Student Clustering Based on Learning Behavior Data in the Intelligent Tutoring System

Int. J. Distance Educ. Technol. Pub Date : 2020-04-01 DOI:10.4018/ijdet.2020040105

Ines Šarić-Grgić, Ani Grubišić, Ljiljana Šerić, T. Robinson

{"title":"Student Clustering Based on Learning Behavior Data in the Intelligent Tutoring System","authors":"Ines Šarić-Grgić, Ani Grubišić, Ljiljana Šerić, T. Robinson","doi":"10.4018/ijdet.2020040105","DOIUrl":null,"url":null,"abstract":"The idea of clustering students according to their online learning behavior has the potential of providingmoreadaptivescaffoldingbytheintelligenttutoringsystemitselforbyahumanteacher. WiththeaimofidentifyingstudentgroupswhowouldbenefitfromthesameinterventioninACwareTutor, this researchexaminedonline learningbehaviorusing8 trackingvariables: the total numberofcontentpagesseeninthelearningprocess;thetotalnumberofconcepts;thetotalonline score;thetotaltimespentonline;thetotalnumberoflogins;thestereotypeaftertheinitialtest,the finalstereotype,andthemeanstereotypevariability.Thepreviousmeasureswereusedinafour-step analysisthatconsistedofdatapreprocessing,dimensionalityreduction,theclustering,andtheanalysis ofaposttestperformanceonacontentproficiencyexam.Theresultswerealsousedtoconstructthe decisiontreeinordertogetahuman-readabledescriptionofstudentclusters. KEywoRDS Blended Learning, Clustering, Decision Tree, Educational Data Mining, Flipped Classroom, Intelligent Tutoring System, Online Learning Behavior, Principal Component Analysis","PeriodicalId":298910,"journal":{"name":"Int. J. Distance Educ. Technol.","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Int. J. Distance Educ. Technol.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/ijdet.2020040105","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 11

Abstract

The idea of clustering students according to their online learning behavior has the potential of providingmoreadaptivescaffoldingbytheintelligenttutoringsystemitselforbyahumanteacher. WiththeaimofidentifyingstudentgroupswhowouldbenefitfromthesameinterventioninACwareTutor, this researchexaminedonline learningbehaviorusing8 trackingvariables: the total numberofcontentpagesseeninthelearningprocess;thetotalnumberofconcepts;thetotalonline score;thetotaltimespentonline;thetotalnumberoflogins;thestereotypeaftertheinitialtest,the finalstereotype,andthemeanstereotypevariability.Thepreviousmeasureswereusedinafour-step analysisthatconsistedofdatapreprocessing,dimensionalityreduction,theclustering,andtheanalysis ofaposttestperformanceonacontentproficiencyexam.Theresultswerealsousedtoconstructthe decisiontreeinordertogetahuman-readabledescriptionofstudentclusters. KEywoRDS Blended Learning, Clustering, Decision Tree, Educational Data Mining, Flipped Classroom, Intelligent Tutoring System, Online Learning Behavior, Principal Component Analysis

查看原文本刊更多论文

智能辅导系统中基于学习行为数据的学生聚类

根据学生的在线学习行为将他们聚集在一起的想法具有providingmoreadaptivescaffoldingbytheintelligenttutoringsystemitselforbyahumanteacher的潜力。目标的识别组织学生给将从相同的受益干预在ACware导师,研究在线学习检查行为使用8跟踪变量:总内容的页面数量见过学习过程;的总数量概念;总在线的分数;总花时间的在线;的总数量登录;刻板印象初始测试后,最终的刻板印象,意味着原型可变性。Thepreviousmeasureswereusedinafour-step analysisthatconsistedofdatapreprocessing，dimensionalityreduction，theclustering，andtheanalysis ofaposttestperformanceonacontentproficiencyexam。Theresultswerealsousedtoconstructthe decisiontreeinordertogetahuman-readabledescriptionofstudentclusters。关键词:混合学习，聚类，决策树，教育数据挖掘，翻转课堂，智能辅导系统，在线学习行为，主成分分析

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Int. J. Distance Educ. Technol.

自引率

0.00%

发文量