Advertisement

A Subsequent Speaker Selection Method for Online Discussions Based on the Multi-armed Bandit Algorithm

  • Mio KuriiEmail author
  • Katsuhide Fujita
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11013)

Abstract

This paper proposes a method to select subsequent speakers in an online discussion, which is one of the important functions of facilitators, using the multi-armed bandit algorithm. Bandit algorithms can be applied to speaker determination by considering each participant as an arm of a slot machine and a facilitator as a player. We define a “discussion score” to evaluate each post, and it is then considered to be equivalent to the reward of the slot machine method. The discussion score of each post is defined based on the following three metrics: (1) Whether the post helps to settle a discussion or not. (2) How interested are the other participants in the post (3) The intention of the post. To consider conflict between participants, our method classifies the participants into groups and determines the next speaker based on clustering results. We demonstrate that our method can select participants who posted good ideas and opinions and promote participants to engage other participants by using questionnaires.

Keywords

Multi-armed bandit problem Decision support system Automated facilitator 

Notes

Acknowledgement

This work was supported by JST CREST Grant Number JPMJCR15E1, Japan.

References

  1. 1.
    Kotani, T., Seki, K., Matsui, T., Okamoto, T.: Development of discussion supporting system based on the “value of favorable words’ influence”. Jpn. Soc. Artif. Intell. 19(2), 95–104 (2004)Google Scholar
  2. 2.
    Kuleshov, V., Precup, D.: Algorithms for the multi-armed bandit problem. J. Mach. Learn. Res. 1, 1–48 (2000)Google Scholar
  3. 3.
    Nakahara, T., Ouchi, A., Uno, T., Hamuro, Y.: Extracted opinions from twitter using bipartite graph polishing. In: The 30th Annual Conference of the Japanese Society for Artificial Intelligence, pp. 1–4 (2016)Google Scholar
  4. 4.
    Nihei, F., Hayashi, Y., Nakano, Y.: Detecting discussion state shifts in group discussions. In: The 28th Annual Conference of the Japanese Society for Artificial Intelligence, pp. 1–4 (2014)Google Scholar
  5. 5.
    Ohmoto, Y., Toda, Y., Ueda, K., Nishida, T.: Analyses of the facilitating behavior by using participant’s agreement and nonverbal behavior. In: 2011 Information Processing Society of Japan, pp. 3659–3670 (2011)Google Scholar
  6. 6.
    Ontanon, S.: Bandit algorithms in game tree search: application to computer renju. J. Artif. Intell. Res. 58, 665–702 (2017)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Villara, S.S., Bowden, J., Wason, J.: Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges. Stat. Sci. 30(2), 199–215 (2015)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Tokyo University of Agriculture and TechnologyTokyoJapan

Personalised recommendations