广东工业大学学报 ›› 2022, Vol. 39 ›› Issue (03): 41-48.doi: 10.12052/gdutxb.210067

• • 上一篇    下一篇

基于贝叶斯网络模型的在线学习行为分析

冯广1, 潘庭锋2, 伍文燕3   

  1. 1. 广东工业大学 自动化学院, 广东 广州 510006;
    2. 广东工业大学 计算机学院, 广东 广州 510006;
    3. 广东工业大学 网络信息与现代教育技术中心, 广东 广州 510006
  • 收稿日期:2021-04-25 出版日期:2022-05-10 发布日期:2022-05-19
  • 通信作者: 伍文燕(1989-),女,高级工程师,硕士,主要研究方向为教育信息化、人工智能、大数据,E-mail:wuwy@gdut.edu.cn
  • 作者简介:冯广(1973-)，男，教授级高级实验师，博士，主要研究方向为网络控制、机器学习、大数据
  • 基金资助:
    国家自然科学基金资助项目(71671048)

An Online Learning Behavior Analysis Based on Bayesian Network Model

Feng Guang1, Pan Ting-feng2, Wu Wen-yan3   

  1. 1. School of Automation, Guangdong University of Technology, Guangzhou 510006, China;
    2. School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China;
    3. Center of Campus Network & Modern Educational Technology, Guangdong University of Technology, Guangzhou 510006, China
  • Received:2021-04-25 Online:2022-05-10 Published:2022-05-19

HTML

PDF (PC)

2693

摘要： 线上线下结合的教学模式是未来教学的一个趋势，每一个学生的学习行为会直接影响学习结果，因此研究学习者学习行为对学习成绩的影响程度是目前的研究重点。目前常见的评价模型存在可信程度较低、可解释性较弱等问题，本文使用基于证据推理的贝叶斯网络(Bayes Network, BN)能够有效地解决这一问题。把方法应用在学习行为分析上，与常用的机器模型和深度学习模型进行比较，表现出更低的误差和更强的可解释性。

关键词: 在线教育, 贝叶斯网络, 学习行为, 联合树, 可解释性

Abstract: The combination of online and offline teaching mode is a trend of teaching in the future. The previous researches show that learners’ learning behavior can directly affect the learning results, so the research focuses on studying the influence level of learning behavior on academic performance. For the current common evaluation models, there are still some problems such as low credibility and weak interpretability. In this study, the Bayesian network (BN) based on evidential reasoning can effectively solve this problem. Compared with the commonly used machine model and deep learning model, it shows a lower error rate and a stronger interpretability.

Key words: online education, Bayesian network, learning behavior, junction tree, interpretability

中图分类号: 

  • G434
[1] JOHNSON M L, SINATRA G M. Use of task-value instructional inductions for facilitating engagement and conceptual change [J]. Contemporary Educational Psychology, 2013, 38(1): 51-63.
[2] 李爽, 王增贤, 喻忱, 等. 在线学习行为投入分析框架与测量指标研究——基于LMS数据的学习分析[J]. 开放教育研究, 2016, 22(2): 77-88.
LI S, WANG Z X, YU C, et al. Research on analysis framework and measurement index of online learning behavior engagement learning analysis based on LMS data [J]. Open Education Research, 2016, 22(2): 77-88.
[3] PERAL J, MATE A, MARCO M. Application of data mining techniques to identify relevant key performance indicators [J]. Computer Standards & Interfaces, 2017, 50: 55-64.
[4] APARICIO M, OLIVEIRA T, BACAO F, et al. Gamification: a key determinant of massive open online course (MOOC) success [J]. Information & Management, 2019, 56(1): 39-54.
[5] MORRIS L V, FINNEGAN C, WU S S. Tracking student behavior, persistence, and achievement in online courses [J]. The Internet and Higher Education, 2005, 8(3): 221-231.
[6] 马飞, 李娟. 基于聚类算法的MOOCs学习者分类及学习行为模式研究[J]. 广东工业大学学报, 2018, 35(3): 18-23.
MA F, LI J. A Research on the classification of learners and patterns of learning behavior based on cluster algorithms under MOOCs’ environment [J]. Journal of Guangdong University of Technology, 2018, 35(3): 18-23.
[7] 牟智佳. MOOCs环境下学习行为群体特征分析与学习结果预测研究[J]. 中国医学教育技术, 2020, 34(1): 1-6.
MOU Z J. Analysis of group characteristics of learning behavior and prediction of learning outcomes in MOOCs environment [J]. China Medical Education Technology, 2020, 34(1): 1-6.
[8] 沈欣忆, 刘美辰, 吴健伟, 等. MOOC学习者在线学习行为和学习绩效评估模型研究[J]. 中国远程教育, 2020, 40(10): 1-8.
SHEN X Y, LIU M C, WU J W, et al. Towards a model for evaluating students' online learning behaviors and learning performance [J]. Distance Education in China, 2020, 40(10): 1-8.
[9] WU Q. MOOC Learning behavior analysis and teaching intelligent decision support method based on improved decision tree C4.5 algorithm [J]. International Journal of Emerging Technologies in Learning (iJET), 2019, 14(12): 29-41.
[10] 陈德鑫, 占袁圆, 杨兵. 深度学习技术在教育大数据挖掘领域的应用分析[J]. 电化教育研究, 2019, 40(2): 68-76.
CHEN D X, ZHAN Y Y, YANG B. Analysis of applications of deep learning in educational big data mining [J]. e-Education Research, 2019, 40(2): 68-76.
[11] 孙霞, 吴楠楠, 张蕾, 等. 基于深度学习的MOOCs辍学率预测方法[J]. 计算机工程与科学, 2019, 41(5): 893-899.
SUN X, WU N N, ZHANG L, et al. A MOOC dropout rate prediction method based on deep learning [J]. Computer Engineering & Science, 2019, 41(5): 893-899.
[12] 胡航, 杜爽, 梁佳柔, 等. 学习绩效预测模型构建: 源于学习行为大数据分析[J]. 中国远程教育, 2021, 41(4): 8-20.
HU H, DU S, LIANG J R, et al. Towards a prediction model of learning performance: informed by learning behavior big data analytics [J]. Distance Education in China, 2021, 41(4): 8-20.
[13] 杨婷, 滕少华. 改进的贝叶斯分类方法在电信客户流失中的研究与应用[J]. 广东工业大学学报, 2015, 32(3): 67-72.
YANG T, TENG S H. Research and application of improved Bayes algorithm for the telecommunication customer churn [J]. Journal of Guangdong University of Technology, 2015, 32(3): 67-72.
[14] 蔡瑞初, 甄启祺, 陈薇, 等. 基于贝叶斯网络的基因变异间的因果关系发现与验证[J]. 计算机应用与软件, 2020, 37(7): 22-28.
CAI R C, ZHEN Q Q, CHEN W, et al. Discovery and validation of causalities among gene mutations based on Bayesian network [J]. Computer Applications and Software, 2020, 37(7): 22-28.
[15] MOE S J, CARRIGER J F, GLENDELL M. Increased use of Bayesian network models has improved environmental risk assessments [J]. Integrated Environmental Assessment and Management, 2020, 17(1): 53-61.
[16] 方媛, 刘俊槐, 谢晶珠, 等. 基于贝叶斯网络的公众参与PPP项目决策研究[J]. 广东工业大学学报, 2018, 35(3): 79-86.
FANG Y, LIU J H, XIE J Z, et al. Public participation in decision-making of ppp project based on Bayesian network [J]. Journal of Guangdong University of Technology, 2018, 35(3): 79-86.
[17] 赵磊, 邓彤, 吴卓平. 基于数据挖掘的MOOC学习者学业成绩预测与群体特征分析[J/OL]. 重庆高教研究, 2021 (2021-01-08)[2021-03-31]. http://kns.cnki.net/kcms/detail/50.1028.G4.20210106.1806.002.html.
[18] 张连文, 郭海鹏. 贝叶斯网引论[M]. 北京: 科学出版社, 2006: 175-178.
[1] 马飞, 李娟. 基于聚类算法的MOOCs学习者分类及学习行为模式研究[J]. 广东工业大学学报, 2018, 35(03): 18-23.
[2] 方媛, 刘俊槐, 谢晶珠, 卢晓晴, 曾妍倩, 谢汉雄. 基于贝叶斯网络的公众参与PPP项目决策研究[J]. 广东工业大学学报, 2018, 35(03): 79-86.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发