Sequential Learner Modeling Using Multi-Relational Graph Convolutional Networks

2026-07-21

AI Summary

This work addresses the limitations of existing graph neural networks in learner modeling, which often overlook relational heterogeneity and temporal interactions, thereby failing to construct semantically rich and temporally aware user representations. To overcome this, the authors propose MR-ConceptGCN, a novel approach that introduces multi-relational graph convolutional networks (MR-GCN) into learner modeling for the first time. By integrating personal knowledge graphs (PKG), SBERT-enhanced concept semantic embeddings, and interaction sequences, MR-ConceptGCN constructs an unsupervised, concept-level sequential learner model that achieves dual awareness of both relational structure and semantic meaning for personalized representation. An online user study (n=31) demonstrates that the proposed method significantly outperforms baseline approaches in terms of recommendation accuracy, usefulness, diversity, and user satisfaction.

Abstract

User modeling is a critical task in a variety of personalized systems. Recognizing their effectiveness in learning from graph-structured data, Graph Neural Networks (GNNs), particularly Graph Convolutional Networks (GCNs), are increasingly employed for user modeling. However, existing approaches typically treat different relation types in a graph as homogeneous, limiting their ability to capture richer semantics and construct more informative user models. While multi-relational GNNs (MR-GNNs) have been adopted for representation learning and recommendation, their application for user modeling remains unexplored. Moreover, existing GNN-based user modeling approaches ignore the user interaction sequence. To address these research gaps, in this work we propose MR-ConceptGCN, a novel fully unsupervised approach focused on concept-based sequential learner modeling using multi-relational GCNs (MR-GCNs). MR-ConceptGCN effecively combines Personal Knowledge Graphs (PKGs), MR-GCNs, and the pre-trained language model SBERT to obtain enhanced relation- and semantic-aware representations of the PKG items. The enriched embeddings of the knowledge concepts that a learner did not understand when interacting with learning materials in CourseMapper are then used to construct a sequential learner model that combines long-term and short-term learner interactions. We report the results of an online user study (n = 31), demonstrating the benefits of MR-ConceptGCN in terms of several important user-centric aspects including accuracy, usefulness, diversity, and satisfaction with an educational recommender system.

Problem

• user modeling
• multi-relational graphs
• sequential interactions
• graph neural networks
• personalized learning

Innovation

• Multi-Relational GCN
• Sequential Learner Modeling
• Personal Knowledge Graph
• SBERT
• Unsupervised User Modeling