Enhancement of creative aspects of a daily conversation with a topic development agent

  • Kazushi Nishimoto
  • Yasuyuki Sumi
  • Kenji Mase
Agent-Based Coordination
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1364)


Daily informal conversations are highly creative activities. However, it is hard for most ordinary creativity support systems and discussion support systems to deal with daily conversations because they are done in environments characterized as free. In this paper, we propose a topic-development agent that is adaptable to daily conversations and that enhances the creative aspects of the conversations by entering them as an equal participant with the human participants and keeping the conversation lively. This agent autonomously detects novel directions in which new topics can be developed in conversations, and provides a piece of information which can likely form the seed of a new topic. From the experimental results, it is suggested that this agent can provide timely information to introduce a new topic and that the agent has the ability to effectively coordinate the creative aspects of daily conversations.


Empty Space Divergent Thinking Text Object Global Topic Conversation Situation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Imai, K., Nonaka, L, and Takeuchi, H.: Managing the New Product Development Process, in 75th Anniversary Colloquium Productivity and Technology, Harvard Business School, Mar. (1984) 28–29Google Scholar
  2. [2]
    Conklin, J. and Begeman, M. L.: gIBIS: A Hypertext Tool for Exploratory Policy Discussion, Proc. of CSCW'88, (1988) 140–152Google Scholar
  3. [3]
    Streitz, N. A., Geibler, J., Haake, J. M., and Hol, J.: DOLPHIN: Integrated Meeting Support across Local and Remote Desktop Environments and Live-Boards, Proc. of CSCW '94, (1994) 345–358Google Scholar
  4. [4]
    Hori, K.: A model to explain and predict the effect of human-computer interaction in the articulation process for concept formation Information Modelling and Knowledge Bases, vol. 7, 1996.Google Scholar
  5. [5]
    Boden, M. A.: Agents and Creativity, Communications of The ACM, Vol. 37, No. 7, (1994) 117–121CrossRefGoogle Scholar
  6. [6]
    Sumi, Y., Ogawa, R., Hori, K., Ohsuga, S., and Mase, K.: Computer-aided communications by visualizing thought space structure, Electronics and Communications in Japan, J79-B-II, (1996) 1120–1129Google Scholar
  7. [7]
    Nishisato, S.: Analysis of Categorical Data: Dual Scaling and Its Applications, Univ. of Toronto press, (1980)Google Scholar
  8. [8]
    Saito, T., and Toriwaki, J.: New Algorithm for Euclidean Distance Transformation of An n-Dimensional Digitized Picture with Applications, Pattern Recognition, Vol. 27, No. 11, (1994) 1551–1566CrossRefGoogle Scholar
  9. [9]
    Nishimoto, K., Abe, S., and Mase, K.: Realtime topic transition detection for a free style dialog of an unspecified domain, Proc. of Symp. on Natural Language Processing Applications, Vol. 95, No. 6, Information Processing Society of Japan, (1995) 41–48 (in Japanese).Google Scholar
  10. [10]
    Nishimoto, K., Abe, S., and Mase, K.: Effectively-heterogeneous information extraction to stimulate divergent thinking, Proc. of Intl. Symp. of Creativity and Cognition 2, (1996) 156–163Google Scholar
  11. [11]
    Nakano, K.: Associatron — A Model of Associative Memory, IEEE Trans. on S.M.C., SMC-2, 3, (1972) 381–388Google Scholar
  12. [12]
    Edmonds, E. A., Candy, L., Jones, R., and Soufi, B.: Support for Collaborative Design: Agents and Emergence, Communications of The ACM, Vol. 37, No. 7, (1994) 41–47CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Kazushi Nishimoto
    • 1
  • Yasuyuki Sumi
    • 1
  • Kenji Mase
    • 1
  1. 1.ATR Media Integration & Communications Research LaboratoriesSoraku-gun, KyotoJapan

Personalised recommendations