On the Effectiveness of Self-Training in MOOC Dropout Prediction

Abstract

Massive open online courses (MOOCs) have gained enormous popularity in recent years and have attracted learners worldwide. However, MOOCs face a crucial challenge in the high dropout rate, which varies between 91%-93%. An interplay between different learning analytics strategies and MOOCs have emerged as a research area to reduce dropout rate. Most existing studies use click-stream features as engagement patterns to predict at-risk students. However, this study uses a combination of click-stream features and the influence of the learner’s friends based on their demographics to identify potential dropouts. Existing predictive models are based on supervised learning techniques that require the bulk of hand-labelled data to train models. In practice, however, scarcity of massive labelled data makes training difficult. Therefore, this study uses self-training, a semi-supervised learning model, to develop predictive models. Experimental results on a public data set demonstrate that semi-supervised models attain comparable results to state-ofthe-art approaches, while also having the flexibility of utilizing a small quantity of labelled data. This study deploys seven well-known optimizers to train the self-training classifiers, out of which, Stochastic Gradient Descent (SGD) outperformed others with the value of F1 score at 94.29%, affirming the relevance of this exposition.

Exploring the factors influencing users’ satisfaction and continuance intention of MOOCs in China

“…Alraimi, Zo, and Ciganek (2015) pointed out that retention rates are on average less than 10 percent and the completion rate is extremely low. Dropout rates of MOOCs are between 91 percent and 93 percent (Goel & Goyal, 2020). A high dropout rate leads to an average completion rate which is less than 13 percent (Krause, Mogalle, Pohl, & Williams, 2015).…”

An Interpretable Pipeline for Identifying At-Risk Students

“…As such, we employed the SMOTE technique on student learning data each week to make sure samples in the two target classes in the dataset are equal. This is in line with the research of Goel and Goyal (2020). Multiple approaches (i.e., Undersampling, Oversampling, and Hybrid methods) were employed by the authors to balance the different classes in the dataset to ensure that the model could better capture the underlying patterns.…”

Recent advances in Predictive Learning Analytics: A decade systematic review (2012–2022)

“…Another research described by Gray and Perkins ( 2019 ) and Chui et al ( 2020 ) identified marginal students who are at-risk of low achievement. Authors in (Adnan et al, 2021 ; Dass et al, 2021 ; Goel & Goyal, 2020 ; Kabathova & Drlik, 2021 ) identified dropout students based on their academic results.…”