Identifying At-Risk Students For Early Interventions - A Time-Series Clustering Approach
Keywords
association rules; classification; Clustering; feature extraction or construction; LMS; mining methods and algorithms; predictive modeling; time-series analysis
Abstract
The purpose of this paper is to identify at-risk online students earlier, more often, and with greater accuracy using time-series clustering. The case study showed that the proposed approach could generate models with higher accuracy and feasibility than the traditional frequency aggregation approaches. The best performing model can start to capture at-risk students from week 10. In addition, the four phases in student's learning process detected holiday effect and illustrate at-risk students' behaviors before and after a long holiday break. The findings also enable online instructors to develop corresponding instructional interventions via course design or student-teacher communications.
Publication Date
1-1-2017
Publication Title
IEEE Transactions on Emerging Topics in Computing
Volume
5
Issue
1
Number of Pages
45-55
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/TETC.2015.2504239
Copyright Status
Unknown
Socpus ID
85027688738 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85027688738
STARS Citation
Hung, Jui Long; Wang, Morgan C.; Wang, Shuyan; Abdelrasoul, Maha; and Li, Yaohang, "Identifying At-Risk Students For Early Interventions - A Time-Series Clustering Approach" (2017). Scopus Export 2015-2019. 5895.
https://stars.library.ucf.edu/scopus2015/5895