Knowledge graph convolutional networks with user preferences for course recommendation

Abstract With the rapid growth of the internet and online education resources, the number of massive open online courses (MOOCs) has increased dramatically, making it difficult for users to find personalized courses that meet their needs. Knowledge graphs (KGs) have been employed in recommendation s...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhong Hua, Jianbai Yang, Weidong Ji
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-14150-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226304708149248
author Zhong Hua
Jianbai Yang
Weidong Ji
author_facet Zhong Hua
Jianbai Yang
Weidong Ji
author_sort Zhong Hua
collection DOAJ
description Abstract With the rapid growth of the internet and online education resources, the number of massive open online courses (MOOCs) has increased dramatically, making it difficult for users to find personalized courses that meet their needs. Knowledge graphs (KGs) have been employed in recommendation systems to effectively address the issue of sparse interaction data in the MOOC scenarios for their rich semantic information. Research on KG-enhanced recommendation algorithms has found that the utilization of side information in KGs is crucial for improving accuracy. This paper introduces KGCN-UP (Knowledge Graph Convolutional Networks with User Preferences), a novel model for predicting the likelihood of a user interacting with a course based on user preferences and item relationships within a knowledge graph. The KGCN-UP model consists of two key modules. First, the user preference propagation module refines user preferences by exploring relational chains in the knowledge graph and dynamically adjusting attention to improve user representation. Second, the item neighbor enhancement module enhances item representations by aggregating semantic relationships and assigning attention weights based on the type of relationship between entities. Together, these components address the challenge of data sparsity and improve the quality of recommendations by leveraging high-order structural and semantic information. Empirical results on a real-world dataset demonstrate that KGCN-UP significantly outperforms existing state-of-the-art recommendation models in terms of accuracy.
format Article
id doaj-art-c32104f585c54a0993e81657e7e96283
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-c32104f585c54a0993e81657e7e962832025-08-24T11:30:19ZengNature PortfolioScientific Reports2045-23222025-08-0115111510.1038/s41598-025-14150-5Knowledge graph convolutional networks with user preferences for course recommendationZhong Hua0Jianbai Yang1Weidong Ji2College of Computer Science and Information Engineering, Harbin Normal UniversityCollege of Computer Science and Information Engineering, Harbin Normal UniversityCollege of Computer Science and Information Engineering, Harbin Normal UniversityAbstract With the rapid growth of the internet and online education resources, the number of massive open online courses (MOOCs) has increased dramatically, making it difficult for users to find personalized courses that meet their needs. Knowledge graphs (KGs) have been employed in recommendation systems to effectively address the issue of sparse interaction data in the MOOC scenarios for their rich semantic information. Research on KG-enhanced recommendation algorithms has found that the utilization of side information in KGs is crucial for improving accuracy. This paper introduces KGCN-UP (Knowledge Graph Convolutional Networks with User Preferences), a novel model for predicting the likelihood of a user interacting with a course based on user preferences and item relationships within a knowledge graph. The KGCN-UP model consists of two key modules. First, the user preference propagation module refines user preferences by exploring relational chains in the knowledge graph and dynamically adjusting attention to improve user representation. Second, the item neighbor enhancement module enhances item representations by aggregating semantic relationships and assigning attention weights based on the type of relationship between entities. Together, these components address the challenge of data sparsity and improve the quality of recommendations by leveraging high-order structural and semantic information. Empirical results on a real-world dataset demonstrate that KGCN-UP significantly outperforms existing state-of-the-art recommendation models in terms of accuracy.https://doi.org/10.1038/s41598-025-14150-5Personalized recommendationKnowledge GraphGraph Convolution Networks.
spellingShingle Zhong Hua
Jianbai Yang
Weidong Ji
Knowledge graph convolutional networks with user preferences for course recommendation
Scientific Reports
Personalized recommendation
Knowledge Graph
Graph Convolution Networks.
title Knowledge graph convolutional networks with user preferences for course recommendation
title_full Knowledge graph convolutional networks with user preferences for course recommendation
title_fullStr Knowledge graph convolutional networks with user preferences for course recommendation
title_full_unstemmed Knowledge graph convolutional networks with user preferences for course recommendation
title_short Knowledge graph convolutional networks with user preferences for course recommendation
title_sort knowledge graph convolutional networks with user preferences for course recommendation
topic Personalized recommendation
Knowledge Graph
Graph Convolution Networks.
url https://doi.org/10.1038/s41598-025-14150-5
work_keys_str_mv AT zhonghua knowledgegraphconvolutionalnetworkswithuserpreferencesforcourserecommendation
AT jianbaiyang knowledgegraphconvolutionalnetworkswithuserpreferencesforcourserecommendation
AT weidongji knowledgegraphconvolutionalnetworkswithuserpreferencesforcourserecommendation