Back to the Basics: Bayesian extensions of IRT outperform neural networks for proficiency estimation
This provides a simpler, better-performing alternative to neural network approaches for computer-based learning systems, though it appears incremental as it builds on established IRT methods.
The researchers compared Bayesian extensions of Item Response Theory (IRT) models against Deep Knowledge Tracing (DKT) neural networks for estimating student proficiency, finding that IRT-based methods consistently matched or outperformed DKT across three datasets, with a hierarchical IRT extension performing best overall.
Estimating student proficiency is an important task for computer based learning systems. We compare a family of IRT-based proficiency estimation methods to Deep Knowledge Tracing (DKT), a recently proposed recurrent neural network model with promising initial results. We evaluate how well each model predicts a student's future response given previous responses using two publicly available and one proprietary data set. We find that IRT-based methods consistently matched or outperformed DKT across all data sets at the finest level of content granularity that was tractable for them to be trained on. A hierarchical extension of IRT that captured item grouping structure performed best overall. When data sets included non-trivial autocorrelations in student response patterns, a temporal extension of IRT improved performance over standard IRT while the RNN-based method did not. We conclude that IRT-based models provide a simpler, better-performing alternative to existing RNN-based models of student interaction data while also affording more interpretability and guarantees due to their formulation as Bayesian probabilistic models.