Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

LLM-Assisted Knowledge Graph Completion for Curriculum and Domain Modelling in Personalized Higher Education Recommendations

Hasan Abu-Rasheed, Constance Jumbo, Rashed Al Amin, Christian Weber, Veit Wiese, Roman Obermaisser, Madjid Fathi

TL;DR

This work tackles the challenge of personalizing higher education by requiring interoperable representations of curricula, domain knowledge, and student contexts within a knowledge-graph framework. It introduces a four-step, LLM-assisted pipeline for ontology-driven KG construction, including ontology definition, automatic content extraction, human validation, and KG building, demonstrated on two embedded-systems modules. Expert feedback and graph-structure metrics show improved cross-course connectivity and potential for personalized recommendations, validating the collaboration between domain experts and AI. The approach lays a practical foundation for interoperable curriculum-domain-user representations across institutions and supports retrieval-augmented prompting to further enhance content extraction and recommendation quality.

Abstract

While learning personalization offers great potential for learners, modern practices in higher education require a deeper consideration of domain models and learning contexts, to develop effective personalization algorithms. This paper introduces an innovative approach to higher education curriculum modelling that utilizes large language models (LLMs) for knowledge graph (KG) completion, with the goal of creating personalized learning-path recommendations. Our research focuses on modelling university subjects and linking their topics to corresponding domain models, enabling the integration of learning modules from different faculties and institutions in the student's learning path. Central to our approach is a collaborative process, where LLMs assist human experts in extracting high-quality, fine-grained topics from lecture materials. We develop a domain, curriculum, and user models for university modules and stakeholders. We implement this model to create the KG from two study modules: Embedded Systems and Development of Embedded Systems Using FPGA. The resulting KG structures the curriculum and links it to the domain models. We evaluate our approach through qualitative expert feedback and quantitative graph quality metrics. Domain experts validated the relevance and accuracy of the model, while the graph quality metrics measured the structural properties of our KG. Our results show that the LLM-assisted graph completion approach enhances the ability to connect related courses across disciplines to personalize the learning experience. Expert feedback also showed high acceptance of the proposed collaborative approach for concept extraction and classification.

LLM-Assisted Knowledge Graph Completion for Curriculum and Domain Modelling in Personalized Higher Education Recommendations

TL;DR

This work tackles the challenge of personalizing higher education by requiring interoperable representations of curricula, domain knowledge, and student contexts within a knowledge-graph framework. It introduces a four-step, LLM-assisted pipeline for ontology-driven KG construction, including ontology definition, automatic content extraction, human validation, and KG building, demonstrated on two embedded-systems modules. Expert feedback and graph-structure metrics show improved cross-course connectivity and potential for personalized recommendations, validating the collaboration between domain experts and AI. The approach lays a practical foundation for interoperable curriculum-domain-user representations across institutions and supports retrieval-augmented prompting to further enhance content extraction and recommendation quality.

Abstract

While learning personalization offers great potential for learners, modern practices in higher education require a deeper consideration of domain models and learning contexts, to develop effective personalization algorithms. This paper introduces an innovative approach to higher education curriculum modelling that utilizes large language models (LLMs) for knowledge graph (KG) completion, with the goal of creating personalized learning-path recommendations. Our research focuses on modelling university subjects and linking their topics to corresponding domain models, enabling the integration of learning modules from different faculties and institutions in the student's learning path. Central to our approach is a collaborative process, where LLMs assist human experts in extracting high-quality, fine-grained topics from lecture materials. We develop a domain, curriculum, and user models for university modules and stakeholders. We implement this model to create the KG from two study modules: Embedded Systems and Development of Embedded Systems Using FPGA. The resulting KG structures the curriculum and links it to the domain models. We evaluate our approach through qualitative expert feedback and quantitative graph quality metrics. Domain experts validated the relevance and accuracy of the model, while the graph quality metrics measured the structural properties of our KG. Our results show that the LLM-assisted graph completion approach enhances the ability to connect related courses across disciplines to personalize the learning experience. Expert feedback also showed high acceptance of the proposed collaborative approach for concept extraction and classification.
Paper Structure (14 sections, 3 figures, 1 table)

This paper contains 14 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background
  3. LLMs Support in Creating KGs
  4. LLM-Enhanced KG Creation for Higher Education
  5. A Comprehensive Ontology for Higher Education
  6. Methodology
  7. Defining a Higher Education Ontology
  8. Automatic Content Extraction and Classification
  9. Human Validation of the Automated Extraction
  10. Knowledge Graph Construction
  11. Evaluation and Results
  12. Expert Evaluation of the Ontology and Pipeline
  13. KG-Structural Evaluation
  14. Conclusion

Figures (3)

  • Figure 1: Proposed ontological structure of the knowledge graph, with domain, curriculum, and user models.
  • Figure 2: Pipeline components for the transcription, extraction, classification, and KG construction, based on a human-AI collaborative approach.
  • Figure 3: The structure of the KG before (left) and after (right) connecting both evaluation modules through semantic Topic and Sub-Topic relations.