Lei Shi
Temporal Analysis in Massive Open Online Courses – Towards Identifying at-Risk Students Through Analyzing Demographical Changes
Shi, Lei; Yang, Bokuan; Toda, Armando
Authors
Bokuan Yang
Armando Toda
Contributors
A. Siarheyeva
Editor
C. Barry
Editor
M. Lang
Editor
H. Linger
Editor
C. Schneider
Editor
Abstract
This chapter demonstrates a temporal analysis in Massive Open Online Courses (MOOCs), towards identifying at-risk students through analyzing their demographical changes. At-risk students are those who tend to drop out from the MOOCs. Previous studies have shown that how students interact in MOOCs could be used to identify at-risk students. Some studies considered student diversity by looking into subgroup behavior. However, most of them lack consideration of students’ demographical changes. Towards bridging the gap, this study clusters students based on both their interaction with the MOOCs (activity logs) and their characteristics and explores their demographical changes along the MOOCs progress. The result shows students’ demographical characteristics (membership of subgroups) changed significantly in the first half of the course and stabilized in the second half. Our findings provide insight into how students may be engaged in MOOCs and suggest the improvement of identifying at-risk students based on the temporal data.
Citation
Shi, L., Yang, B., & Toda, A. (2020). Temporal Analysis in Massive Open Online Courses – Towards Identifying at-Risk Students Through Analyzing Demographical Changes. In A. Siarheyeva, C. Barry, M. Lang, H. Linger, & C. Schneider (Eds.), Advances in information systems development (146-163). Springer Verlag. https://doi.org/10.1007/978-3-030-49644-9_9
Online Publication Date | Aug 1, 2020 |
---|---|
Publication Date | 2020 |
Deposit Date | Aug 2, 2020 |
Publicly Available Date | Aug 4, 2020 |
Publisher | Springer Verlag |
Pages | 146-163 |
Series Title | Lecture notes in information systems and organisation |
Series Number | 39 |
Book Title | Advances in information systems development. |
ISBN | 9783030496432 |
DOI | https://doi.org/10.1007/978-3-030-49644-9_9 |
Files
Accepted Book Chapter
(479 Kb)
PDF
Copyright Statement
The final authenticated version is<br />
available online at https://doi.org/10.1007/978-3-030-49644-9_9
You might also like
Is Unimodal Bias Always Bad for Visual Question Answering? A Medical Domain Study with Dynamic Attention
(2022)
Conference Proceeding
Efficient Uncertainty Quantification for Multilabel Text Classification
(2022)
Conference Proceeding