based Profiling and Recommending System for Mobile TV

We present here a recommending system that has been developed for filtering TV content provided to mobile devices users. This recommender is fully based on ontologies, which are used to formalize both the user and her/his interests, and the audiovisual content. The developed ontologies allow matchmaking between user and content at different levels, based on three means to define user interests: according to categories, content description, or any combination of concepts defined in an ontology. The computation of user profiles relies on both explicit and implicit profiling, based on incremental learning of interest degrees from content usage.

[1]  Lora Aroyo,et al.  Semantic-based framework for personalised ambient media , 2006, Multimedia Tools and Applications.

[2]  Federica Cena,et al.  The Role of Ontologies in Context-Aware Recommender Systems , 2006, 7th International Conference on Mobile Data Management (MDM'06).

[3]  Pablo Castells,et al.  A Multi-Purpose Ontology-Based Approach for Personalized Content Filtering and Retrieval , 2006, 2006 First International Workshop on Semantic Media Adaptation and Personalization (SMAP'06).

[4]  Stéphane Betgé-Brezetz,et al.  A profiling engine for converged service delivery platforms , 2008, Bell Labs Technical Journal.

[5]  Pablo Castells,et al.  A Multi-Purpose Ontology-Based Approach for Personalized Content Filtering and Retrieval , 2006, 2006 First International Workshop on Semantic Media Adaptation and Personalization (SMAP'06).

[6]  James A. Hendler,et al.  The Semantic Web" in Scientific American , 2001 .

[7]  Boris Brandherm,et al.  Gumo - The General User Model Ontology , 2005, User Modeling.

[8]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[9]  Chrisa Tsinaraki,et al.  A multimedia user preference model that supports semantics and its application to MPEG 7/21 , 2006, 2006 12th International Multi-Media Modelling Conference.