Advertisement

AI & SOCIETY

, Volume 20, Issue 2, pp 125–137 | Cite as

Designing conversational agents: effect of conversational form on our comprehension

  • Koji Yamashita
  • Hidekazu Kubota
  • Toyoaki Nishida
Original Article

Abstract

We have developed a broadcasting agent system, public opinion channel (POC) caster, which generates understandable conversational form from text-based documents. The POC caster circulates the opinions of community members by using conversational form in a broadcasting system on the Internet. We evaluated its transformation rules in two experiments. In experiment 1, we examined our transformation rules for conversational form in relation to sentence length. Twenty-four participants listened to two types of sentence (long sentences and short sentences) with conversational form or with single speech. In experiment 2, we investigated the relationship between conversational form and the user’s knowledge level. Forty-two participants (21 with a high knowledge level and 21 with a low knowledge level) were selected for a knowledge task and listened to two kinds of sentence (sentences about a well-known topic or sentences about an unfamiliar topic). Our results indicate that the conversational form aided comprehension, especially for long sentences and when users had little knowledge about the topic. We explore possible explanations and implications of these results with regard to human cognition and text comprehension.

Keywords

Agents Information providing Conversational form Comprehension Evaluative study 

References

  1. Azechi S, Fujihara N, Sumi K, Hirata T, Yano H, Nishida T (2000) Public opinion channel: A challenge for interactive community broadcasting. In: Ishida T, Isbister K (eds) Digital cities: technologies, experiences, and future perspectives. Springer-Verlag, New York, pp 427–441Google Scholar
  2. Ausubel D (1963) The psychology of meaningful verbal learning. Grune & Stratton, New YorkGoogle Scholar
  3. Ausubel D (1978) In defense of advance organizers: a reply to the critics. Rev Educ Res 48:251–257CrossRefGoogle Scholar
  4. Bransford JD, Johnson MK (1972) Contextual prerequisites for hierarchical retrieval schemes in recall of categorized word lists. J Verbal Learn Verbal Behav 11:717–726CrossRefGoogle Scholar
  5. Bromage BK, Mayer RE (1986) Quantitative and qualitative effects of repetition on learning from technical text. J Educ Psychol 78:271–278CrossRefGoogle Scholar
  6. Cassel J, Bickmore T, Campbell L, Vilhjalmsson H, Yan H (2000) Human conversation as a system framework: Design embodied conversational agents. In: Cassell J et al (eds) Embodied conversational agents. MIT Press, Cambridge, MA, pp 29–63Google Scholar
  7. van Dijk TA, Kintch W (1983) Strategies for discourse comprehension. Academic Press, New YorkGoogle Scholar
  8. Fukuhara T, Chikama M, Nishida T (2003) Supporting an experiment of a community support system: Community analysis and maintenance functions in the public opinion channel. In: Huysman M, Wenger E, Wulf V (eds) Communities and technologies. Kluwer Academic Publishers, Dordrecht, pp 347–367Google Scholar
  9. Kintch W (1998) Comprehension: a paradigm for cognition. Cambridge University Press, CambridgeGoogle Scholar
  10. Kubota H, Yamashita K, Fukuhara T, Nishida T (2002a) POC caster: Broadcasting agent using conversational form for Internet community. Trans Jpn Soc Artif Intelligence 17:313–321 (in Japanese with English abstract)Google Scholar
  11. Kubota H, Yamashita K, Nishida T (2002b) Conversational contents making comment automatically. In: Damiani E, Howlett RJ, Jain LC, Ichalkaranje N (eds) Frontiers in artificial intelligence and applications, vol 4. Knowledge-based intelligent information engineering systems & allied technologies Part 2. IOS Press, Amsterdam, pp 1326–1330Google Scholar
  12. Mayer RE, Dow GT, Mayer S (2003) Multimedia learning in an interactive self-explaining environment: what works in the design of agent-based microworlds? J Educ Psychol 95:806–812CrossRefGoogle Scholar
  13. Moreno R, Mayer RE, Spires HA, Lester JC (2001) The case for social agency in computer-based teaching: do students learn more deeply when they interact with animated pedagogical agents? Cogn Instr 19:177–213CrossRefGoogle Scholar
  14. Moreno R, Mayer RE (2002) Learning science in virtual reality multimedia environments: role of methods and media. J Educ Psychol 94:598–610CrossRefGoogle Scholar
  15. Nishida T, Fujihara N, Azechi S, Sumi K, Yano H, Hirata H (1999) Public opinion channel for communities in the information age. N Generation Computing 17:417–427CrossRefGoogle Scholar
  16. Pitchart JW, Anderson RC (1977) Taking different perspectives on a story. J Educ Psychol 69:309–315CrossRefGoogle Scholar
  17. Rickel J, Johnson WL (1998) STEVE: A pedagogical agent for virtual reality. In: Syncara KP, Wooldridge M (eds) Proceedings of the 2nd international conference on autonomous agents (AGENTS 98). ACM Press, New York, pp332–333Google Scholar
  18. Waddili PJ, McDaniel MA (1988) Illustrations as adjuncts to prose: a text-appropriate processing approach. J Educ Psychol 80:457–464CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2005

Authors and Affiliations

  • Koji Yamashita
    • 1
  • Hidekazu Kubota
    • 2
  • Toyoaki Nishida
    • 2
  1. 1.Keihanna Human Info-Communication Research CenterNational Institute of Information and Communications Technology Japan
  2. 2.Graduate School of InformaticsKyoto UniversitySakyo-kuJapan

Personalised recommendations