Chapter 5 TV PERSONALIZATION SYSTEM Design of a TV Show Recommender Engine and Interface

The arrival of PVRs (Personal Video Recorders)—tape less devices that allow for easy navigation and storage of TV content—and the availability of hundreds of TV channels in US homes have transformed the task of selecting something to watch into a content overload problem. In order to ease this content overload, we pursued three related research themes. First, we developed a recommender engine that tracks users’ TV-preferences and delivers accurate content recommendations. Second, we designed a user interface that allows easy navigation of selections and supports inputs required by the recommender engine. Finally, we explored the importance of gaining users’ trust in the recommender by automatically generating explanations for content recommendations. In our user tests, our smart user interface came out tops beating TiVo’s interface and TV Guide, in terms of usability, fun, and quick access to relevant content. Further, our approach of combining multiple recommender ratings—resulting from various machine-learning methods— using neural networks has produced very accurate content recommendations.

[1]  F. Javier Lerch,et al.  How do we trust machine advice , 1989 .

[2]  Michael J. Pazzani,et al.  Learning Collaborative Information Filters , 1998, ICML.

[3]  John Zimmerman,et al.  Exposing profiles to build trust in a recommender , 2002, CHI Extended Abstracts.

[4]  Duco A. D. Das,et al.  Recommender Systems for TV , 1998 .

[5]  Lawrence R. Wheeless,et al.  THE MEASUREMENT OF TRUST AND ITS RELATIONSHIP TO SELF‐DISCLOSURE , 1977 .

[6]  John Riedl,et al.  Explaining collaborative filtering recommendations , 2000, CSCW '00.

[7]  Barry Smyth,et al.  Surfing the Digital Wave Generating Personalised TV Listings using Collaborative, Case-Based Recommendation , 1999 .

[8]  John Zimmerman,et al.  TV Personalization System , 2004, Personalized Digital Television.

[9]  James Lull,et al.  Inside Family Viewing : Ethnographic Research on Television's Audiences , 1990 .

[10]  John Zimmerman,et al.  TV Content Recommender System , 2000, AAAI/IAAI.

[11]  Patrick Baudisch,et al.  TV Scout: Guiding Users from Printed TV Program Guides to Personalized TV Recommendation , 2002 .

[12]  Liliana Ardissono,et al.  Architecture of a system for the generation of personalized Electronic Program Guides , 2001 .

[13]  B. J. Fogg,et al.  The elements of computer credibility , 1999, CHI '99.

[14]  J. Ross Quinlan,et al.  Learning Efficient Classification Procedures and Their Application to Chess End Games , 1983 .

[15]  Kristian J. Hammond,et al.  A Case-Based Approach to Knowledge Navigation , 1994, IJCAI.

[16]  Jeho Nam,et al.  Personalized Contents Guide and Browsing based on User Preference , 2002 .

[17]  Justine Cassell,et al.  Relational agents: a model and implementation of building user trust , 2001, CHI.

[18]  Fabio Bellifemine,et al.  User Modeling and Recommendation Techniques for Personalized Electronic Program Guides , 2004, Personalized Digital Television.

[19]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[20]  Han Kohar,et al.  Double agent—presentation and filtering agents for a digital television recording system , 1998, CHI Conference Summary.

[21]  John Zimmerman,et al.  A Multi-Agent TV Recommender , 2001 .