Paper Info
Title
Developing a Learning Analytics Intervention in E-learning to Enhance Students’ Learning Performance: A Case Study
Abstract
The emergence of Learning Analytics has brought benefits to the educational field, as it can be used to analyse authentic data from students to identify the problems encountered in e-learning and to provide intervention to assist students. However, much is still unknown about the development of Learning Analytics intervention in terms of providing personalised learning materials to students to meet their needs in order to enhance their learning performance. Thus, this study aims to develop a Learning Analytics intervention in e-learning to enhance students’ learning performance. In order to develop the intervention, four stages of Learning Analytics Cycle proposed by Clow: learner, data, metrics and intervention were carried out, integrating with two well-known models: Felder-Silverman’s and Keller’s Attention, Relevance, Confidence and Satisfaction (ARCS) models in e-learning, to develop various Learning Objects in e-learning. After that, a case study was carried out to assess this intervention with various validated research instruments. A quantitative approach involving a one-group pre-test–post-test experimental design was adopted, which consists of a population of 50 undergraduate students who enrolled in the Information System Management in Education course. The results indicated that the Learning Analytics intervention is useful, as it overall helped the majority of students to enhance their motivation, academic achievement, cognitive engagement and cognitive retention in e-learning. From this study, readers can understand the way to implement the Learning Analytics intervention which is proved to made positive impact on students’ learning achievement with the Cohen’s d of 5.669. Lastly, this study contributes significant new knowledge to the current understanding of how Learning Analytics intervention can perform to optimize students’ learning experience and also serves to fill a gap in research on Learning Analytics, namely the lack of development of interventions to assist students.
Year
DOI
Venue
2022
10.1007/s10639-022-10904-0
Education and Information Technologies
Keywords
DocType
Volume
Learning analytics intervention, Personalised learning objects, e-learning, At-risk students
Journal
27
Issue
ISSN
Citations 
5
1360-2357
0
PageRank 
References 
Authors
0.34
2
2
Name
Order
Citations
PageRank
Si Na Kew100.34
Zaidatun Tasir200.68