Equity and Fairness of Bayesian Knowledge Tracing

TL;DR

This paper examines the fairness of Knowledge Tracing-based tutoring systems, introduces a new model BBKT for better individualization, and shows it enhances equity and effectiveness over existing models.

Contribution

The paper introduces Bayesian-Bayesian Knowledge Tracing (BBKT), a novel model that improves individualization and fairness in tutoring curricula derived from Knowledge Tracing models.

Findings

Existing models like BKT and DKT can be inequitable.

BBKT enables more personalized and equitable tutoring.

Curricula from BBKT outperform classical models in fairness and effectiveness.

Abstract

We consider the equity and fairness of curricula derived from Knowledge Tracing models. We begin by defining a unifying notion of an equitable tutoring system as a system that achieves maximum possible knowledge in minimal time for each student interacting with it. Realizing perfect equity requires tutoring systems that can provide individualized curricula per student. In particular, we investigate the design of equitable tutoring systems that derive their curricula from Knowledge Tracing models. We first show that many existing models, including classical Bayesian Knowledge Tracing (BKT) and Deep Knowledge Tracing (DKT), and their derived curricula can fall short of achieving equitable tutoring. To overcome this issue, we then propose a novel model, Bayesian-Bayesian Knowledge Tracing (BBKT), that naturally enables online individualization and, thereby, more equitable tutoring. We demonstrate that curricula derived from our model are more effective and equitable than those derived from classical BKT models. Furthermore, we highlight that improving models with a focus on the fairness of next-step predictions might be insufficient to develop equitable tutoring systems.