To elicit or to tell

Does it matter

Min Chi, Pamela Jordan, Kurt VanLehn, Diane Litman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

While high interactivity has been one of the main characteristics of one-on-one human tutoring, a great deal of controversy surrounds the issue of whether interactivity is indeed the key feature of tutorial dialogue that impacts students' learning results. There are two commonly held hypotheses regarding the issue: a widely-believed monotonic interactivity hypothesis and a better supported interaction plateau hypothesis. The former hypothesis predicts increasing in interactivity causes an increase in learning while the latter states that increasing interactivity yields increasing learning until it hits a plateau, and further increases in interactivity do not cause noticeably increase in learning. In this study, we proposed the tactical interaction hypothesis which predicts beyond a certain level of interactivity, further increases in interactivity do not cause increase in learning unless they are guided by effective tutorial tactics. Overall our results support this hypothesis. However, finding effective tactics is not easy. This paper sheds some light on how to apply Reinforcement Learning to derive effective tutorial tactics.

Original languageEnglish (US)
Title of host publicationFrontiers in Artificial Intelligence and Applications
Pages197-204
Number of pages8
Volume200
Edition1
DOIs
StatePublished - 2009

Publication series

NameFrontiers in Artificial Intelligence and Applications
Number1
Volume200
ISSN (Print)09226389

Fingerprint

Reinforcement learning
Students

Keywords

  • Intelligent tutoring systems
  • Knowledge component
  • Natural language tutoring systems
  • Pedagogical tutorial tactics
  • Reinforcement learning

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Chi, M., Jordan, P., VanLehn, K., & Litman, D. (2009). To elicit or to tell: Does it matter. In Frontiers in Artificial Intelligence and Applications (1 ed., Vol. 200, pp. 197-204). (Frontiers in Artificial Intelligence and Applications; Vol. 200, No. 1). https://doi.org/10.3233/978-1-60750-028-5-197

To elicit or to tell : Does it matter. / Chi, Min; Jordan, Pamela; VanLehn, Kurt; Litman, Diane.

Frontiers in Artificial Intelligence and Applications. Vol. 200 1. ed. 2009. p. 197-204 (Frontiers in Artificial Intelligence and Applications; Vol. 200, No. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chi, M, Jordan, P, VanLehn, K & Litman, D 2009, To elicit or to tell: Does it matter. in Frontiers in Artificial Intelligence and Applications. 1 edn, vol. 200, Frontiers in Artificial Intelligence and Applications, no. 1, vol. 200, pp. 197-204. https://doi.org/10.3233/978-1-60750-028-5-197
Chi M, Jordan P, VanLehn K, Litman D. To elicit or to tell: Does it matter. In Frontiers in Artificial Intelligence and Applications. 1 ed. Vol. 200. 2009. p. 197-204. (Frontiers in Artificial Intelligence and Applications; 1). https://doi.org/10.3233/978-1-60750-028-5-197
Chi, Min ; Jordan, Pamela ; VanLehn, Kurt ; Litman, Diane. / To elicit or to tell : Does it matter. Frontiers in Artificial Intelligence and Applications. Vol. 200 1. ed. 2009. pp. 197-204 (Frontiers in Artificial Intelligence and Applications; 1).
@inproceedings{49633f834f404c2eb81add9b5fbf2fcb,
title = "To elicit or to tell: Does it matter",
abstract = "While high interactivity has been one of the main characteristics of one-on-one human tutoring, a great deal of controversy surrounds the issue of whether interactivity is indeed the key feature of tutorial dialogue that impacts students' learning results. There are two commonly held hypotheses regarding the issue: a widely-believed monotonic interactivity hypothesis and a better supported interaction plateau hypothesis. The former hypothesis predicts increasing in interactivity causes an increase in learning while the latter states that increasing interactivity yields increasing learning until it hits a plateau, and further increases in interactivity do not cause noticeably increase in learning. In this study, we proposed the tactical interaction hypothesis which predicts beyond a certain level of interactivity, further increases in interactivity do not cause increase in learning unless they are guided by effective tutorial tactics. Overall our results support this hypothesis. However, finding effective tactics is not easy. This paper sheds some light on how to apply Reinforcement Learning to derive effective tutorial tactics.",
keywords = "Intelligent tutoring systems, Knowledge component, Natural language tutoring systems, Pedagogical tutorial tactics, Reinforcement learning",
author = "Min Chi and Pamela Jordan and Kurt VanLehn and Diane Litman",
year = "2009",
doi = "10.3233/978-1-60750-028-5-197",
language = "English (US)",
isbn = "9781607500285",
volume = "200",
series = "Frontiers in Artificial Intelligence and Applications",
number = "1",
pages = "197--204",
booktitle = "Frontiers in Artificial Intelligence and Applications",
edition = "1",

}

TY - GEN

T1 - To elicit or to tell

T2 - Does it matter

AU - Chi, Min

AU - Jordan, Pamela

AU - VanLehn, Kurt

AU - Litman, Diane

PY - 2009

Y1 - 2009

N2 - While high interactivity has been one of the main characteristics of one-on-one human tutoring, a great deal of controversy surrounds the issue of whether interactivity is indeed the key feature of tutorial dialogue that impacts students' learning results. There are two commonly held hypotheses regarding the issue: a widely-believed monotonic interactivity hypothesis and a better supported interaction plateau hypothesis. The former hypothesis predicts increasing in interactivity causes an increase in learning while the latter states that increasing interactivity yields increasing learning until it hits a plateau, and further increases in interactivity do not cause noticeably increase in learning. In this study, we proposed the tactical interaction hypothesis which predicts beyond a certain level of interactivity, further increases in interactivity do not cause increase in learning unless they are guided by effective tutorial tactics. Overall our results support this hypothesis. However, finding effective tactics is not easy. This paper sheds some light on how to apply Reinforcement Learning to derive effective tutorial tactics.

AB - While high interactivity has been one of the main characteristics of one-on-one human tutoring, a great deal of controversy surrounds the issue of whether interactivity is indeed the key feature of tutorial dialogue that impacts students' learning results. There are two commonly held hypotheses regarding the issue: a widely-believed monotonic interactivity hypothesis and a better supported interaction plateau hypothesis. The former hypothesis predicts increasing in interactivity causes an increase in learning while the latter states that increasing interactivity yields increasing learning until it hits a plateau, and further increases in interactivity do not cause noticeably increase in learning. In this study, we proposed the tactical interaction hypothesis which predicts beyond a certain level of interactivity, further increases in interactivity do not cause increase in learning unless they are guided by effective tutorial tactics. Overall our results support this hypothesis. However, finding effective tactics is not easy. This paper sheds some light on how to apply Reinforcement Learning to derive effective tutorial tactics.

KW - Intelligent tutoring systems

KW - Knowledge component

KW - Natural language tutoring systems

KW - Pedagogical tutorial tactics

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=73149125369&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=73149125369&partnerID=8YFLogxK

U2 - 10.3233/978-1-60750-028-5-197

DO - 10.3233/978-1-60750-028-5-197

M3 - Conference contribution

SN - 9781607500285

VL - 200

T3 - Frontiers in Artificial Intelligence and Applications

SP - 197

EP - 204

BT - Frontiers in Artificial Intelligence and Applications

ER -