• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 教学法与教学组织 • 上一篇    下一篇

基于MOOC学习行为大数据的网络课程通过率预测方法

郑龙1,2,周忠宝1,胡艳丽2,蔡建国1   

  1. (1.湖南大学工商管理学院,湖南 长沙 410082;2.国防科技大学信息系统工程重点实验室,湖南 长沙 410073)
  • 收稿日期:2018-07-11 修回日期:2018-09-15 出版日期:2018-11-26 发布日期:2018-11-25
  • 基金资助:

    湖南省普通高等学校教学改革研究项目;湖南省教育科学“十三五”规划课题(XJK016BGD009);湖南大学教改课题;国防科技大学教改课题(yjsy2015001,U2015010)

A course pass rate prediction method based
on large data of MOOC learning behavior
 

ZHENG Long1,2,ZHOU Zhongbao1,HU Yanli2,CAI Jianguo1   

  1. (1.School of Business Administration,Hunan University,Changsha 410082;
    2.Science and Technology on Information Systems Engineering Laboratory,
    National University of Defense Technology,Changsha 410073,China)
     
  • Received:2018-07-11 Revised:2018-09-15 Online:2018-11-26 Published:2018-11-25

摘要:

在分析大规模在线开放课程平台数据中影响课程通过率的评价指标基础上,引入随机图和概率论,建立了一种预测网络课程通过率的概率模型与算法。该模型基于网络图论和学习时长的随机性,通过时频域间的概率函数相互转化,直观地预测课程通过率的动态变化,可分析连续概率分布和离散经验分布函数,以及大规模的网络课程通过率问题,且便于计算机仿真实现。最后,结合Matlab给出的某一网络课程通过率算例,验证了该随机概率模型及其算法的可行性和有效性,并实际应用于高校大规模网络课程平台,显示出其良好的前景。

关键词: 计算机仿真, 大数据;课程通过率;预测

Abstract:

Based on the analysis of the evaluation indexes of the large data from the MOOC platform, we introduce the theory of random graph and probability theory, and establish a probability graph model and an algorithm for course pass rate. Based on the network graph theory and the randomness of learning duration, we analyze the dynamic change process of course pass rate qualitatively through the mutual transformation of probability function between timedomain and frequencydomain. Our model can deal with continuous probability distribution cases and discrete probability distribution cases l, as well as massive course pass rate problems highly effectively. Finally, numerical experiment results on MATLAB illustrate the feasibility and effectiveness of the proposed model and algorithm, which can be applied to university MOOC platforms and show a good application prospect.

Key words: computer simulation, large data, course pass rate, prediction