Predictive Modeling of Student Dropout in MOOCs and Self-Regulated Learning

Abstract

The primary objective of this study is to examine the factors that contribute to the early prediction of Massive Open Online Courses (MOOCs) dropouts in order to identify and support at-risk students. We utilize MOOC data of specific duration, with a guided study pace. The dataset exhibits class imbalance, and we apply oversampling techniques to ensure data balancing and unbiased prediction. We examine the predictive performance of five classic classification machine learning (ML) algorithms under four different oversampling techniques and various evaluation metrics. Additionally, we explore the influence of self-reported self-regulated learning (SRL) data provided by students and various other prominent features of MOOCs as potential indicators of early stage dropout prediction. The research questions focus on (1) the performance of the classic classification ML models using various evaluation metrics before and after different methods of oversampling, (2) which self-reported data may constitute crucial predictors for dropout propensity, and (3) the effect of the SRL factor on the dropout prediction performance. The main conclusions are: (1) prominent predictors, including employment status, frequency of chat tool usage, prior subject-related experiences, gender, education, and willingness to participate, exhibit remarkable efficacy in achieving high to excellent recall performance, particularly when specific combinations of algorithms and oversampling methods are applied, (2) self-reported SRL factor, combined with easily provided/self-reported features, performed well as a predictor in terms of recall when LR and SVM algorithms were employed, (3) it is crucial to test diverse machine learning algorithms and oversampling methods in predictive modeling.

Autorregulate: An Alternative to Support Self-Regulation in MOOCs

“…Psathas et al [10] reported their study exploring the effectiveness of machine learning models in predicting student dropout rates in MOOCs, focusing on the impact of self-regulated learning (SRL) data. The study highlights the use of oversampling techniques to manage data imbalances, and it demonstrates that SRL data, along with participant records in MOOCs, such as employment status and chat usage, significantly improve the predictive capacity of these models.…”

“…As a result, various lines of research have been created in the field of MOOCs as an object of study, among which are the specification of the MOOC creation processes [3]- [5], gamification as a teaching strategy in MOOCs [6], the evaluation of the quality of MOOCs [7], the analysis of various types of interaction of the participants [8]- [10], accessibility in the contents of MOOCs [11], as well as support for Self-regulated Learning (SRL) [12]- [17].…”

Predicting Dropout in Programming MOOCs through Demographic Insights

“…Several studies take into account both behavioral and demographic features to increase the accuracy of online courses dropouts prediction [15,[27][28][29][30][31][32][33][34]. There are also studies showing the impact of user information and course attributes on dropout prediction [16,[35][36][37][38]. Throughout the analysis of the studies, behavioral (log data) followed by demographic data were the most widely used in both dropout prediction and performance prediction.…”

“…Table 1 lists identified literature sources that took into account demographic predictors influencing the dropout/completion rate in MOOCs and online courses. [34] 597,692 * X X X E3, U1, U3, U5, U8 [36] 379 X X X X C1, C2, U4 [45] 2338 X X X X X D9 [37] 67,333 X X X X A1, A4, H1, U5, U6, U7 [46] 79 X X X D10 [30] 32,593 ** X X X X B9, D1, D11, E4, U1, U2, U7 [27] Unspecified X X X X X D2-D8, H1, S1, S2 [3] 668,017 *** X X X C1, U1, U5, U9, U11 [47] 624 X X X X X A3, A4, D6, D9, H3 [28] 32,593 ** X X X X D1, D11, E4, U1, U2, U7 [38] 1069 X X X X A4, H1, H4, S4, S5 [48] 1038 X X X A3, A4, H1, S4, U11 [29] 14,791 X X X D10, S2, U7, U9, U11 [49] 154,763 X X X D9, U1, U7, U9, U14 * HarvardX, ** OULAD, *** XuetangX.…”