Improving the Quality of the Personalized Electronic Program Guide

Abstract

Abstract. As Digital TV subscribers are offered more and more channels, it is becoming increasingly difficult for them to locate the right programme information at the right time. The personalized Electronic Programme Guide (pEPG) is one solution to this problem; it leverages artificial intelligence and user profiling techniques to learn about the viewing preferences of individual users in order to compile personalized viewing guides that fit their individual preferences. Very often the limited availability of profiling information is a key limiting factor in such personalized recommender systems. For example, it is well known that collaborative filtering approaches suffer significantly from the sparsity problem, which exists because the expected item-overlap between profiles is usually very low. In this article we address the sparsity problem in the Digital TV domain. We propose the use of data mining techniques as a way of supplementing meagre ratings-based profile knowledge with additional item-similarity knowledge that can be automatically discovered by mining user profiles. We argue that this new similarity knowledge can significantly enhance the performance of a recommender system in even the sparsest of profile spaces. Moreover, we provide an extensive evaluation of our approach using two large-scale, state-of-the-art online systems-PTVPlus, a personalized TV listings portal and Físchlár, an online digital video library system.

Collaborative video searching on a tabletop

“…Collaborative filtering is a lively research area and has been successfully employed in different domains such as TV programme recommendation [8], movie recommendation [9], joke recommendation [10] as well as commercially successful book recommendations on Amazon.com. Collaborative filtering is a good example of how information seeking can be supported in a collaborative way.…”

Semantic-based framework for personalised ambient media

“…Simple programme guides are thus likely to turn inefficient in terms of helping the user in choosing from an overwhelming amount of content [5,17]. This creates a challenge for media systems to support the user by intelligent recommendations to find the most relevant and interesting programmes.…”

“…Various filtering techniques for recommending movies have previously been explored by Masthoff [12], in which several user models are combined to create group filtering. Other related work is the PTVPlus online recommendation system for the television domain by O'Sullivan et al [17] and the Adaptive Assistant for Personalized TV by Yu and Zhou [22].…”

Interactive Searching and Browsing of Video Archives: Using Text and Using Image Matching

“…In this way, the user can start by browsing a news story detail, followed by jumping between related stories that the system automatically generates links to. Users can also access the news stories by automatic recommendation in which they indicate their preference for a particular news story using a 5-point thumbs-up and -down scale icons located beside each story, and as this information from the users accumulates over time the system can recommend some of the newly appeared stories as well as older stories in the archive to individual users by way of collaborative filtering [18].…”