Extracting Causal Relations in Deep Knowledge Tracing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hong, Kevin, Karbasi, Kia, Pottie, Gregory
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915601809670144
author Hong, Kevin
Karbasi, Kia
Pottie, Gregory
author_facet Hong, Kevin
Karbasi, Kia
Pottie, Gregory
contents A longstanding goal in computational educational research is to develop explainable knowledge tracing (KT) models. Deep Knowledge Tracing (DKT), which leverages a Recurrent Neural Network (RNN) to predict student knowledge and performance on exercises, has been proposed as a major advancement over traditional KT methods. Several studies suggest that its performance gains stem from its ability to model bidirectional relationships between different knowledge components (KCs) within a course, enabling the inference of a student's understanding of one KC from their performance on others. In this paper, we challenge this prevailing explanation and demonstrate that DKT's strength lies in its implicit ability to model prerequisite relationships as a causal structure, rather than bidirectional relationships. By pruning exercise relation graphs into Directed Acyclic Graphs (DAGs) and training DKT on causal subsets of the Assistments dataset, we show that DKT's predictive capabilities align strongly with these causal structures. Furthermore, we propose an alternative method for extracting exercise relation DAGs using DKT's learned representations and provide empirical evidence supporting our claim. Our findings suggest that DKT's effectiveness is largely driven by its capacity to approximate causal dependencies between KCs rather than simple relational mappings.
format Preprint
id arxiv_https___arxiv_org_abs_2511_03948
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Extracting Causal Relations in Deep Knowledge Tracing
Hong, Kevin
Karbasi, Kia
Pottie, Gregory
Artificial Intelligence
Human-Computer Interaction
I.2.6; K.3.1
A longstanding goal in computational educational research is to develop explainable knowledge tracing (KT) models. Deep Knowledge Tracing (DKT), which leverages a Recurrent Neural Network (RNN) to predict student knowledge and performance on exercises, has been proposed as a major advancement over traditional KT methods. Several studies suggest that its performance gains stem from its ability to model bidirectional relationships between different knowledge components (KCs) within a course, enabling the inference of a student's understanding of one KC from their performance on others. In this paper, we challenge this prevailing explanation and demonstrate that DKT's strength lies in its implicit ability to model prerequisite relationships as a causal structure, rather than bidirectional relationships. By pruning exercise relation graphs into Directed Acyclic Graphs (DAGs) and training DKT on causal subsets of the Assistments dataset, we show that DKT's predictive capabilities align strongly with these causal structures. Furthermore, we propose an alternative method for extracting exercise relation DAGs using DKT's learned representations and provide empirical evidence supporting our claim. Our findings suggest that DKT's effectiveness is largely driven by its capacity to approximate causal dependencies between KCs rather than simple relational mappings.
title Extracting Causal Relations in Deep Knowledge Tracing
topic Artificial Intelligence
Human-Computer Interaction
I.2.6; K.3.1
url https://arxiv.org/abs/2511.03948