Counterfactual Monotonic Knowledge Tracing for Assessing Students' Dynamic Mastery of Knowledge Concepts

TL;DR

This paper introduces Counterfactual Monotonic Knowledge Tracing (CMKT), a novel method that uses counterfactual assumptions to improve the accuracy of assessing students' evolving mastery of knowledge concepts in educational settings.

Contribution

The paper proposes a new counterfactual-based approach for knowledge tracing that constrains the evolution of mastery estimates, addressing limitations of previous implicit methods.

Findings

Demonstrates improved accuracy in mastery estimation.

Effectively constrains the evolution of knowledge mastery values.

Enhances the reliability of student modeling in educational applications.

Abstract

As the core of the Knowledge Tracking (KT) task, assessing students' dynamic mastery of knowledge concepts is crucial for both offline teaching and online educational applications. Since students' mastery of knowledge concepts is often unlabeled, existing KT methods rely on the implicit paradigm of historical practice to mastery of knowledge concepts to students' responses to practices to address the challenge of unlabeled concept mastery. However, purely predicting student responses without imposing specific constraints on hidden concept mastery values does not guarantee the accuracy of these intermediate values as concept mastery values. To address this issue, we propose a principled approach called Counterfactual Monotonic Knowledge Tracing (CMKT), which builds on the implicit paradigm described above by using a counterfactual assumption to constrain the evolution of students' mastery of knowledge concepts.