Predicting Abandonment in Online Coding Tutorials
This addresses the issue of learner dropout in online education, offering a potential tool for timely intervention, though it is incremental as it applies existing methods to a new dataset.
The paper tackled the problem of predicting learner abandonment in online coding tutorials by developing machine-learned classifiers using interaction logs from a programming game, achieving prediction rates of 61% to 76% for learners not completing the next level with an average AUC of 0.68.
Learners regularly abandon online coding tutorials when they get bored or frustrated, but there are few techniques for anticipating this abandonment to intervene. In this paper, we examine the feasibility of predicting abandonment with machine-learned classifiers. Using interaction logs from an online programming game, we extracted a collection of features that are potentially related to learner abandonment and engagement, then developed classifiers for each level. Across the first five levels of the game, our classifiers successfully predicted 61% to 76% of learners who did not complete the next level, achieving an average AUC of 0.68. In these classifiers, features negatively associated with abandonment included account activation and help-seeking behaviors, whereas features positively associated with abandonment included features indicating difficulty and disengagement. These findings highlight the feasibility of providing timely intervention to learners likely to quit.