AutoTutor Passes the Bystander Turing Test
Purchase or Subscription required for access
Purchase individual articles and papers
Subscribe for faster access!
Subscribe and receive access to 100,000+ documents, for only $19/month (or $150/year).
Already have access?
Individual Subscription
If you have an individual subscription, sign in here for access
Institutional Subscription
You don't appear to be accessing the site through a subscribing institution (your IP address is 18.119.133.43).
If your university, college, or library subscribes to LearnTechLib, you may be able access full text articles through a login page.
You can search for your instition by name or by location.
Authors
E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education, 2002 in Montreal, Canada ISBN 978-1-880094-46-4
Abstract
In this study, the Bystander Turing Test (BTT) paradigm is used to determine whether participants rate particular dialog moves in tutoring transcripts to be generated by a computer tutor, AutoTutor, or by a skilled human tutor. Results indicate that participants are unable to differentiate computer-generated moves from those generated by skilled human tutors. Participants did, however, view some dialog move categories to be more pedagogically effective than others regardless of whether the dialog move was generated by AutoTutor or by a skilled human tutor.
Citation
Erkel, M., Person, N. & Graesser, A. (2002). AutoTutor Passes the Bystander Turing Test. In M. Driscoll & T. Reeves (Eds.), Proceedings of E-Learn 2002--World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education (pp. 778-784). Montreal, Canada: Association for the Advancement of Computing in Education (AACE). Retrieved August 14, 2024 from https://www.learntechlib.org/p/15301.
© 2002 AACE