MiSPOT: Enhanced Availability and Quality in Delivering Personalized M-Learning Linked to TV Programs

Abstract

The development of digital television for mobile devices brings in new possibilities for informal learning, by means of interactive educational services linked to the TV programs. Some systems exist in the m-learning literature that may automatically discover the most valuable services for each viewer at any time, matching information about his/her interests, context and needs, about the services available and about the TV programs that those services may be linked to. Most commonly, however, the reasoning process is performed by remote servers, which implies that the personalization features become unavailable in the frequent cases of sporadic or null access to a bidirectional communication channel. The alternative exists to do local reasoning in the mobile devices, but their limited computational power results in low personalization quality. In this paper, we solve these problems with a scalable approach to perform semantic reasoning in mobile devices, backed up by the bandwidth and robustness of the same broadcast networks that deliver the TV programs.