Advertisement

Recommendation System Based on Interaction with Multiple Agents for Users with Vague Intention

  • Itaru Kuramoto
  • Atsushi Yasuda
  • Mitsuru Minakuchi
  • Yoshihiro Tsujino
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6762)

Abstract

We propose an agent-based recommendation system interface for users with vague intention based on interaction with multiple character agents, which are talking each other about their recommendations. This interface aims the user to make his/her intentions and/or potential opinions clear with hearing agents’ conversation about recommendations. Whenever the user hits on any opinion, he/she can naturally join the conversation for getting more favorite recommendation. According to the result of experimental evaluation, the system with proposed interface can introduce more recommendations without any additional frustrations than the conventional recommendation systems with single agent.

Keywords

Vague intention Character agent Recommendation Natural conversation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Rist, T., Andre, E., Baldes, S.: A flexible Platform for Building Applications with Life-Like Characters. In: the 8th International Conference on Intelligent User Interfaces (IUI 2003), pp. 158–165. ACM, New York (2003)Google Scholar
  2. 2.
    Shimazu, H.: ExpertClerk: Navigating Shoppers’ Buying Process with the Combination of Asking and Proposing. In: 7th International Joint Conference on Artificial Intelligence, pp. 1443–1448 (2001)Google Scholar
  3. 3.
    André, E., Rist, T.: Adding Life-Like Synthetic Characters to the Web. In: Klusch, M., Kerschberg, L. (eds.) CIA 2000. LNCS (LNAI), vol. 1860, pp. 1–13. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  4. 4.
    Sakamoto, T., Kitamura, Y., Tatsumi, S.: A Competitive Information Recommendation System and Its Rational Recommendation Method. Systems and Computers in Japan 38(9), 74–84 (2007)CrossRefzbMATHGoogle Scholar
  5. 5.
    Jameson, A.: More than the Sum of Its Members: Challenges for Group Recommendation Systems. In: The Working Conference on Advanced Visual Interfaces (AVI 2004), pp. 48–54. ACM, New York (2004)CrossRefGoogle Scholar
  6. 6.
    Mutlu, B., Shiwa, T., Kanda, T., Ishiguro, H., Hagira, N.: Footing in Human-Robot Conversations: How Robots might Shape Participant Roles Using Gaze Cues. In: the Fourth ACM/IEEE International Conference on Human-Robot Interaction (HRI 2009), pp. 61–68. ACM, New York (2009)Google Scholar
  7. 7.
    Shinozawa, K., Naya, F., Yamato, J., Kogure, K.: Differences in effect of robot and screen agent recommendations on human decision-making. International Jounal of Human-Computer Studies 62, 267–279 (2005)CrossRefGoogle Scholar
  8. 8.
    Isard, A., Brockmann, C., Oberlander, J.: Individuality and Alignment in Generated Dialogues. In: The Fourth International Natural Language Generation Conference, pp. 25–32. Association for Computational Linguistic, Sydney (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Itaru Kuramoto
    • 1
  • Atsushi Yasuda
    • 1
  • Mitsuru Minakuchi
    • 2
  • Yoshihiro Tsujino
    • 1
  1. 1.Kyoto Institute of TechnologyKyotoJapan
  2. 2.Kyoto Sangyo UniversityKyotoJapan

Personalised recommendations