An Empirical Comparison of Deep Learning Models for Knowledge Tracing on Large-Scale Dataset
This work provides guidance for selecting deep learning methods in educational technology when large student performance datasets are available, but it is incremental as it builds on existing techniques.
The paper tackled the problem of knowledge tracing by empirically comparing deep learning models on a large-scale dataset, showing that incorporating contextual information like exercise relations and student forget behavior improves performance.
Knowledge tracing (KT) is the problem of modeling each student's mastery of knowledge concepts (KCs) as (s)he engages with a sequence of learning activities. It is an active research area to help provide learners with personalized feedback and materials. Various deep learning techniques have been proposed for solving KT. Recent release of large-scale student performance dataset \cite{choi2019ednet} motivates the analysis of performance of deep learning approaches that have been proposed to solve KT. Our analysis can help understand which method to adopt when large dataset related to student performance is available. We also show that incorporating contextual information such as relation between exercises and student forget behavior further improves the performance of deep learning models.