云学习平台大学生学业成绩预测与干预研究

发布时间：2018-01-20 08:04

本文关键词： 云学习平台学业成绩预测干预多元线性回归　出处：《中国远程教育》2016年09期 　论文类型：期刊论文

【摘要】：预测在校大学生学业成绩并及时进行干预指导,是提升大学生学习效果的有效途径。云环境下,学习中过程性数据的积累为预测分析提供了有力依据。本研究设计并开展一门基于实体课堂和云学习平台(MOODLE平台、微信平台)的混合式大学课程。通过收集学生多类属性及学习过程性数据建立多元回归模型,对其将取得的成绩进行预测,并展开教学干预以提升其学习效果。结果显示,在预测模型方面,多元回归模型可以在全班水平上取得较佳的预测效果;在预测因子方面,绩点、在线学习参与度、前导课成绩和学习兴趣是影响学业成绩的重要因素;在干预效果方面,教学干预取得了较好效果,学弱群体接受干预后进步显著。
[Abstract]:It is an effective way to improve the learning effect of college students to predict the academic achievement of college students and conduct timely intervention guidance. The accumulation of process data in learning provides a strong basis for prediction and analysis. This study designed and carried out an entity based classroom and cloud learning platform Moode platform. WeChat platform) of mixed university courses. Through the collection of students' multi-class attributes and learning process data to establish a multi-regression model to predict the results it will achieve. Teaching intervention was carried out to improve the learning effect. The results showed that the multivariate regression model could achieve better prediction effect on the whole class level. In terms of predictive factors, GPA, online learning participation, leading class achievement and learning interest are the important factors that affect academic achievement. In the aspect of intervention effect, the teaching intervention has achieved better effect, and the learning weak group has made remarkable progress after accepting the intervention.
【作者单位】：首都师范大学信息工程学院;
【基金】：国家社会科学基金重大委托项目“语言大数据挖掘与文化价值发现”(批准号:14&ZH0036)的部分研究成果
【分类号】：G434
【正文快照】： 一、研究背景在线学习和课堂学习相结合的混合式教学方法,已成为目前许多高校正在探索的模式。随着以云计算、云存储为标志的云时代的到来,在线学习方式变得更加多元。学习者可以随时随地使用任何设备接入云端学习平台,基于云存储的大量在线学习痕迹也为学业成绩预测和个性化

【相似文献】