Y. Blanco-Fernández et al.: TripFromTV+: Targeting Personalized Tourism to Interactive Digital TV Viewers 953 by Social Networking and Semantic Reasoning Contributed Paper Manuscript received 03/09/11 Current version published 06/27/11 Electronic version published 06/27/11. 0098 3063/11/$20.00 © 2011 IEEE TripFromTV+: Targeting Personalized Tourism to Interactive Digital TV Viewers by Social Networking and Semantic Reasoning Yolanda Blanco-Fernández, Martín López-Nores, José J. Pazos-Arias, Jorge García-Duque, Manuela I. Martín-Vicente Abstract — Interactive Digital Television applications bring new value-added functionalities to viewers. In order to fight the current information overload, many of these applications offer personalization capabilities, by matching each viewer’s preferences against the available resources. This paper describes TripFromTV+, an interactive application that provides cut-price tailor-made tourist packages by helping the viewer to decide what to do and what to visit during a trip. Different from the existing approaches, this application automatically infers the viewer’s preferences from the kind of TV programs he/she enjoyed and from his/her activity in social networking sites, whose diffusion mechanisms are exploited to make the existing tourism offers known among the viewer’s contacts. The paper shows how interactive TV applications can incorporate content from the Internet, by creating seamlessly integrated presentations that allow the viewer to have the advantages of the network capabilities in the TV environment through domestic and mobile consumer devices 1 . Index Terms — Interactive Digital TV, personalization, Semantic Web, social networking, Web Services. I. INTRODUCTION The emergence of Interactive Digital Television (IDTV) has paved the way for applications that offer a huge amount and diversity of value-added functionalities to the viewers. Many of these applications are joined to personalization capabilities (see examples in [1]), in order to alleviate information overload by matching the available resources against each viewer’s preferences (modeled in personal profiles). In this paper, we describe an interactive application (named TripFromTV+) for DTV viewers, which can be downloaded via a backchannel and executed in domestic set-top boxes or even in handheld consumer devices. TripFromTV+ enhances the broadcast and viewing experience by showing a list of tourist attractions and resources, which are selected by considering the viewer’s particular preferences and the kind of TV programs he/she enjoyed in the past. 1 Work supported by the Spanish Ministry of Education and Science research Project TIN2010-20797. All the authors are with the Department of Telematics Engineering, University of Vigo, 36310 Vigo, Spain (e-mail: yolanda@det.uvigo.es, mlnores@det.uvigo.es, jose@det.uvigo.es, jgd@det.uvigo.es, mvicente@det.uvigo.es). Personalization capabilities are undoubtedly valuable in tourism because there are many options of destination, events and activities for someone who goes sightseeing, were it for adventure, cultural/historical or holiday reasons. Bearing this in mind, users often need advice about where to go and what to visit, what to see and what to do in a specific destination. Out of the scope of TV environment, there exist recommender systems that help to decide a travel plan, indicating places to visit, road maps, options for hotels and air companies (see [2]- [11]). Besides making trip planning much easier, existing systems support the user on move by providing ubiquitous access to tourism information of interest at anytime, from anywhere and any media, as detailed in [12]-[14]. The limitation of the current approaches lies within the fact that they request the users to enter manually their personal preferences and particular interests accurately, which is a cumbersome task. The research contribution of the paper is an approach that infers automatically the viewers’ particular interests by exploiting Digital TV capabilities and technologies joined to the Semantic Web and the Web 2.0:  First, the potential of the Semantic Web has to do with the fact that its technologies conceive semantics (i.e. the meaning of words) as a key fact to finding the way in the expanding web space, whereas web resources can only be discovered nowadays via keyword-based syntactic matching. The goal is to semantically connect isolated pieces of information to alleviate the user’s burden of finding, understanding and using tourism- related information sources [15]-[17].  Second, the irruption of the Web 2.0 has turned social networking sites into very influential elements in the users’ decision-making [18], since they resort to social communities to find opinions about accommodation options, tourist attractions to visit, etc. Grounding on this technological landscape, TripFromTV+ first discovers the preferences of the viewers (with no involvement from them) by automatically tracking the kind of DTV contents they enjoyed in the past. This makes it possible to learn valuable information to offer tourism recommendations, like interest in sports, nature, gastronomy or culture. Besides, if the viewer is logged in social networking sites, TripFromTV+ can access (with previous permission) to his/her profiles in these communities and infer knowledge about particular interests and preferences usable when recommending tourism resources.