Togetherness: Multiple Pedagogical Conversational Agents as Companions in Collaborative Learning

  • Yugo Hayashi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8474)


This study investigates the design of effective interaction using pedagogical conversational agents (PCAs) as companions in collaborative learning activities. Specifically, we focus on the use of embodied PCAs that evoke social awareness and engagement from human learners. In controlled experiments, paired collaborative learners were selectively accompanied by “peer-advisor” PCAs in a set of learning activities. Results show that learners who engaged with multiple PCAs gained a better understanding of target concepts than those using a single PCA. Furthermore, learners who engaged PCAs playing different collaborative roles (e.g., “mentor” and “expert”) outperformed those who engaged PCAs without distinct roles. The implications of these results are explored and directions for future study are discussed.


Pedagogical Conversational Agents Collaborative Learning Explanation Activities Social Facilitation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Vygotsky, L.S.: Mind in Society: The Development of Higher Psychological Processes. Harvard University (1978)Google Scholar
  2. 2.
    Lave, J., Wenger, E.: Situated Learning - Legitimate Peripheral Participation. Cambridge University Press (1991)Google Scholar
  3. 3.
    Kumar, R., Rose, C.: Architecture for building conversational agents that support collaborative learning. IEEE Transactions on Learning Technologies 4(1), 21–34 (2011)CrossRefGoogle Scholar
  4. 4.
    Graesser, A., McNamara, D.: Self-regulated learning in learning environments with pedagogical agents that interact in natural language. Educational Psychologist 45(4), 234–244 (2010)CrossRefGoogle Scholar
  5. 5.
    Baylor, A.L., Kim, Y.: Simulating instructional roles through pedagogical agents. International Journal of Artificial Intelligence in Education 15(1), 95–115 (2005)Google Scholar
  6. 6.
    Baylor, A.L., Ryu, J.: The API (Agent Persona Instrument) for Assessing Pedagogical Agent Persona. In: Lassner, D., McNaught, C. (eds.) Proc. World Conference on Educational Multimedia, Hypermedia and Telecommunications, pp. 448–451 (2003)Google Scholar
  7. 7.
    Gulz, A., Haake, M.: Design of animated pedagogical agents: A look at their look. International Journal of Human-Computer Studies 63(4), 322–339 (2006)CrossRefGoogle Scholar
  8. 8.
    Kim, Y., Baylor, A.L., Shen, E.: Pedagogical agents as learning companions: The impact of agent emotion and gender. Journal of Computer Assisted Learning 23(3), 220–234 (2007)CrossRefGoogle Scholar
  9. 9.
    Heidig, S., Clarebout, G.: Do pedagogical agents make a difference to student motivation and learning? Educational Research Review 6(1), 27–54 (2011)CrossRefGoogle Scholar
  10. 10.
    Chi, M., Leeuw, N., Chiu, M., Lavancher, C.: Eliciting self-explanations improves understanding. Cognitive Science 18(3), 439–477 (1994)Google Scholar
  11. 11.
    Okada, T., Simon, H.: Collaborative discovery in a scientific domain. Cognitive Science 21(2), 109–146 (1997)CrossRefGoogle Scholar
  12. 12.
    Shirouzu, H., Miyake, N., Masukawa, H.: Cognitively active externalization for situated reflection. Cognitive Science 26(4), 469–501 (2002)CrossRefGoogle Scholar
  13. 13.
    Holmes, J.: Designing agents to support learning by explaining. Computers and Education 48(4), 523–547 (2007)CrossRefGoogle Scholar
  14. 14.
    Moreno, R., Mayer, E.: Role of guidance, reaction, and interactivity in an agent-based multi-media game. Journal of Educational Psychology 97(1), 117–128 (2005)CrossRefGoogle Scholar
  15. 15.
    Hayashi, Y.: Learner-support agents for collaborative interaction: A study on affect and communication channels. In: Proc. 10th International Conference on Computer Supported Collaborative Learning, pp. 232–239 (2013)Google Scholar
  16. 16.
    Salomon, G.: Distributed Cognition: Psychological and Educational Considerations. Cambridge University Press, New York (2001)Google Scholar
  17. 17.
    Miyake, N.: Constructive interaction and the interactive process of understanding. Cognitive Science 10, 151–177 (1986)CrossRefGoogle Scholar
  18. 18.
    Hayashi, Y., Miwa, K., Morita, J.: A laboratory study on distributed problem solving by taking different perspectives. In: Proc. 28th Annual Conference of the Cognitive Science Society, pp. 333–338. Lawrence Erlbaum Associates (2006)Google Scholar
  19. 19.
    Hayashi, Y.: On pedagogical effects of learner support agents in collaborative interaction. In: Cerri, S.A., Clancey, W.J., Papadourakis, G., Panourgia, K. (eds.) ITS 2012. LNCS, vol. 7315, pp. 22–32. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  20. 20.
    Hayashi, Y.: Pedagogical conversational agents for supporting collaborative learning: Effects of communication channels. In: Proc. CHI EA 2013, pp. 655–660. ACM Press (2013)Google Scholar
  21. 21.
    Levine, D., Resnick, L.B., Higgins, E.T.: Social foundations of cognition. Annual Review of Psychology 44, 585–612 (1993)CrossRefGoogle Scholar
  22. 22.
    Alport, F.H.: The influence of the group upon association and thought. Journal of Experimental Psychology 3, 159–182 (1920)CrossRefGoogle Scholar
  23. 23.
    Lee, E.J., Nass, C.: Experimental tests of normative group influence and representation effects in computer-mediated communication when interacting via computers differs from interacting with computers. Human Communication Research 28(3), 349–381 (2002)Google Scholar
  24. 24.
    Beck, B.U., Wintermantel, M., Borg, A.: Principles of regulating interaction in teams practicing face-to-face communication versus teams practicing computer-mediated communication. Small Group Research 36, 499–536 (2005)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Yugo Hayashi
    • 1
  1. 1.Department of PsychologyRitsumeikan UniversityKita-kuJapan

Personalised recommendations