USP Electronic Research Repository

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

Jokhan, Anjeela D. and Sharma, Bibhya N. and Singh, Shaveen (2018) Early warning system as a predictor for student performance in higher education blended courses. Studies in Higher Education . pp. 1-12. ISSN 0307-5079

[img] PDF - Published Version
Restricted to Repository staff only

Download (1725Kb)

    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 under performing students early in their course of allowing for early intervention.

    Item Type: Journal Article
    Subjects: L Education > LB Theory and practice of education > LB2300 Higher Education
    Q Science > QA Mathematics > QA76 Computer software
    Divisions: Faculty of Science, Technology and Environment (FSTE) > School of Computing, Information and Mathematical Sciences
    Faculty of Science, Technology and Environment (FSTE)
    Depositing User: Fulori Nainoca
    Date Deposited: 24 May 2018 12:32
    Last Modified: 24 May 2018 12:32
    URI: http://repository.usp.ac.fj/id/eprint/10765
    UNSPECIFIED

    Actions (login required)

    View Item

    Document Downloads

    More statistics for this item...