Inferring Prerequisite Knowledge Concepts in Educational Knowledge Graphs: A Multi-criteria Approach

2025-09-05

AI Summary

To address the absence of explicit prerequisite relationships (PRs) in the Educational Knowledge Graph (EduKG) of the MOOC platform CourseMapper, this paper proposes an unsupervised, multi-criteria method for automatic inference of prerequisite concept relations. The approach requires no human annotation and integrates ten heterogeneous criteria—including document co-occurrence, Wikipedia hyperlinks, graph structural proximity, and semantic similarity—within a weighted voting framework to ensure robust inference. Its key innovation lies in the first unified modeling of diverse weak supervision signals under a fully unsupervised paradigm, with built-in support for cross-domain transfer. Experiments on benchmark datasets demonstrate that our method achieves significantly higher precision than current state-of-the-art approaches, while exhibiting strong scalability and platform adaptability. This work provides reliable, knowledge-driven sequentialization of concepts, thereby enabling effective adaptive learning path planning.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Data Mining & Knowledge Management: Knowledge Acquisition from the Web
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Educational Knowledge Graphs (EduKGs) organize various learning entities and their relationships to support structured and adaptive learning. Prerequisite relationships (PRs) are critical in EduKGs for defining the logical order in which concepts should be learned. However, the current EduKG in the MOOC platform CourseMapper lacks explicit PR links, and manually annotating them is time-consuming and inconsistent. To address this, we propose an unsupervised method for automatically inferring concept PRs without relying on labeled data. We define ten criteria based on document-based, Wikipedia hyperlink-based, graph-based, and text-based features, and combine them using a voting algorithm to robustly capture PRs in educational content. Experiments on benchmark datasets show that our approach achieves higher precision than existing methods while maintaining scalability and adaptability, thus providing reliable support for sequence-aware learning in CourseMapper.

Problem

• Infer prerequisite relationships in educational knowledge graphs
• Automate annotation without labeled data using unsupervised method
• Combine multiple criteria to robustly capture concept dependencies

Innovation

• Unsupervised method for inferring prerequisite relationships
• Combines ten criteria using a voting algorithm
• Achieves higher precision while maintaining scalability