Does Interpretability of Knowledge Tracing Models Support Teacher Decision Making?

TL;DR

This study investigates whether the interpretability of knowledge tracing models improves teacher decision-making, finding that while interpretability increases trust and usability, it does not significantly reduce the number of tasks needed for mastery.

Contribution

The paper provides the first empirical evidence on how interpretability of KT models influences teacher decisions and student mastery, combining simulation and human teacher studies.

Findings

Interpretable KT models increase teacher trust and perceived usability.

Teacher decisions based on interpretability do not significantly reduce tasks to mastery.

Simulation shows faster mastery with interpretable models.

Abstract

Knowledge tracing (KT) models are a crucial basis for pedagogical decision-making, namely which task to select next for a learner and when to stop teaching a particular skill. Given the high stakes of pedagogical decisions, KT models are typically required to be interpretable, in the sense that they should implement an explicit model of human learning and provide explicit estimates of learners' abilities. However, to our knowledge, no study to date has investigated whether the interpretability of KT models actually helps human teachers to make teaching decisions. We address this gap. First, we perform a simulation study to show that, indeed, decisions based on interpretable KT models achieve mastery faster compared to decisions based on a non-interpretable model. Second, we repeat the study but ask $N=12$ human teachers to make the teaching decisions based on the information provided by KT models. As expected, teachers rate interpretable KT models higher in terms of usability and trustworthiness. However, the number of tasks needed until mastery hardly differs between KT models. This suggests that the relationship between model interpretability and teacher decisions is not straightforward: teachers do not solely rely on KT models to make decisions and further research is needed to investigate how learners and teachers actually understand and use KT models.