Early warning system as a predictor for student performance in higher education blended courses

Anjeela Jokhan, Bibhya Sharma, Shaveen Singh

Research output: Contribution to journalArticleResearchpeer-review

5 Citations (Scopus)

Abstract

Early warning systems are being used to assist students in their studies as well as understanding student behaviour and performance better. A home-grown EWS plug-in for Moodle was used to predict the student performance in a first year IT literacy course at University of the South Pacific. The alert tool was designed to capture student logins, completion of online activities and online engagement. Data were captured from Moodle and statistical modelling using the regression model was used to determine any correlation between student’s online behaviour and their performance. Student performance in this higher education course could be predicted based on their average logins per week and the average completion rates of activities. The accuracy of the model was 60.8%. Hence the EWS can be a very useful tool to measure student progression in a course as well as identifying underperforming students early in their course of allowing for early intervention.

Original languageEnglish
Pages (from-to)1900-1911
Number of pages12
JournalStudies in Higher Education
Volume44
Issue number11
DOIs
Publication statusPublished - 22 May 2018
Externally publishedYes

Keywords

  • at-risk students
  • Early warning system
  • higher education
  • online learning

Cite this