No Task Left Behind: Multi-Task Learning of Knowledge Tracing and Option Tracing for Better Student Assessment

TL;DR

This paper introduces DP-MTL, a multi-task learning framework that jointly models knowledge tracing and option tracing to enhance student assessment accuracy, especially for multiple-choice questions.

Contribution

It presents a novel multi-task learning approach that combines knowledge tracing and option tracing, improving assessment precision and benefiting downstream scoring tasks.

Findings

DP-MTL significantly improves KT and OT performance.

The framework enhances downstream score prediction accuracy.

KT acts as a regularizer for OT in the model.

Abstract

Student assessment is one of the most fundamental tasks in the field of AI Education (AIEd). One of the most common approach to student assessment is Knowledge Tracing (KT), which evaluates a student's knowledge state by predicting whether the student will answer a given question correctly or not. However, in the context of multiple choice (polytomous) questions, conventional KT approaches are limited in that they only consider the binary (dichotomous) correctness label (i.e., correct or incorrect), and disregard the specific option chosen by the student. Meanwhile, Option Tracing (OT) attempts to model a student by predicting which option they will choose for a given question, but overlooks the correctness information. In this paper, we propose Dichotomous-Polytomous Multi-Task Learning (DP-MTL), a multi-task learning framework that combines KT and OT for more precise student assessment. In particular, we show that the KT objective acts as a regularization term for OT in the DP-MTL framework, and propose an appropriate architecture for applying our method on top of existing deep learning-based KT models. We experimentally confirm that DP-MTL significantly improves both KT and OT performances, and also benefits downstream tasks such as Score Prediction (SP).