Showing papers by "Manuel Ramos-Cabrer published in 2010"

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

Abstract: 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.

Exploiting digital TV users' preferences in a tourism recommender system based on semantic reasoning

Abstract: Tourism recommender systems match the user preferences against the huge diversity of tourist resources, helping to decide where to go and what to do. Current approaches require the users to initialize manually their profiles by expressing their interests accurately, which is a very tedious process. We propose a system that automatically infers the users' preferences from their TV viewing histories, i.e., the tourism resources the users might appreciate are selected by considering the TV contents they enjoyed in the past. To this aim, we have developed a context-aware semantics-based recommendation strategy that considers both the users' preferences and the interests of like-minded individuals. The resulting recommendations shape a tailor-made on-move travel plan the users can access via (domestic and) handheld consumer devices.

Incentivized provision of metadata, semantic reasoning and time-driven filtering: Making a puzzle of personalized e-commerce

Abstract: e-Commerce recommender systems select potentially interesting products for users by looking at their purchase histories and preferences. In order to compare the available products against those included in the user's profile, semantics-based recommendation strategies consider metadata annotations that describe their main attributes. Besides, to ensure successful suggestions of products, these strategies adapt the recommendations as the user's preferences evolve over time. Traditional approaches face two limitations related to the aforementioned features. First, product providers are not typically willing to take on the tedious task of annotating accurately a huge diversity of commercial items, thus leading to a substantial impoverishment of the personalization quality. Second, the adaptation process of the recommendations misses the time elapsed since the user has bought an item, which is an essential parameter that affects differently to each purchased product. This results in some pointless recommendations, e.g. including regularly items that the users are only willing to buy sporadically. In order to fight both limitations, we propose a personalized e-commerce system with two main features. On the one hand, we incentivize the users to provide high-quality metadata for commercial products; on the other, we explore a strategy that offers time-aware recommendations by combining semantic reasoning about these annotations with item-specific time functions. The synergetic effects derived from this combination lead to suggestions adapted to the particular needs of the users at any time. This approach has been experimentally validated with a set of users who accessed our personalized e-commerce system through a range of fixed and handheld consumer devices.

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

Abstract: 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.

Enhancing TV programmes with additional contents using MPEG-7 segmentation information

Abstract: Interactive Digital TV offers a large amount of TV channels, as well as new contents that come along with the TV programmes. To take advantage of these additional contents and make them easily available to viewers, this paper proposes to offer additional contents linked to the segments of TV programmes by means of semantic relations obtained using MPEG-7 segmentation information. As a practical use of this work, we propose two different application fields: t-learning, with the aim of using TV programmes to engage viewers in education; and personalised advertising, whose goal is offering viewers products of their interest, maximising its effectiveness.

Semantic Query Validation in Guided-Based Systems: Assuring the Construction of Queries that Make Sense

Abstract: Semantic search importance is growing each day as millions of people around the world need to obtain objective and concrete information. Guided-based systems are an alternative to natural language systems regarding the query construction method. However, current guided-based systems perform query validation only at a syntactical level. In this paper we address the semantic validation of queries in order to avoid redundancy and incoherency, therefore preventing the formulation of queries that do not make sense.

Automatic Query Generation in Guided Systems: Natural Language Generation from Graphically Built Query

Abstract: Guided-based systems are an alternative to natural language systems regarding the query construction method. We present a new solution that bridges the gap between these two types of systems by providing a hybrid interface which combines a graphical query interface for query construction with the correspondent natural language expression automatically generated by the system.

Exploiting MPEG‐4 Capabilities for Personalized Advertising in Digital TV

Abstract: The object‐oriented vision of multimedia contents enabled by MPEG‐4 brings in an opportunity to revolutionize the state‐of‐the‐art in TV advertising. In this chapter, we discuss a model of “dynamic product placement” that consists of blending the TV programs with advertising material selected specifically for each individual viewer, with interaction possibilities to launch e‐commerce applications. We give an architectural overview of a system that realizes this idea, followed by details of the MPEG‐4 modules and the accompanying tools we have developed for Digital TV providers and content producers. Finally, we include a report of experiments that sustain the technical feasibility of the proposal.