Adapting Bayesian knowledge tracing to a massive open online course in edX

Zachary A. Pardos, Yoav Bergner, Daniel T. Seaton, David E. Pritchard

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

Abstract

Massive Open Online Courses (MOOCs) are an increasingly pervasive newcomer to the virtual landscape of higher-education, delivering a wide variety of topics in science, engineering, and the humanities. However, while technological innovation is enabling unprecedented open access to high quality educational material, these systems generally inherit similar homework, exams, and instructional resources to that of their classroom counterparts and currently lack an underlying model with which to talk about learning. In this paper we will show how existing learner modeling techniques based on Bayesian Knowledge Tracing can be adapted to the inaugural course, 6.002x: circuit design, on the edX MOOC platform. We identify three distinct challenges to modeling MOOC data and provide predictive evaluations of the respective modeling approach to each challenge. The challenges identified are; lack of an explicit knowledge component model, allowance for unpenalized multiple problem attempts, and multiple pathways through the system that allow for learning influences outside of the current assessment.

Original languageEnglish (US)
Title of host publicationProceedings of the 6th International Conference on Educational Data Mining, EDM 2013
EditorsSidney K. D'Mello, Rafael A. Calvo, Andrew Olney
PublisherInternational Educational Data Mining Society
ISBN (Electronic)9780983952527
StatePublished - Jan 1 2013
Event6th International Conference on Educational Data Mining, EDM 2013 - Memphis, United States
Duration: Jul 6 2013Jul 9 2013

Publication series

NameProceedings of the 6th International Conference on Educational Data Mining, EDM 2013

Conference

Conference6th International Conference on Educational Data Mining, EDM 2013
CountryUnited States
CityMemphis
Period7/6/137/9/13

Fingerprint

Innovation
Education
Networks (circuits)

Keywords

  • Bayesian knowledge tracing
  • EdX
  • MOOC
  • Probabilistic graphical models
  • Resource model

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

Pardos, Z. A., Bergner, Y., Seaton, D. T., & Pritchard, D. E. (2013). Adapting Bayesian knowledge tracing to a massive open online course in edX. In S. K. D'Mello, R. A. Calvo, & A. Olney (Eds.), Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013 (Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013). International Educational Data Mining Society.

Adapting Bayesian knowledge tracing to a massive open online course in edX. / Pardos, Zachary A.; Bergner, Yoav; Seaton, Daniel T.; Pritchard, David E.

Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013. ed. / Sidney K. D'Mello; Rafael A. Calvo; Andrew Olney. International Educational Data Mining Society, 2013. (Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013).

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

Pardos, ZA, Bergner, Y, Seaton, DT & Pritchard, DE 2013, Adapting Bayesian knowledge tracing to a massive open online course in edX. in SK D'Mello, RA Calvo & A Olney (eds), Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013. Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013, International Educational Data Mining Society, 6th International Conference on Educational Data Mining, EDM 2013, Memphis, United States, 7/6/13.
Pardos ZA, Bergner Y, Seaton DT, Pritchard DE. Adapting Bayesian knowledge tracing to a massive open online course in edX. In D'Mello SK, Calvo RA, Olney A, editors, Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013. International Educational Data Mining Society. 2013. (Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013).
Pardos, Zachary A. ; Bergner, Yoav ; Seaton, Daniel T. ; Pritchard, David E. / Adapting Bayesian knowledge tracing to a massive open online course in edX. Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013. editor / Sidney K. D'Mello ; Rafael A. Calvo ; Andrew Olney. International Educational Data Mining Society, 2013. (Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013).
@inproceedings{123c981dc8d1481fb91657fed4f4222e,
title = "Adapting Bayesian knowledge tracing to a massive open online course in edX",
abstract = "Massive Open Online Courses (MOOCs) are an increasingly pervasive newcomer to the virtual landscape of higher-education, delivering a wide variety of topics in science, engineering, and the humanities. However, while technological innovation is enabling unprecedented open access to high quality educational material, these systems generally inherit similar homework, exams, and instructional resources to that of their classroom counterparts and currently lack an underlying model with which to talk about learning. In this paper we will show how existing learner modeling techniques based on Bayesian Knowledge Tracing can be adapted to the inaugural course, 6.002x: circuit design, on the edX MOOC platform. We identify three distinct challenges to modeling MOOC data and provide predictive evaluations of the respective modeling approach to each challenge. The challenges identified are; lack of an explicit knowledge component model, allowance for unpenalized multiple problem attempts, and multiple pathways through the system that allow for learning influences outside of the current assessment.",
keywords = "Bayesian knowledge tracing, EdX, MOOC, Probabilistic graphical models, Resource model",
author = "Pardos, {Zachary A.} and Yoav Bergner and Seaton, {Daniel T.} and Pritchard, {David E.}",
year = "2013",
month = "1",
day = "1",
language = "English (US)",
series = "Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013",
publisher = "International Educational Data Mining Society",
editor = "D'Mello, {Sidney K.} and Calvo, {Rafael A.} and Andrew Olney",
booktitle = "Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013",

}

TY - GEN

T1 - Adapting Bayesian knowledge tracing to a massive open online course in edX

AU - Pardos, Zachary A.

AU - Bergner, Yoav

AU - Seaton, Daniel T.

AU - Pritchard, David E.

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Massive Open Online Courses (MOOCs) are an increasingly pervasive newcomer to the virtual landscape of higher-education, delivering a wide variety of topics in science, engineering, and the humanities. However, while technological innovation is enabling unprecedented open access to high quality educational material, these systems generally inherit similar homework, exams, and instructional resources to that of their classroom counterparts and currently lack an underlying model with which to talk about learning. In this paper we will show how existing learner modeling techniques based on Bayesian Knowledge Tracing can be adapted to the inaugural course, 6.002x: circuit design, on the edX MOOC platform. We identify three distinct challenges to modeling MOOC data and provide predictive evaluations of the respective modeling approach to each challenge. The challenges identified are; lack of an explicit knowledge component model, allowance for unpenalized multiple problem attempts, and multiple pathways through the system that allow for learning influences outside of the current assessment.

AB - Massive Open Online Courses (MOOCs) are an increasingly pervasive newcomer to the virtual landscape of higher-education, delivering a wide variety of topics in science, engineering, and the humanities. However, while technological innovation is enabling unprecedented open access to high quality educational material, these systems generally inherit similar homework, exams, and instructional resources to that of their classroom counterparts and currently lack an underlying model with which to talk about learning. In this paper we will show how existing learner modeling techniques based on Bayesian Knowledge Tracing can be adapted to the inaugural course, 6.002x: circuit design, on the edX MOOC platform. We identify three distinct challenges to modeling MOOC data and provide predictive evaluations of the respective modeling approach to each challenge. The challenges identified are; lack of an explicit knowledge component model, allowance for unpenalized multiple problem attempts, and multiple pathways through the system that allow for learning influences outside of the current assessment.

KW - Bayesian knowledge tracing

KW - EdX

KW - MOOC

KW - Probabilistic graphical models

KW - Resource model

UR - http://www.scopus.com/inward/record.url?scp=84964262740&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964262740&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84964262740

T3 - Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013

BT - Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013

A2 - D'Mello, Sidney K.

A2 - Calvo, Rafael A.

A2 - Olney, Andrew

PB - International Educational Data Mining Society

ER -