“…AVATAR has been deployed in the past both as a provider-side recommendation engine (remotely in a centralized service) and as a receiver-side recommendation engine in a fixed TV context. In the first case, the ontology required for the reasoning techniques and the user profiles would be stored in a dedicated server, and the hybrid recommendation strategy would run remotely, too [13,14]. In the receiver-based scheme [27], the user's profile would be kept in the receiver, where the recommendation strategy is locally executed in a restricted way because of the unmanageability of the TV ontology in limited-resources devices (IDTV set-top-boxes in this case).…”