Downsizing Semantic Reasoning to Fixed and Mobile DTV Receivers

Semantic reasoning is being increasingly applied in digital TV as a means to provide personalized information services. The pioneering initiatives have opted to place the personalization engines in the service providers´ side, because the semantic mechanisms exceed - by far - the computational power of DTV receivers. Unfortunately, this approach has the drawback that it can expose data about the users´ interests and preferences to commercial entities, raising severe legal and ethical obstacles. Moreover, in a domain where most of the information is transmitted through broadcast, there are many cases of intermittent, sporadic or null access to a return channel, which make the personalization features unavailable if lodged remotely. With these problems in mind, this paper introduces an architectural approach to deliver personalized DTV services, downsizing a semantic reasoning process to match the capabilities of fixed and mobile receivers. Preliminary experiments are reported, showing up to what point the enhanced privacy and availability impinge on personalization quality.