Dynamic models for knowledge tracing & prediction of future performance

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Large-scale data about learners’ behavior are being generated at high speed on various online learning platforms. Knowledge Tracing (KT) is a family of machine learning sequence models that are capable of using these data efficiently with the objective to identify the likelihood of future learning performance. This study provides an overview of KT models from a technical and an educational point of view. It focuses on data representation, evaluation, and optimization, and discusses the underlying model assumptions such that the strengths and weaknesses with regard to a specific application become visible. Based on the need for advanced analytical methods suited for large and diverse data, we briefly review big data analytics along with KT learning algorithms’ efficiency, learnability and scalability. Challenges and future research directions are also outlined. In general, the overview can serve as a guide for researchers and developers, linking the dynamic knowledge tracing models and properties to the learner’s knowledge acquisition process that should be accurately modeled over time. Applied KT models to online learning environments hold great potential for the online education industry because it enables the development of personalized adaptive learning systems.
Original languageEnglish
Title of host publication7th International Conference on Data Analytics
EditorsSandjai Bhulai, Dimitris Kardaras, Ivana Semanjski
Place of PublicationAthens, Greece
PublisherIARIA
Pages121-129
Number of pages9
ISBN (Print)9781612086811
Publication statusPublished - 18 Nov 2018

Fingerprint

Dynamic models
Learning systems
Knowledge acquisition
Learning algorithms
Scalability
Education
Industry

Keywords

  • big data applications
  • educational data mining
  • knowledge tracing
  • sequential supervised machine learning

Cite this

Sapountzi, A., Bhulai, S., Cornelisz, I., & van Klaveren, C. P. B. J. (2018). Dynamic models for knowledge tracing & prediction of future performance. In S. Bhulai, D. Kardaras, & I. Semanjski (Eds.), 7th International Conference on Data Analytics (pp. 121-129). Athens, Greece: IARIA.
Sapountzi, A. ; Bhulai, Sandjai ; Cornelisz, I. ; van Klaveren, C.P.B.J. / Dynamic models for knowledge tracing & prediction of future performance. 7th International Conference on Data Analytics. editor / Sandjai Bhulai ; Dimitris Kardaras ; Ivana Semanjski. Athens, Greece : IARIA, 2018. pp. 121-129
@inproceedings{5e52364c04154a888d3569c47b5c7fd6,
title = "Dynamic models for knowledge tracing & prediction of future performance",
abstract = "Large-scale data about learners’ behavior are being generated at high speed on various online learning platforms. Knowledge Tracing (KT) is a family of machine learning sequence models that are capable of using these data efficiently with the objective to identify the likelihood of future learning performance. This study provides an overview of KT models from a technical and an educational point of view. It focuses on data representation, evaluation, and optimization, and discusses the underlying model assumptions such that the strengths and weaknesses with regard to a specific application become visible. Based on the need for advanced analytical methods suited for large and diverse data, we briefly review big data analytics along with KT learning algorithms’ efficiency, learnability and scalability. Challenges and future research directions are also outlined. In general, the overview can serve as a guide for researchers and developers, linking the dynamic knowledge tracing models and properties to the learner’s knowledge acquisition process that should be accurately modeled over time. Applied KT models to online learning environments hold great potential for the online education industry because it enables the development of personalized adaptive learning systems.",
keywords = "big data applications, educational data mining, knowledge tracing, sequential supervised machine learning",
author = "A. Sapountzi and Sandjai Bhulai and I. Cornelisz and {van Klaveren}, C.P.B.J.",
year = "2018",
month = "11",
day = "18",
language = "English",
isbn = "9781612086811",
pages = "121--129",
editor = "Sandjai Bhulai and Dimitris Kardaras and Ivana Semanjski",
booktitle = "7th International Conference on Data Analytics",
publisher = "IARIA",

}

Sapountzi, A, Bhulai, S, Cornelisz, I & van Klaveren, CPBJ 2018, Dynamic models for knowledge tracing & prediction of future performance. in S Bhulai, D Kardaras & I Semanjski (eds), 7th International Conference on Data Analytics. IARIA, Athens, Greece, pp. 121-129.

Dynamic models for knowledge tracing & prediction of future performance. / Sapountzi, A.; Bhulai, Sandjai; Cornelisz, I.; van Klaveren, C.P.B.J.

7th International Conference on Data Analytics. ed. / Sandjai Bhulai; Dimitris Kardaras; Ivana Semanjski. Athens, Greece : IARIA, 2018. p. 121-129.

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Dynamic models for knowledge tracing & prediction of future performance

AU - Sapountzi, A.

AU - Bhulai, Sandjai

AU - Cornelisz, I.

AU - van Klaveren, C.P.B.J.

PY - 2018/11/18

Y1 - 2018/11/18

N2 - Large-scale data about learners’ behavior are being generated at high speed on various online learning platforms. Knowledge Tracing (KT) is a family of machine learning sequence models that are capable of using these data efficiently with the objective to identify the likelihood of future learning performance. This study provides an overview of KT models from a technical and an educational point of view. It focuses on data representation, evaluation, and optimization, and discusses the underlying model assumptions such that the strengths and weaknesses with regard to a specific application become visible. Based on the need for advanced analytical methods suited for large and diverse data, we briefly review big data analytics along with KT learning algorithms’ efficiency, learnability and scalability. Challenges and future research directions are also outlined. In general, the overview can serve as a guide for researchers and developers, linking the dynamic knowledge tracing models and properties to the learner’s knowledge acquisition process that should be accurately modeled over time. Applied KT models to online learning environments hold great potential for the online education industry because it enables the development of personalized adaptive learning systems.

AB - Large-scale data about learners’ behavior are being generated at high speed on various online learning platforms. Knowledge Tracing (KT) is a family of machine learning sequence models that are capable of using these data efficiently with the objective to identify the likelihood of future learning performance. This study provides an overview of KT models from a technical and an educational point of view. It focuses on data representation, evaluation, and optimization, and discusses the underlying model assumptions such that the strengths and weaknesses with regard to a specific application become visible. Based on the need for advanced analytical methods suited for large and diverse data, we briefly review big data analytics along with KT learning algorithms’ efficiency, learnability and scalability. Challenges and future research directions are also outlined. In general, the overview can serve as a guide for researchers and developers, linking the dynamic knowledge tracing models and properties to the learner’s knowledge acquisition process that should be accurately modeled over time. Applied KT models to online learning environments hold great potential for the online education industry because it enables the development of personalized adaptive learning systems.

KW - big data applications

KW - educational data mining

KW - knowledge tracing

KW - sequential supervised machine learning

M3 - Conference contribution

SN - 9781612086811

SP - 121

EP - 129

BT - 7th International Conference on Data Analytics

A2 - Bhulai, Sandjai

A2 - Kardaras, Dimitris

A2 - Semanjski, Ivana

PB - IARIA

CY - Athens, Greece

ER -

Sapountzi A, Bhulai S, Cornelisz I, van Klaveren CPBJ. Dynamic models for knowledge tracing & prediction of future performance. In Bhulai S, Kardaras D, Semanjski I, editors, 7th International Conference on Data Analytics. Athens, Greece: IARIA. 2018. p. 121-129