Graph-based knowledge tracing: Modeling student proficiency using graph neural networks

By Hiromi Nakagawa, Yusuke Iwasawa, Yutaka Matsuo. International Conference on Wirtschaftsinformatik, 2019

476 citations recorded by the source corpus.

Recent advancements in computer-assisted learning systems have caused an increase in the research in knowledge tracing, wherein student performance is predicted over time. Student coursework can potentially be structured as a graph. Incorporating this graph-structured nature into a knowledge tracing model as a relational inductive bias can improve its performance; however, previous methods, such as deep knowledge tracing, did not consider such a latent graph structure. Inspired by the recent successes of graph neural networks (GNNs), we herein propose a GNN-based knowledge tracing method, i.e., graph-based knowledge tracing. Casting the knowledge structure as a graph enabled us to reformulate the knowledge tracing task as a time-series node-level classification problem in the GNN. As the knowledge graph structure is not explicitly provided in most cases, we propose various implementations of the graph structure. Empirical validations on two open datasets indicated that our method could potentially improve the prediction of student performance and demonstrated more interpretable predictions compared to those of the previous methods, without the requirement of any additional information.

Subfields: Artificial Intelligence, Computer Science Applications

View Paper: https://www.semanticscholar.org/paper/323f421c8511716806bb02ac006ddd8837a8e22c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Heng Ji
2. Jiawei Han
3. Meng Jiang
4. Bernardo Pereira Nunes
5. Bowen Jin
6. Chi Han
7. Qing Wang
8. Gang Liu

In Computer Science Applications

1. Jiawei Han
2. Bernardo Pereira Nunes
3. Qing Wang
4. Ghodai M. Abdelrahman

Citations in the corpus

• Large Language Models on Graphs: A Comprehensive Survey (2023, background): “The model learned on such a graph can be utilized for knowledge tracing [136] and student performance prediction [137].”
• Knowledge Tracing: A Survey (2022, methodology): “BKT [25] DBN [55] HMM/BN DBN ✓ ✓ Binary scalar Binary vector × × IRT [41] HIRT [125] TIRT [125] LFA [16] AFM [17] PFA [89] KTM [119] KTM-DLF [35] LR LR LR LR LR LR FM FM ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ Real-valued vector Real-valued vector Real-valued vector Real-valued vector Real-valued vector Real-valued vector ”