Manuela I. Martín-Vicente

MiSPOT: dynamic product placement for digital TV through MPEG-4 processing and semantic reasoning

In an increasingly competitive market, stakeholders of the television industry strive to exploit all the possibilities to get revenues from advertising, but their practices are usually at odds with the comfort of the TV viewers. This paper presents the proof of concept of MiSPOT, a system that brings a non-invasive and fully personalized form of advertising to Interactive Digital TV, targeting both domestic and mobile receivers. MiSPOT employs semantic reasoning techniques to select advertisements suited to the preferences, interests and needs of each individual viewer, and then relies on multimedia composition abilities to blend the advertising material with the TV program he/she is viewing at any time. The advertisements can be set to launch interactive commercials, thus enabling means for the provision of t-commerce services. Evaluation experiments are described to show the technical viability of the proposal, and also to gauge the opinions of end users. Questions about the potential impact and exploitation of this new form of advertising are addressed too.

TripFromTV+: targeting personalized tourism to interactive digital TV viewers by social networking and semantic reasoning

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 viewers 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 viewers 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 viewers 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.

A semantic approach to avoiding fake neighborhhoods in collaborative recommmendation of coupons through Digital TV

Consumers are flooded with amounts of discount coupons, oftentimes for products that are far from their interests. This marketing custom is already rising on the Internet and is imminent in Digital TV, where the massive sending of coupons leads to their devaluation and consumer indifference. The computing capabilities of these media permit to alleviate this problem by means of recommender systems, which are very useful tools in application domains that suffer from information overload. However, current recommender systems overlook the diversity of products and services available in the market, which gives rise to forming fake neighborhoods in collaborative filtering strategies. In this paper, we apply semantic reasoning techniques to avoid such fake neighborhoods and, thereby, improve the recommendation process. Furthermore, taking advantage of the Digital TV medium, we propose matching the recommended coupons to TV contents semantically related with them, in order to increase their redemption.

Improving collaborative recommendation of coupons through Digital TV by semantic inference of users' reputation

Recommender systems have proven to be an effective response to the information overload problem, by identifying items the users may be interested in. Trust and reputation are being increasingly incorporated in collaborative recommender systems in order to improve their accuracy and reliability, using network structures in which nodes represent users and edges represent trust statements. However, current approaches require the users to provide explicit data (about which other users they trust or not) to form such networks. In this paper, we apply a semantic approach to automatically build implicit trust networks and, thereby, improve the recommendation results transparently to the users. Even though our approach is not limited to any specific domain, we illustrate it within the recommendation of promotional coupons through Digital TV, which can be accessed from domestic and mobile consumer devices.

Automatic Generation of Mashups for Personalized Commerce in Digital TV by Semantic Reasoning

The evolution of information technologies is consolidating recommender systems as essential tools in e-commerce. To date, these systems have focused on discovering the items that best match the preferences, interests and needs of individual users, to end up listing those items by decreasing relevance in some menus. In this paper, we propose extending the current scope of recommender systems to better support trading activities, by automatically generating interactive applications that provide the users with personalized commercial functionalities related to the selected items. We explore this idea in the context of Digital TV advertising, with a system that brings together semantic reasoning techniques and new architectural solutions for web services and mashups.

Context-Aware Recommender Systems Influenced by the Users’ Health-Related Data

This chapter provides an overview of past and current developments in the area of recommender systems, paying special attention to two concepts that we view as cornerstones to provide effective assistance to people during their daily lives: context awareness and health awareness. We will enumerate different dimensions of context that are handled nowadays to maximize the value of the information delivered to the users, and then explain the existing approaches to take health-related data into consideration. Finally, we will describe the main features of a mobile application we are developing that interacts with electronic health record repositories and manages location information to recommend commercial products to the users.

Semantics-driven recommendation of coupons through Digital TV: Exploiting synergies with social networks

The well-known marketing strategy of distributing discount coupons can greatly benefit from Digital TV. Its interactive capabilities allow incorporating a recommender system to make such distribution personalized (based on each viewers preferences), and also presenting the selected coupons attractively, related to the TV programs broadcast at any moment. In this paper, exploiting the possibilities that Web 2.0 offers, we propose a recommender system that goes one step further to increase coupon redemptions, by utilizing social networks as tools to add extra information to the system and reach new consumers.

Enhancing Recommender Systems with Access to Electronic Health Records and Groups of Interest in Social Networks

Recommender systems have been around for several years as tools intended to discover items that are likely to be of interest for the users, as inferred from profiles that gather information about web pages they visit, TV programs they watch or commercial products they purchase. In this paper, we introduce health-related aspects as a new dimension of the user profiles, enabling a number of features that may have a significant impact in the field of interactive services to the home. Specifically, we have enhanced an existing recommender system to process information stored in electronic health records and in groups of interest created within social networks. This has made it necessary to refine the recommendation logic in order to reckon the enabling/disabling nature of health-related data, and also to deal with the risks that arise from ignorance or commercial interest in the social context.

Avoiding Fake Neighborhoods in e-Commerce Collaborative Recommender Systems: A Semantic Approach

Recommender systems are very useful tools inapplication domains that suffer from information overload,offering the users suggestions they may be interested in.Owing to its business interest, e-commerce has become amajor domain in this research field, since identifying thoseproducts that the users will appreciate could increase users’consumption. However, current e-commerce recommendersystems overlook some implications of the great diversity ofproducts and services available in the market, giving rise toform fake neighborhoods in collaborative filtering strategies.In this paper, we propose applying semantic reasoning techniquesto solve this problem, thus improving, qualitativelyand computationally, the recommendation process.

Implicit Trust Networks: A Semantic Approach to Improve Collaborative Recommendations

Collaborative recommender systems suggest items each user may like or find useful basing on the preferences of other like-minded individuals. Thus, the main concern in a collaborative recommendation is to identify the most suitable set of users to drive the selection of the items to be offered in each case. To distinguish relevant and reliable users from unreliable ones, trust and reputation models are being increasingly incorporated in these systems, by using network structures in which nodes represent users and edges represent trust statements. However, current approaches require the users to provide explicit data (about which other users they trust or not) to form such networks. In this chapter, we apply a semantic approach to automatically build implicit trust networks and, thereby, improve the recommendation results transparently to the users.