题目：Using Learning Analytics to Support Self-regulated Learning in Online Courses (利用学习分析技术支持在线自主学习)

2021年12月21日，13:30-14:30

主  讲： 李秋劼 博士

主持人：贾积有教授

评议人：北京师范大学武法提教授

腾讯会议链接：https://meeting.tencent.com/dm/8Ava0SnNNZGh

会议 ID：755-275-872

摘要：已有研究表明自主学习能力是影响员工在线学习表现的重要因素。在线平台自动记录的海量学习日志数据,以及基于此数据发展起来的学习分析技术，为测量、理解、支持在线自主学习带来了新的机遇。近年来，大量研究开始探讨如何通过学习日志数据实时测量学习者的自主学习能力，以及如何利用平台测量指标还原学习者的自主学习过程并有效甄别自主学习能力较差的员工。研究者们还利用平台数据开发面向学习者的学习分析反馈报告，用来帮助学习者更好地反思和改进自己的学习过程。虽然现有研究已经取得了一定成果，但两个关键问题亟待解答：1）利用平台数据测量自主学习能力的效果如何？；2）基于学习分析的反馈报告对学习者的学习过程和学习成就会产生怎样的影响以及通过何种机制产生该影响？针对这些问题，本次报告将介绍两个利用学习分析技术支持在线自主学习的实证研究。第一项研究利用Canvas学习平台日志数据，构建学习者时间管理能力和学习力维持能力两方面指标，进而验证该两项指标的有效性；第二项研究采用随机试验的方法，在本科课程中检验一种在线学习分析反馈干预对学习过程和学习成就的影响，并验证该项干预的影响机制。

The ability to regulate one’s learning is essential for success in online courses. Clickstream data, the detailed and real-time record of students’ interaction with the online platforms, provide new opportunities to measure, understand, and support students’ self-regulation in virtual learning. Recent efforts have used clickstream data to create timely, fine-grained, and comprehensive measures of self-regulated learning (SRL) behaviors in online courses in an attempt to shed light on the process of SRL and to improve the identification of students who lack SRL skills and are at risk of low achievement. Studies have also attempted to support students’ self-regulation in virtual learning environments using the clickstream data to provide students with learning analytics on their behaviors. However, key questions remain: to what extent do these clickstream measures correspond to traditional self-reported measures about specific SRL constructs? How effective are learning analytics interventions on student learning process and performance outcomes and what are the operating mechanisms? In this talk, I will discuss two studies that attempted to answer these questions. The first study used the clickstream data collected from Canvas to measure two aspects of SRL (i.e., time management and effort regulation) and triangulated clickstream measures with student self-reported data from before and after the course. The second study tested the effect of one learning analytics intervention on student outcomes and verified a proposed mechanism through a randomized controlled trial in a large online undergraduate course.

报告人简介：李秋劼，加州尔湾大学分校博士后研究员，加州大学欧文分校教育学博士，此前分别获得北京师范大学教育技术学硕士和学士学位。主要研究方向包括：高等教育阶段在线教学的效果评估与提升等议题。她的研究先后在The Internet and Higher Education、Computers and Education、Educational Evaluation and Policy Analysis、Motivation and Emotion、Research in Higher Education、International Conference on Educational Data Mining, International Conference on Learning Analytics and Knowledge等杂志和会议上发表。