Predicting Learners' Performance in Virtual Learning Environment (VLE) based on Demographic, Behavioral and Engagement Antecedents

Abstract

This study aims at predicting undergraduate students' performance in the Virtual Learning Environment (VLE) based on four time periods of the examined online course. This is to provide an early and continuous prediction of students' academic achievement. This research depends on data from one of the scientific courses at the Open University (OU) in Britain, which offers its lectures using VLE. The data investigated consists of 1938 students in which the influence of demographic and behavioral variables was explored first. Then, three features were generated to improve the prediction accuracy as well as examining the effect of learners' engagement on their academic performance. Accordingly, a comparison was made between the prediction accuracy of integrating the proposed features with the behavioral and demographic features and the use of the original features only. The findings suggest that some of the demographic variables and all behavioral features had a significant impact on students' performance. However, the accuracy was highly improved after using the new generated features. It was found that the level of the financial and service instability, level of participation in the course, assessment grades, the total number of clicks, the interaction with different course activities, and students' engagement were significant predictors of academic achievement.

Remote Learning in Transnational Education: Relationship between Virtual Learning Engagement and Student Academic Performance in BSc Pharmaceutical Biotechnology

“…The removal of outliers increased the correlation coefficients in all variables related to the VLE, reaching up to 0.618 with total page views, which indicates a student studying style impacting on the correlation when using all students, as some students may engage less with the VLE but perform quite well in examinations ( Figure 4 ). This observation was also reported elsewhere, where demographic and behavioural features impact student VLE engagement style [ 23 , 24 ]. The use of all of these variables in a simple linear regression model generated a correlation coefficient of 0.6 (Equation (1)) and, by removing the outliers, this increased to 0.724 (Equation (3)) ( Table 2 ).…”

Evaluation of the Implementation Online Virtual Learning in Engineering Students

“…The majority of students agree that the quality of virtual learning is sufficient to improve their learning outcomes. This has in common with the results of research on an increase in student learning performance when using virtual learning (Al-azawei & Al-masoudy, 2020). Besides that, it is also in line with research on learning simulation models able to make better understanding of the material obtained by students (Pfahl & Laitenberger, 2004), and learning modules presented in electronic media combined with discussion methods are able to improve concept understanding and problem solving (Wong et al, 2017).…”

Using Socio-Demographic Information in Predicting Students' Degree Completion based on a Dynamic Model

“…Al-Azawei and Al-Masoudy [18] used both demographic and behavioral features to determine students' learning performance in a virtual learning environment (VLE). After building the prediction model based on the M5P regression algorithm, the results showed that some of the demographic features and all online behavioral variables were predictors of students' performance.…”