Data mining meta-analysis coding to develop smart learning systems that dynamically customize scaffolding

Nam Ju Kim, Brian R. Belland, Yong Kim

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

Abstract

Scaffolding, defined as support to help students perform and gain skill at complex tasks, has been integrated into instruction in a wide range of educational levels, disciplines, and problem-centered instructional approaches. In the underlying project, we aim to use machine learning to dynamically customize computer-based scaffolding. In this paper, we estimate the predictive power of machine learning classifiers with different types of input variables such as scaffolding characteristics, study characteristics, student characteristics, and study quality characteristics. Three classifiers (i.e., Naïve Bayes, support vector machines, and decision tree) can accurately predict with an averaged accuracy of over 50% the effectiveness of scaffolding using only scaffolding characteristics information. In addition, Decision Tree classifier leads to 91.34% accuracy when scaffolding characteristics and study characteristics are classified. Our findings from this preliminary experiment provide a foundation to set up initial parameters that a smart learning system can utilize to provide individualized and customized scaffolding.

Original languageEnglish (US)
Title of host publicationAMCIS 2017 - America's Conference on Information Systems
Subtitle of host publicationA Tradition of Innovation
PublisherAmericas Conference on Information Systems
Volume2017-August
ISBN (Electronic)9780996683142
StatePublished - Jan 1 2017
Externally publishedYes
EventAmerica�s Conference on Information Systems: A Tradition of Innovation, AMCIS 2017 - Boston, United States
Duration: Aug 10 2017Aug 12 2017

Other

OtherAmerica�s Conference on Information Systems: A Tradition of Innovation, AMCIS 2017
CountryUnited States
CityBoston
Period8/10/178/12/17

Fingerprint

Data mining
Learning systems
Classifiers
Decision trees
Students
Support vector machines
Experiments

Keywords

  • Data Mining
  • Machine Learning Classification
  • Problem-centered Instructional Models
  • Scaffolding

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Computer Networks and Communications

Cite this

Kim, N. J., Belland, B. R., & Kim, Y. (2017). Data mining meta-analysis coding to develop smart learning systems that dynamically customize scaffolding. In AMCIS 2017 - America's Conference on Information Systems: A Tradition of Innovation (Vol. 2017-August). Americas Conference on Information Systems.

Data mining meta-analysis coding to develop smart learning systems that dynamically customize scaffolding. / Kim, Nam Ju; Belland, Brian R.; Kim, Yong.

AMCIS 2017 - America's Conference on Information Systems: A Tradition of Innovation. Vol. 2017-August Americas Conference on Information Systems, 2017.

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

Kim, NJ, Belland, BR & Kim, Y 2017, Data mining meta-analysis coding to develop smart learning systems that dynamically customize scaffolding. in AMCIS 2017 - America's Conference on Information Systems: A Tradition of Innovation. vol. 2017-August, Americas Conference on Information Systems, America�s Conference on Information Systems: A Tradition of Innovation, AMCIS 2017, Boston, United States, 8/10/17.
Kim NJ, Belland BR, Kim Y. Data mining meta-analysis coding to develop smart learning systems that dynamically customize scaffolding. In AMCIS 2017 - America's Conference on Information Systems: A Tradition of Innovation. Vol. 2017-August. Americas Conference on Information Systems. 2017
Kim, Nam Ju ; Belland, Brian R. ; Kim, Yong. / Data mining meta-analysis coding to develop smart learning systems that dynamically customize scaffolding. AMCIS 2017 - America's Conference on Information Systems: A Tradition of Innovation. Vol. 2017-August Americas Conference on Information Systems, 2017.
@inproceedings{d92ab569a59247ccbb96c43d446f7271,
title = "Data mining meta-analysis coding to develop smart learning systems that dynamically customize scaffolding",
abstract = "Scaffolding, defined as support to help students perform and gain skill at complex tasks, has been integrated into instruction in a wide range of educational levels, disciplines, and problem-centered instructional approaches. In the underlying project, we aim to use machine learning to dynamically customize computer-based scaffolding. In this paper, we estimate the predictive power of machine learning classifiers with different types of input variables such as scaffolding characteristics, study characteristics, student characteristics, and study quality characteristics. Three classifiers (i.e., Na{\"i}ve Bayes, support vector machines, and decision tree) can accurately predict with an averaged accuracy of over 50{\%} the effectiveness of scaffolding using only scaffolding characteristics information. In addition, Decision Tree classifier leads to 91.34{\%} accuracy when scaffolding characteristics and study characteristics are classified. Our findings from this preliminary experiment provide a foundation to set up initial parameters that a smart learning system can utilize to provide individualized and customized scaffolding.",
keywords = "Data Mining, Machine Learning Classification, Problem-centered Instructional Models, Scaffolding",
author = "Kim, {Nam Ju} and Belland, {Brian R.} and Yong Kim",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
volume = "2017-August",
booktitle = "AMCIS 2017 - America's Conference on Information Systems",
publisher = "Americas Conference on Information Systems",

}

TY - GEN

T1 - Data mining meta-analysis coding to develop smart learning systems that dynamically customize scaffolding

AU - Kim, Nam Ju

AU - Belland, Brian R.

AU - Kim, Yong

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Scaffolding, defined as support to help students perform and gain skill at complex tasks, has been integrated into instruction in a wide range of educational levels, disciplines, and problem-centered instructional approaches. In the underlying project, we aim to use machine learning to dynamically customize computer-based scaffolding. In this paper, we estimate the predictive power of machine learning classifiers with different types of input variables such as scaffolding characteristics, study characteristics, student characteristics, and study quality characteristics. Three classifiers (i.e., Naïve Bayes, support vector machines, and decision tree) can accurately predict with an averaged accuracy of over 50% the effectiveness of scaffolding using only scaffolding characteristics information. In addition, Decision Tree classifier leads to 91.34% accuracy when scaffolding characteristics and study characteristics are classified. Our findings from this preliminary experiment provide a foundation to set up initial parameters that a smart learning system can utilize to provide individualized and customized scaffolding.

AB - Scaffolding, defined as support to help students perform and gain skill at complex tasks, has been integrated into instruction in a wide range of educational levels, disciplines, and problem-centered instructional approaches. In the underlying project, we aim to use machine learning to dynamically customize computer-based scaffolding. In this paper, we estimate the predictive power of machine learning classifiers with different types of input variables such as scaffolding characteristics, study characteristics, student characteristics, and study quality characteristics. Three classifiers (i.e., Naïve Bayes, support vector machines, and decision tree) can accurately predict with an averaged accuracy of over 50% the effectiveness of scaffolding using only scaffolding characteristics information. In addition, Decision Tree classifier leads to 91.34% accuracy when scaffolding characteristics and study characteristics are classified. Our findings from this preliminary experiment provide a foundation to set up initial parameters that a smart learning system can utilize to provide individualized and customized scaffolding.

KW - Data Mining

KW - Machine Learning Classification

KW - Problem-centered Instructional Models

KW - Scaffolding

UR - http://www.scopus.com/inward/record.url?scp=85048393611&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048393611&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2017-August

BT - AMCIS 2017 - America's Conference on Information Systems

PB - Americas Conference on Information Systems

ER -