ICLS 2000 Proceedings

Designing AutoTutor to be an Effective Conversational Partner

Natalie K. Person
Department of Psychology
Rhodes College
2000 N. Parkway
Memphis, TN 38112
Email: Person@rhodes.edu

Arthur C. Graesser and the Tutoring Research Group
Department of Psychology, University of Memphis
Memphis, TN 38152
a-graesser@memphis.edu
http://mnemosyne.csl.psyc.memphis.edu/home/graesser/

Abstract: AutoTutor is an automated computer literacy tutor that participates in a conversation with the student. This paper describes the conversational features that have been incorporated into AutoTutor to improve his performance as a conversational partner. We depict AutoTutor's dialog move options in the Dialog Advancer Network (DAN). The DAN illustrates how AutoTutor adapts his dialog moves to the preceding student turn as well as how AutoTutor gives the floor back to the student. We also discuss how AutoTutor conforms to conversational norms, provides appropriate emotional responses, and appears interested in the student's conversational input.

Keywords: tutoring, discourse, artificial intelligence, pedagogy, modeling, cognitive science

Preferred Citation Format:
Person, N.K., & Graesser, A.C. (2000). Designing AutoTutor to be an Effective Conversational Partner. In B. Fishman & S. O'Connor-Divelbiss (Eds.), Proceedings of the Fourth International Conference of the Learning Sciences (pp. 246-253). Mahwah, NJ: Erlbaum.

Click here to download the full version of this paper in PDF form.