Exploiting Contextual Information in Recommender Systems for Interactive Digital TV

The advent of Digital TV has provided the growth in the volume of TV programs offered by TV operators. Consequently, the difficulty in finding the content the TV viewer wishes in a transparent way among the available TV programs increased. Within this scenario, the recommender systems stand out as a possible solution for this problem. However, the context has rarely been explored during the recommendation process. Thus, this paper presents a software infrastructure in an Interactive Digital TV environment to support context-aware personalized recommendation of TV programs – entitled PersonalTVware. To demonstrate and validate the functionalities in a usage scenario was developed a context-aware recommender system as a case study which uses the PersonalTVware.