User model elicitation and enrichment for context-sensitive personalization in a multiplatform tv environment

With the rising integration of more and more online data sets with various hardware platforms, such as set-top boxes, mobile phones, it becomes increasingly crucial to have intelligent systems guiding the user through the maze of data. A necessity in such systems is a comprehensive user model which allows the system to know how and what the user might expect. In iFanzy, a context-sensitive personalized TV guide, we amass such a user model by monitoring the user's actions and behavior and extensively making use of Semantic Web techniques to interpret these activities and offer in the right moment the right content to the user. We focus on solving the 'cold start' problem by importing user data from external to iFanzy online applications. This is realized by exploiting background ontological knowledge to map the imported concepts, so that iFanzy can minimize the effort in accumulating a complete user model.

[1]  Ah-Hwee Tan,et al.  Dynamically-optimized context in recommender systems , 2005, MDM '05.

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

[3]  Yoav Shoham,et al.  Fab: content-based, collaborative recommendation , 1997, CACM.

[4]  Lora Aroyo.  Distributed Personalization: Bridging Digital Islands in Museum and Interactive TV , 2008, ERCIM News.

[5]  Von-Wun Soo,et al.  A personalized restaurant recommender agent for mobile e-service , 2004, IEEE International Conference on e-Technology, e-Commerce and e-Service, 2004. EEE '04. 2004.

[6]  Konstantinos Chorianopoulos,et al.  Personalized and mobile digital TV applications , 2006, Multimedia Tools and Applications.

[7]  Federica Cena,et al.  Towards a Tag-Based User Model: How Can User Model Benefit from Tags? , 2007, User Modeling.

[8]  Omer F. Rana,et al.  Deriving ratings through social network structures , 2006, First International Conference on Availability, Reliability and Security (ARES'06).

[9]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[10]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[11]  Alfred Kobsa,et al.  Personalized Digital Television: Targeting Programs to Individual Viewers (Human-Computer Interaction Series, 6) , 2004 .

[12]  Jerry R. Hobbs,et al.  An ontology of time for the semantic web , 2004, TALIP.

[13]  Ellen M. Voorhees,et al.  Building a question answering test collection , 2000, SIGIR '00.

[14]  Oren Etzioni,et al.  Adaptive Web Sites: an AI Challenge , 1997, IJCAI.

[15]  Lora Aroyo,et al.  SenSee Framework for Personalized Access to TV Content , 2007, EuroITV.

[16]  Stefan Arbanowski,et al.  Context-aware, ontology-based recommendations , 2006, International Symposium on Applications and the Internet Workshops (SAINTW'06).

[17]  Alfred Kobsa,et al.  The Adaptive Web, Methods and Strategies of Web Personalization , 2007, The Adaptive Web.

[18]  Lora Aroyo,et al.  RSS-Based Interoperability for User Adaptive Systems , 2008, AH.

[19]  Tim O'Reilly,et al.  What is Web 2.0: Design Patterns and Business Models for the Next Generation of Software , 2007 .

[20]  Yoav Shoham,et al.  Fab: content-based, collaborative recommendation.(Special Section: Recommender Systems) , 1997 .

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

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

[23]  Barry Smyth,et al.  PTV: Intelligent Personalised TV Guides , 2000, AAAI/IAAI.

[24]  Wolfgang Wörndl,et al.  Utilizing Physical and Social Context to Improve Recommender Systems , 2007, 2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops.