View in EDS

Learning analytics to support self-regulated learning in asynchronous online courses: A case study at a women's university in South Korea.

Saved in:
Bibliographic Details
Title: Learning analytics to support self-regulated learning in asynchronous online courses: A case study at a women's university in South Korea.
Authors: Kim, Dongho1 donghokim@ufl.edu, Yoon, Meehyun2 meehyun@uga.edu, Jo, Il-Hyun1,3 ijo@ewha.ac.kr, Branch, Robert Maribe2 rbranch@uga.edu
Source: Computers & Education. Dec2018, Vol. 127, p233-251. 19p.
Subject Terms: *Autodidacticism, *Online education, *Asynchronous learning, *Universities & colleges, *Classroom environment
Geographic Terms: South Korea
Abstract: Abstract With the recognition of the importance of self-regulated learning (SRL) in asynchronous online courses, recent research has explored how SRL strategies impact student learning in these learning environments. However, little has been done to examine different patterns of students with different SRL profiles over time, which precludes providing optimal on-going instructional support for individual students. To address the gap in research, we applied learning analytics to analyze log data from 284 undergraduate students enrolled in an asynchronous online statistics course. Specifically, we identified student SRL profiles, and examined the actual student SRL learning patterns. The k-medoids clustering identified three self-regulated learning profiles: self-regulation, partial self-regulation, and non-self-regulation. Self-regulated students showed more study regularity and help-seeking, than did the other two groups of students. The partially self-regulated students showed high study regularity but inactive help-seeking, while the non-self-regulated students exhibited less study regularity and less frequent help-seeking than the other two groups; their self-reported time management scores were significantly lower. The analysis of each week's log variables using the random forest algorithm revealed that self-regulated students studied course content early before exams and sought help during the general exam period, whereas non-self-regulated students studied the course content during the general exam period. Based on our findings, we provide instructional strategies that can be used to support student SRL. We also discuss implications of this study for advanced learning analytics research, and the design of effective asynchronous online courses. Highlights • We used students log traces to examine their self-regulated learning (SRL) patterns. • Students were classified into three clusters that represent different SRL profiles. • We provided strategies for supporting student SRL in asynchronous online courses. [ABSTRACT FROM AUTHOR]
Copyright of Computers & Education is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Education Research Complete
Description
Abstract:Abstract With the recognition of the importance of self-regulated learning (SRL) in asynchronous online courses, recent research has explored how SRL strategies impact student learning in these learning environments. However, little has been done to examine different patterns of students with different SRL profiles over time, which precludes providing optimal on-going instructional support for individual students. To address the gap in research, we applied learning analytics to analyze log data from 284 undergraduate students enrolled in an asynchronous online statistics course. Specifically, we identified student SRL profiles, and examined the actual student SRL learning patterns. The k-medoids clustering identified three self-regulated learning profiles: self-regulation, partial self-regulation, and non-self-regulation. Self-regulated students showed more study regularity and help-seeking, than did the other two groups of students. The partially self-regulated students showed high study regularity but inactive help-seeking, while the non-self-regulated students exhibited less study regularity and less frequent help-seeking than the other two groups; their self-reported time management scores were significantly lower. The analysis of each week's log variables using the random forest algorithm revealed that self-regulated students studied course content early before exams and sought help during the general exam period, whereas non-self-regulated students studied the course content during the general exam period. Based on our findings, we provide instructional strategies that can be used to support student SRL. We also discuss implications of this study for advanced learning analytics research, and the design of effective asynchronous online courses. Highlights • We used students log traces to examine their self-regulated learning (SRL) patterns. • Students were classified into three clusters that represent different SRL profiles. • We provided strategies for supporting student SRL in asynchronous online courses. [ABSTRACT FROM AUTHOR]
ISSN:03601315
DOI:10.1016/j.compedu.2018.08.023