Avatar: Enhancing the Personalized Television by Semantic Inference

Abstract

The generalized arrival of Digital TV will lead to a significant increase in the amount of channels and programs available to end users, making it difficult to find interesting programs among a myriad of irrelevant contents. Thus, in this field, automatic content recommenders should receive special attention in the following years to improve assistance to users. Current approaches of content recommenders have significant well-known deficiencies that hamper their wide acceptance. In this paper, a new approach for automatic content recommendation is presented that considerably reduces those deficiencies. This approach, based on the so-called Semantic Web technologies, has been implemented in the AVATAR tool, a hybrid content recommender that makes extensive use of well-known standards, such as TV-Anytime and OWL. Our proposal has been evaluated experimentally with real users, showing significant increases in the recommendation accuracy with respect to other existing approaches.

Making the most of TV on the move: My newschannel☆

“…To be precise, this paper is related with our previous work in AVATAR [13,14], a semantic hybrid recommendation engine for fixed TV.…”

“…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).…”

“…Thus, for each subscriber in a stereotype it is obtained the distance between his/her rating vector and the rating vector of the stereotype distanceðV U i ; V S j ). This distance is obtained by applying the Pearson-r correlation [14,13]. Notice that to calculate the distance between two rating vectors it is not required that the same programs have been watched by both profiles.…”

“…4 The Private Data field in Content Fragment provides an extension point to specify private data, so neither the syntax nor the semantics are defined in the ESG specification. 5 matchðN; SÞ ¼ 1 #NS P #NS i¼1 SemSimðN; n i Þ:DOIðn i Þ, where n i is the ith news content in the stereotype ontology-profile S, DOI(n i ) is the level of interest of S regarding n i , #N S is the total number of programs included in the ontology-profile S, and SemSim is the metric proposed in [14,13]. the IP platform and its corresponding NSG i is fragmented and packetized to this address.…”

A flexible semantic inference methodology to reason about user preferences in knowledge-based recommender systems

“…9 The degrees of interest (named DOI indexes) belong to the range [À1, 1] and can be specified by the user or inferred automatically by the recommender system. Specifically, the value of the DOI index corresponding to a program recommended by AVATAR depends on several factors, such as the user's reply to the suggestion (accept or reject), the percentage of the program viewed by the user, and the time elapsed until the user decides to view the recommended program [6].…”