Blending E-Learning with Hands-on Laboratory Instruction in Engineering Education

An Experimental Study on Early Prediction of Student Performance and Behavior

Abstract

Among the various information sources exploited for the improvement of the learning process and outcomes, access and usage data from the interaction of students with e-learning platforms along with (past) student performance data are established as the two most meaningful and informative groups of variables. In the present study, these two groups of variables are jointly investigated as to their efficiency in providing both accurate and early prediction of student performance and behavior. The relevant educational intervention is designed and implemented as a quasi-experiment with undergraduate Electrical and Electronics Engineering students, under a novel approach that blends e-learning (asynchronous e-study and synchronous e-assessment) with a hands-on laboratory component. Can educational data mining algorithms provide both early and accurate prediction of student performance and student behavior under this scenario? If yes, how much prediction accuracy can be traded for prediction timeliness in order to allow a proactive class instructor take supportive measures for weak/marginal students, implementing a ‘self-contained’ strategy? To answer these questions, real data from the interaction of 3 academic year student cohorts with moodle are collected and analyzed. Results reveal that the proposed scenario can afford both accurate and early prediction of student performance and behavior, on the basis of data collected within the running academic term. The middle of the term is indicated as the earliest time point for getting meaningful predictions. Moreover, clustering of the data in the selected feature space reveals a consistent and therefore exploitable behavior of students along the term.