KTCF: Actionable Recourse in Knowledge Tracing via Counterfactual Explanations for Education
Woojin Kim, Changkwon Lee, Hyeoncheol Kim

TL;DR
This paper introduces KTCF, a novel counterfactual explanation method for Knowledge Tracing in education, providing actionable, causal insights that improve student modeling and educational instruction, with demonstrated superior performance.
Contribution
We propose KTCF, a new counterfactual explanation approach for KT that incorporates concept relationships and translates explanations into educational instructions.
Findings
KTCF outperforms existing methods with 5.7% to 34% improvements.
The educational instructions reduce study burden effectively.
Counterfactual explanations enhance responsible AI use in education.
Abstract
Using Artificial Intelligence to improve teaching and learning benefits greater adaptivity and scalability in education. Knowledge Tracing (KT) is recognized for student modeling task due to its superior performance and application potential in education. To this end, we conceptualize and investigate counterfactual explanation as the connection from XAI for KT to education. Counterfactual explanations offer actionable recourse, are inherently causal and local, and easy for educational stakeholders to understand who are often non-experts. We propose KTCF, a counterfactual explanation generation method for KT that accounts for knowledge concept relationships, and a post-processing scheme that converts a counterfactual explanation into a sequence of educational instructions. We experiment on a large-scale educational dataset and show our KTCF method achieves superior and robust performance…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsIntelligent Tutoring Systems and Adaptive Learning · Explainable Artificial Intelligence (XAI) · Online Learning and Analytics
