Agent oriented media recommender system utilizing Smart multimedia

Conventional multimedia recommender systems treat multimedia as a passive file that plays no role in the computation. In this paper we introduce the concept of Smart multimedia at which the knowledge and the computation required to solve the recommendation problem is transferred to the multimedia itself. Hence, converting the multimedia into an autonomous computational entity that performs its own computation and is responsible for its own decisions concerning where it should be displayed. Our approach utilizes content-based recommendation, where the internal content semantics are captured through semantic level intelligence. Hence, it is very suitable to be used in personalized advertisements.