Adaptive user preference modeling and its application to in-flight entertainment

ABSTRACT

This paper first presents an adaptive user preference model for personalized service delivery systems. In this model, user preference is modeled by a two-layer tree with dynamic changeable structures. The top layer of the tree is used for modeling user's long term service preference. Each node represents user's long term evolving commitment to certain categories of service. The lower layer of the tree is used for modeling user spontaneous service requirement which depends on context of use. Each node relates one context of use to one or more desired service requirements. The tree is dynamically constructed by the formal relation definitions among nodes. The advantage of this structure is three folds: (1) it can not only model the user's long term but also spontaneous preference items. More over, the relations between all preference items are formally defined; (2) if the number of preference items is many, it is more efficient and easier to find the right preference items; (3) if the user desired service has been removed, the system can utilize the personalized hierarchy service structure of the preference tree to calculate and recommend similar services. After the introduction of the user preference modeling, an algorithm of how to build it is presented. Finally, we customized the user preference for personalized in-flight entertainment recommendation to validate its features.

REFERENCES

• 1: Oppermann R. 2005. From user-adaptive to context-adaptive information systems. i-com 3, 4--14.
• 2: Bartneck C., Masuoka A., Takahashi T., Fukaya T. 2006. The Learning Experience with Electronic Museum Guides. Psychology of Aesthetics, Creativity, and the Arts, 0(1), 18--25.
• 3: Pawn S. 2000. Music and Choice: adaptive systems and multimodal interaction, PhD thesis, Technical university of Eindhoven.
• 4: Pawn S., Eggen B. 2003. Realization and user evaluation of an automatic playlist generator, Journal of new music research, 2003, Vol. 32, No. 2. pp 179--192.
• 5: Mohit Goel , Sudeshna Sarkar, Web Site Personalization Using User Profile Information, Proceedings of the Second International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems, p.510-513, May 29-31, 2002
• 6: R. Etter , P. D. Costa , T. Broens, A Rule-Based Approach Towards Context-Aware User Notification Services, Proceedings of the 2006 ACS/IEEE International Conference on Pervasive Services, p.281-284, June 26-29, 2006 [doi>10.1109/PERSER.2006.1652242]
• 7: Shi X., Hua J. 2005. An adaptive preference learning method for future personalized TV. In proceeding of KIMAS 2005, Craig Thompson and Henry Hexmoor (Eds.), pp. 260--264.
• 8: Robert R. Korfhage, Query enhancement by user profiles, Proc. of the third joint BCS and ACM symposium on Research and development in information retrieval, p.111-121, November 1984, King's College, Cambridge
• 9: Alexander Pretschner , Susan Gauch, Ontology Based Personalized Search, Proceedings of the 11th IEEE International Conference on Tools with Artificial Intelligence, p.391, November 08-10, 1999
• 10: Giuseppe Amato , Umberto Straccia, User Profile Modeling and Applications to Digital Libraries, Proceedings of the Third European Conference on Research and Advanced Technology for Digital Libraries, p.184-197, September 22-24, 1999
• 11: Rolf Kraemer , Peter Schwander, Bluetooth based wireless Internet applications for indoor hot spots: experience of a successful experiment during CeBIT 2001, Computer Networks: The International Journal of Computer and Telecommunications Networking, v.41 n.3, p.303-312, 21 February 2003 [doi>10.1016/S1389-1286(02)00418-8]
• 12: Kim J. Y., Kim J. W., and Kim C. 2007. Ontology-Based User Preference Modeling for Enhancing Interoperability in Personalized Services, C. Stephanidis (Ed.): Universal Access in HCI, Part III, HCII 2007, LNCS 4556, pp. 903--912.
• 13: Liu H., Rauterberg M. 2007. Context-aware in-flight entertainment system. In: M. J. Dainoff (Ed.) Proceedings of Posters at HCI International: Part X (LNCS CD-Rom {ISBN 978-3-540-73332-4}, pp. 1249--1254), Springer.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.1 MODELS AND PRINCIPLES
      H.1.2 User/Machine Systems
          Subjects: Human factors

Additional Classification:
  H. Information Systems
  H.1 MODELS AND PRINCIPLES
      H.1.2 User/Machine Systems
          Subjects: Human information processing

General Terms:
Algorithms, Design, Human Factors, Languages, Verification

Keywords:
context-awareness, in-flight entertainment, user preference