Abductive theorem proving for analyzing student explanations to guide feedback in intelligent tutoring systems

Maxim Makatchev, Pamela W. Jordan, Kurt VanLehn

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

The Why2-Atlas tutoring system presents students with qualitative physics questions and encourages them to explain their answers through natural language. Although there are inexpensive techniques for analyzing explanations, we claim that better understanding is necessary for use within tutoring systems. In this paper we motivate and describe how the system creates and uses a deeper proof-based representation of student essays in order to provide students with substantive feedback on their explanations. We describe in detail the abductive reasoner, Tacitus-lite+, that we use within the tutoring system. We also discuss evaluation results for an early version of the Why2-Atlas system and a subsequent evaluation of the theorem-proving module. We conclude with the discussion of work in progress and additional future work for deriving more benefits from a proof-based approach for tutoring applications.

Original languageEnglish (US)
Pages (from-to)187-226
Number of pages40
JournalJournal of Automated Reasoning
Volume32
Issue number3
DOIs
StatePublished - 2004
Externally publishedYes

Fingerprint

Theorem proving
Intelligent systems
Students
Feedback
Physics

Keywords

  • Abductive reasoning
  • Intelligent tutoring systems
  • Qualitative physics

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Abductive theorem proving for analyzing student explanations to guide feedback in intelligent tutoring systems. / Makatchev, Maxim; Jordan, Pamela W.; VanLehn, Kurt.

In: Journal of Automated Reasoning, Vol. 32, No. 3, 2004, p. 187-226.

Research output: Contribution to journalArticle

@article{e464dff05c05492eac4eef96a58bf418,
title = "Abductive theorem proving for analyzing student explanations to guide feedback in intelligent tutoring systems",
abstract = "The Why2-Atlas tutoring system presents students with qualitative physics questions and encourages them to explain their answers through natural language. Although there are inexpensive techniques for analyzing explanations, we claim that better understanding is necessary for use within tutoring systems. In this paper we motivate and describe how the system creates and uses a deeper proof-based representation of student essays in order to provide students with substantive feedback on their explanations. We describe in detail the abductive reasoner, Tacitus-lite+, that we use within the tutoring system. We also discuss evaluation results for an early version of the Why2-Atlas system and a subsequent evaluation of the theorem-proving module. We conclude with the discussion of work in progress and additional future work for deriving more benefits from a proof-based approach for tutoring applications.",
keywords = "Abductive reasoning, Intelligent tutoring systems, Qualitative physics",
author = "Maxim Makatchev and Jordan, {Pamela W.} and Kurt VanLehn",
year = "2004",
doi = "10.1023/B:JARS.0000044823.50442.cd",
language = "English (US)",
volume = "32",
pages = "187--226",
journal = "Journal of Automated Reasoning",
issn = "0168-7433",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - Abductive theorem proving for analyzing student explanations to guide feedback in intelligent tutoring systems

AU - Makatchev, Maxim

AU - Jordan, Pamela W.

AU - VanLehn, Kurt

PY - 2004

Y1 - 2004

N2 - The Why2-Atlas tutoring system presents students with qualitative physics questions and encourages them to explain their answers through natural language. Although there are inexpensive techniques for analyzing explanations, we claim that better understanding is necessary for use within tutoring systems. In this paper we motivate and describe how the system creates and uses a deeper proof-based representation of student essays in order to provide students with substantive feedback on their explanations. We describe in detail the abductive reasoner, Tacitus-lite+, that we use within the tutoring system. We also discuss evaluation results for an early version of the Why2-Atlas system and a subsequent evaluation of the theorem-proving module. We conclude with the discussion of work in progress and additional future work for deriving more benefits from a proof-based approach for tutoring applications.

AB - The Why2-Atlas tutoring system presents students with qualitative physics questions and encourages them to explain their answers through natural language. Although there are inexpensive techniques for analyzing explanations, we claim that better understanding is necessary for use within tutoring systems. In this paper we motivate and describe how the system creates and uses a deeper proof-based representation of student essays in order to provide students with substantive feedback on their explanations. We describe in detail the abductive reasoner, Tacitus-lite+, that we use within the tutoring system. We also discuss evaluation results for an early version of the Why2-Atlas system and a subsequent evaluation of the theorem-proving module. We conclude with the discussion of work in progress and additional future work for deriving more benefits from a proof-based approach for tutoring applications.

KW - Abductive reasoning

KW - Intelligent tutoring systems

KW - Qualitative physics

UR - http://www.scopus.com/inward/record.url?scp=6944242995&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=6944242995&partnerID=8YFLogxK

U2 - 10.1023/B:JARS.0000044823.50442.cd

DO - 10.1023/B:JARS.0000044823.50442.cd

M3 - Article

VL - 32

SP - 187

EP - 226

JO - Journal of Automated Reasoning

JF - Journal of Automated Reasoning

SN - 0168-7433

IS - 3

ER -