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

Kim, Dongho; Yoon, Meehyun; Jo, Il Hyun; Branch, Robert Maribe

doi:10.1016/j.compedu.2018.08.023

Cited by 115 publications

(95 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They clustered students into four groups based on self-reported SRL data and found their actual learning patterns in gStudy differed substantially, even among students from the same cluster. Kim, et al (2018) made a similar comparison among undergraduates in Korea. They analysed online trace data from 284 undergraduate students enrolled in an asynchronous online statistics course.…”

Section: Status Of Research On Srl Combining Self-reports and Online mentioning

confidence: 99%

“…In addition, this study compares multiple cohorts, which yields insight in continuity and change of strategy use with the constant evolvement of course design. Secondly, the few studies that have been comparing self-reports and online trace data so far dealt with relatively small sample sizes (Cho & Yoo, 2017;Guerra et al, 2016;Hadwin et al, 2007;Kim et al, 2018) or did not measure the full range of self-motivational beliefs and strategies with self-reports (Hadwin et al, 2007;Cho & Yoo, 2017). As a result, there is no clarity, yet, on the relevance and actionability of online trace data in comparison to inventories on motivation, strategy use, and self-regulation.…”

Section: Research Questions and Hypothesesmentioning

confidence: 99%

See 1 more Smart Citation

Tracking Patterns in Self-Regulated Learning Using Students’ Self-Reports and Online Trace Data

Halem

Klaveren

Drachsler

et al. 2020

FLR

View full text Add to dashboard Cite

For decades, self-report instruments-which rely heavily on students' perceptions and beliefs-have been the dominant way of measuring motivation and strategy use. Eventbased measures based on online trace data arguably has the potential to remove analytical restrictions of self-report measures. The purpose of this study is therefore to triangulate constructs suggested in theory and measured using self-reported data with revealed online traces of learning behaviour. The results show that online trace data of learning behaviour are complementary to self-reports, as they explained a unique proportion of variance in student academic performance. The results also reveal that self-reports explain more variance in online learning behaviour of prior weeks than variance in learning behaviour in succeeding weeks. Student motivation is, however, to a lesser extent captured with online trace data, likely because of its covert nature. In that respect, it is of importance to recognize the crucial role of self-reports in capturing student learning holistically. This manuscript is 'frontline' in the sense that event-based measurement methodologies with online trace data are relatively unexplored. The comparison with self-report data made in this manuscript sheds new light on the added values of innovative and traditional methods of measuring motivation and strategy use.

show abstract

Section: Status Of Research On Srl Combining Self-reports and Online mentioning

confidence: 99%

Section: Research Questions and Hypothesesmentioning

confidence: 99%

Tracking Patterns in Self-Regulated Learning Using Students’ Self-Reports and Online Trace Data

Halem

Klaveren

Drachsler

et al. 2020

FLR

View full text Add to dashboard Cite

show abstract

“…The quality and effectiveness of decision processes can be greatly enhanced using educational data mining [27], and likewise, vital feedbacks from students can also be evaluated using data mining techniques in order to identify lapses, areas of need and improvement in teaching and learning processes. Through data mining techniques, students can be classified into unique groups based on well-defined criteria to enable the deployment of purposespecific and targeted learning interventions, and for identifying common skill set, social attitudes, learning behaviours [28,29] and interests [30,31]. The effectiveness of academic modules and the developments of new contents can also be evaluated using data mining techniques [32].…”

Section: Introductionmentioning

confidence: 99%

Toward an improved learning process: the relevance of ethnicity to data mining prediction of students’ performance

Adekitan

Salau

2019

SN Appl. Sci.

View full text Add to dashboard Cite

The ability to predict failure is an advantageous educational tool that can be effectively used to counsel student, and this may also be used as a tool for developing, and channelling adequate academic interventions toward preventing failure and dropout tendencies. Students are generally admitted based on their evaluated academic potentials as measured using their admission criteria scores. This study seeks to identify the relationship, if any, between the admission criteria scores and the graduation grades, and to examine the influence of ethnicity using the geopolitical zone of origin of the student on the predictive accuracy of the models developed using a Nigerian University as a case study. Data mining analyses were carried out using four classifiers on the Orange Software, and the results were verified with multiple regression analysis. The maximum classification accuracy observed is 53.2% which indicates that the pre-admission scores alone are insufficient for predicting the graduation result of students but it may serve as a useful guide. By applying over-sampling technique, the accuracy increased to 79.8%. The results establish that the ethnic background of the student is statistically insignificant in predicting their graduation results. Hence, the use of ethnicity in admission processes is therefore not ideal.

show abstract

“…Going forward, it seems that the emphasis on behaviours will only deepen because technological innovation in online learning systems is likely to improve the access, quality and use of computer-generated logs of learner behaviours (Ben-Eliyahu & Bernacki, 2015). After all, behavioural involvement is the only facet of learning that leaves 'visible' traces online and thus generates research data that are relatively easy to capture and incorporate in pedagogical research (Kim, Yoon, Jo, & Branch, 2018).…”

Section: Interactivity In Online Pedagogiesmentioning

confidence: 99%

“…[Insert Table 2 here] For each participating student, we collected evidence from the learning platform (Moodle) that reflected their online activity and captured the intensity of their behavioural engagement with eLearning. In line with previous studies (Huang et al, 2012;Kim et al, 2018;Shaw, 2012), the evidence included system logs (the total number of logs during the eight weeks or the number of times student entered the learning platform, the pattern of logs over time, and time on the platform) and other evidence of their activity (e.g. posts, replies, uploads of files, quizzes, downloads, video views).…”

Section: [Insert Figure1 Here]mentioning

confidence: 99%

Of Possums, Hogs, and Horses: Capturing the Duality of Student Engagement in eLearning

Morgan‐Thomas

Dudau

2019

AMLE

View full text Add to dashboard Cite

The current preoccupation with activity and interactivity in pedagogical research on eLearning precariously elevates the importance of students' behavioural engagement and insufficiently accounts for other forms of productive involvement in learning. We argue that theoretical developments on the concept of student engagement offer a critical opportunity to revise this stance and problematize online activity. Through the lens of engagement, we depict online engagement as a multi-dimensional concept that encompasses behaviour, emotion and cognition. We further argue that the focus of online engagement may be dual in nature: engagement with online pedagogies and, separately, with the substantive knowledge being acquired. This study draws on qualitative data from postgraduate management research students in an online research methods course. To tease out the complexity of engagement, we use evidence of online activity to categorize learners into three distinct types: hogs, possums and horses. We juxtapose these behavioural categories against narrative accounts of engagement in eLearning to reveal a rich set of textures as well as misalignment among behaviour, emotion and cognition. The findings seem to question the privileged status of interactivity in online pedagogy and tentatively suggest the possibility that online disengagement may not be detrimental to learning.

show abstract

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

Cited by 115 publications

References 82 publications

Tracking Patterns in Self-Regulated Learning Using Students’ Self-Reports and Online Trace Data

Tracking Patterns in Self-Regulated Learning Using Students’ Self-Reports and Online Trace Data

Toward an improved learning process: the relevance of ethnicity to data mining prediction of students’ performance

Of Possums, Hogs, and Horses: Capturing the Duality of Student Engagement in eLearning

Contact Info

Product

Resources

About