Uncertainty-Aware Knowledge Tracing Models
This work tackles student error detection in educational platforms, particularly for limited-resource settings, but is incremental as it adds uncertainty capabilities to existing KT models.
The paper addresses the problem of Knowledge Tracing (KT) models making incorrect predictions when students choose distractors, by introducing an approach to capture predictive uncertainty, showing that higher uncertainty aligns with model errors.
The main focus of research on Knowledge Tracing (KT) models is on model developments with the aim of improving predictive accuracy. Most of these models make the most incorrect predictions when students choose a distractor, leading to student errors going undetected. We present an approach to add new capabilities to KT models by capturing predictive uncertainty and demonstrate that a larger predictive uncertainty aligns with model incorrect predictions. We show that uncertainty in KT models is informative and that this signal would be pedagogically useful for application in an educational learning platform that can be used in a limited resource setting where understanding student ability is necessary.