Advertisement

Abstract

Despite the fact that stereotyping has been used many times in recommender systems, little is known about why stereotyping is successful for some users but unsuccessful for others. To begin to address this issue, we conducted experiments in which stereotype-based user models were automatically constructed and the performance of overall user models and individual stereotypes observed. We have shown how concepts from data fusion, a previously unconnected field, can be applied to illustrate why the performance of stereotyping varies between users. Our study illustrates clearly that the interactions between stereotypes, in terms of their ratings of items, is a major factor in overall user model performance and that poor performance on the part of an individual stereotype need not directly cause poor overall user model performance.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ardissono, L., Gena, C., Torasso, P., Bellifemine, F., Difino, A., Negro, B.: User Modeling and Recommendation Techniques for Electronic Program Guides. In: Ardissono, L., Kobsa, A., Maybury, M. (eds.) Personalized Digital Television. Targeting programs to individual users. Kluwer Academic Publishers, Dordrecht (2004)Google Scholar
  2. 2.
    Beitzel, S., Jensen, E., Chowdhury, A., Frieder, O., Grossman, D., Goharian, N.: Disproving the Fusion Hypothesis: An Analysis of Data Fusion via Effective Information Retrieval Stategies. In: ACM Eighteenth Symposium on Applied Computing (SAC) (2003)Google Scholar
  3. 3.
    Gena, C., Ardissono, L.: On the construction of TV viewer stereotypes starting from lifestyle surveys. In: Bauer, M., Gmytrasiewicz, P.J., Vassileva, J. (eds.) UM 2001. LNCS, vol. 2109. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  4. 4.
    Lee, J.: Combining multiple evidence from different relevant feedback methods. Database Systems for Advanced Applications 4(4), 421–430 (1997)Google Scholar
  5. 5.
    Mitchell, T.: Machine Learning. McGraw-Hill, New York (1997)zbMATHGoogle Scholar
  6. 6.
    Rich, E.: Building and Exploiting User Models. Carnegie-Mellon University, Computer Science Department (1979)Google Scholar
  7. 7.
    Shapira, B., Shoval, P., Hanani, U.: Stereotypes in Information Filtering Systems. Information Processing and Management 33(3), 273–287 (1997)CrossRefGoogle Scholar
  8. 8.
    Vogt, C., Cottrell, G.: Predicting the Performance of Linearly Combined IR Systems. In: Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval, pp. 190–196 (1998)Google Scholar
  9. 9.
    Witten, I., Frank, E.: Data Mining. Morgan Kaufmann, San Francisco (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Zoë Lock
    • 1
  • Daniel Kudenko
    • 2
  1. 1.QinetiQ, Malvern Technology CentreMalvernUK
  2. 2.Department of Computer ScienceUniversity of YorkHeslington, YorkUK

Personalised recommendations