在线学习危机精准预警及干预:模型与实证研究
|
摘要
对学生学习行为进行全面的定量化描述、学业诊断、精准预警、处方干预,有助于准确识别学习危机学生,提供精准教学服务。本研究利用数据挖掘和学习分析技术,跟踪分析在线学习中非干预行为数据,包括过程性结构化外显信息(如学习状态、学习交互、学业水平等)和非结构化内隐信息(如学习者情绪),确定在线学习危机预警因素。本研究采用朴素贝叶斯构建精准预警模型,利用准实验设计对处于学习危机的学生进行聚类分组,并提出采用邮件通知人工干预和在线学习支持环境自动干预两种策略,同时通过信誉积分和预警指标干预制度加以保障。研究结果表明,模型能够准确识别学习者学习状态与趋势,发现学习异常者;干预策略能够有效引导学生学习,化解学习危机,促进个性化教学和学生管理。
It is conducive to accurate identification of students. learning crisis and providing accurate teaching to conduct comprehensive quantitative description of students. learning behavior, learning diagnosis, accurate alerting and prevention intervention. Adopting data mining and learning analytics technology, the authors analyze the non-interventional behavior data in online learning, including explicit procedural structural information(such as state of learning, learning interaction and learning performance, etc.) and implicit non-structural information(such as learners mood), and identify the alerting factors of online learning crisis. This study constructs an accurate alerting model using Na?ve Bayes classifiers, and classifies students in learning crisis with cluster grouping using quasi-experimental design. It also proposes two intervening strategies, emailing artificial intervention or intervening automatically in the learning environment. The results show that this model is able to identify the state of learning and trends of the learners, esp. the abnormal learners, and the intervening strategies can supervise the learners in their effective learning, resolve their learning crisis, and enhance personalized learning and teaching and administration.
It is conducive to accurate identification of students. learning crisis and providing accurate teaching to conduct comprehensive quantitative description of students. learning behavior, learning diagnosis, accurate alerting and prevention intervention. Adopting data mining and learning analytics technology, the authors analyze the non-interventional behavior data in online learning, including explicit procedural structural information(such as state of learning, learning interaction and learning performance, etc.) and implicit non-structural information(such as learners mood), and identify the alerting factors of online learning crisis. This study constructs an accurate alerting model using Na?ve Bayes classifiers, and classifies students in learning crisis with cluster grouping using quasi-experimental design. It also proposes two intervening strategies, emailing artificial intervention or intervening automatically in the learning environment. The results show that this model is able to identify the state of learning and trends of the learners, esp. the abnormal learners, and the intervening strategies can supervise the learners in their effective learning, resolve their learning crisis, and enhance personalized learning and teaching and administration.
引文
武法提,牟智佳.2016.基于学习者个性行为分析的学习结果预测框架设计研究[J].中国电化教育(01):41-48.
杨现民,叶洋,王林丽.2016.基于大数据的在线学习预警模型设计--“教育大数据研究与实践专栏”之学习预警篇[J].现代教育技术,26(07):5-11.
杨雪,姜强,赵蔚,李勇帆,李松.2017.大数据时代基于学习分析的在线学习拖延诊断与干预研究[J].电化教育研究(07):51-57.
尤佳鑫,孙众.2016.云学习平台大学生学业成绩预测与干预研究[J].中国远程教育(09):14-20.
赵慧琼,姜强,赵蔚,李勇帆,赵艳.2017.基于大数据学习分析的在线学习绩效预警因素及干预对策的实证研究[J].电化教育研究(01):62-69.
周涛.2017-05-31.预测的局限性[EB/OL].[2018-11-01].http://blog.sciencenet.cn/blog-3075-1058131.html
Ahmed,Elaraby.(2014).Sayed Elaraby I.Data Mining:A prediction for Students Performance Using Classification Method.World Journal of Computer Application&Technology,2(2),43-47.
Hanan Khalil,Martin Ebner.(2014).MOOCs Completion Rates and Pos?sible Methods to Improve Retention-A Literature Review.World Con?ference on Educational Multimedia,Hypermedia and Telecommunica?tions.Chesapeake,VA:AACE,1236-1244.
Ke Arnold,MD Pistilli.(2012).Course signals at Purdue:using learning analytics to increase student success.International Conference on Learning Analytics and Knowledge.New York:ACM Press,267-270.
Kolo David Kolo,Solomon A.Adepojub,John Kolo Alhassan.(2015).A Decision Tree Approach for Predicting Students Academic Perfor?mance.Education and Management Engineering,5,12-19.
Lang P J.(1980).Behavioral treatment and bio-behavioral assessment:Computer applications.Norwood,N.J.:Ablex Pub.Corp.
Marbouti F,Diefes-Dux H A,Madhavan K.(2016).Models for early pre?diction of at-risk students in a course using standards-based grading.Computers&Education,103,1-15.
Mezzari,Adelina.(2013).Strategies for the early detection of evasion propensity.Knowledge Management&E-Learning:an International Journal,5(1),104-116.
M Goga,S Kuyoro,N Goga.(2015).A Recommender for Improving the Student Academic Performance[J].Procedia-Social and Behavioral Sciences,180(5),1481-1488.
Yu P T.(2015).The benefits of a challenge:student motivation and flow experience in tablet-PC-game-based learning.Interactive Learning Environments,23(2),172-190.
ZahyahAlharbi,James Cornford,Liam Dolder,Beatriz De La Iglesia.(2016).Using data mining techniques to predict students at risk of poor performance.Sai Computing Conference.London:IEEE Com?puter Society Press,523-531.
杨现民,叶洋,王林丽.2016.基于大数据的在线学习预警模型设计--“教育大数据研究与实践专栏”之学习预警篇[J].现代教育技术,26(07):5-11.
杨雪,姜强,赵蔚,李勇帆,李松.2017.大数据时代基于学习分析的在线学习拖延诊断与干预研究[J].电化教育研究(07):51-57.
尤佳鑫,孙众.2016.云学习平台大学生学业成绩预测与干预研究[J].中国远程教育(09):14-20.
赵慧琼,姜强,赵蔚,李勇帆,赵艳.2017.基于大数据学习分析的在线学习绩效预警因素及干预对策的实证研究[J].电化教育研究(01):62-69.
周涛.2017-05-31.预测的局限性[EB/OL].[2018-11-01].http://blog.sciencenet.cn/blog-3075-1058131.html
Ahmed,Elaraby.(2014).Sayed Elaraby I.Data Mining:A prediction for Students Performance Using Classification Method.World Journal of Computer Application&Technology,2(2),43-47.
Hanan Khalil,Martin Ebner.(2014).MOOCs Completion Rates and Pos?sible Methods to Improve Retention-A Literature Review.World Con?ference on Educational Multimedia,Hypermedia and Telecommunica?tions.Chesapeake,VA:AACE,1236-1244.
Ke Arnold,MD Pistilli.(2012).Course signals at Purdue:using learning analytics to increase student success.International Conference on Learning Analytics and Knowledge.New York:ACM Press,267-270.
Kolo David Kolo,Solomon A.Adepojub,John Kolo Alhassan.(2015).A Decision Tree Approach for Predicting Students Academic Perfor?mance.Education and Management Engineering,5,12-19.
Lang P J.(1980).Behavioral treatment and bio-behavioral assessment:Computer applications.Norwood,N.J.:Ablex Pub.Corp.
Marbouti F,Diefes-Dux H A,Madhavan K.(2016).Models for early pre?diction of at-risk students in a course using standards-based grading.Computers&Education,103,1-15.
Mezzari,Adelina.(2013).Strategies for the early detection of evasion propensity.Knowledge Management&E-Learning:an International Journal,5(1),104-116.
M Goga,S Kuyoro,N Goga.(2015).A Recommender for Improving the Student Academic Performance[J].Procedia-Social and Behavioral Sciences,180(5),1481-1488.
Yu P T.(2015).The benefits of a challenge:student motivation and flow experience in tablet-PC-game-based learning.Interactive Learning Environments,23(2),172-190.
ZahyahAlharbi,James Cornford,Liam Dolder,Beatriz De La Iglesia.(2016).Using data mining techniques to predict students at risk of poor performance.Sai Computing Conference.London:IEEE Com?puter Society Press,523-531.