Peer-inspired Student Performance Prediction in Interactive Online Question Pools with Graph Neural Network

TL;DR

This paper introduces a novel GNN-based method called R^2GCN for predicting student performance in interactive online question pools, outperforming traditional models on real-world data.

Contribution

The paper proposes a new GNN model tailored for heterogeneous student-question interaction networks to improve performance prediction in online education.

Findings

R^2GCN achieves higher accuracy than traditional methods.

The approach effectively models knowledge evolution in interactive question pools.

Experimental results on real-world data validate the model's effectiveness.

Abstract

Student performance prediction is critical to online education. It can benefit many downstream tasks on online learning platforms, such as estimating dropout rates, facilitating strategic intervention, and enabling adaptive online learning. Interactive online question pools provide students with interesting interactive questions to practice their knowledge in online education. However, little research has been done on student performance prediction in interactive online question pools. Existing work on student performance prediction targets at online learning platforms with predefined course curriculum and accurate knowledge labels like MOOC platforms, but they are not able to fully model knowledge evolution of students in interactive online question pools. In this paper, we propose a novel approach using Graph Neural Networks (GNNs) to achieve better student performance prediction in interactive online question pools. Specifically, we model the relationship between students and questions using student interactions to construct the student-interaction-question network and further present a new GNN model, called R^2GCN, which intrinsically works for the heterogeneous networks, to achieve generalizable student performance prediction in interactive online question pools. We evaluate the effectiveness of our approach on a real-world dataset consisting of 104,113 mouse trajectories generated in the problem-solving process of over 4000 students on 1631 questions. The experiment results show that our approach can achieve a much higher accuracy of student performance prediction than both traditional machine learning approaches and GNN models.