Research on Personalized Course Resource Recommendation Method Based on GEMRec

With the rapid growth of online educational resources, existing personalized course recommendation systems face challenges in multimodal feature integration and limited recommendation interpretability when dealing with complex and diverse instructional content. This paper proposes a graph-enhanced m...

Full description

Saved in:
Bibliographic Details
Main Authors: Enliang Wang, Zhixin Sun
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/3/1075
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849717778441830400
author Enliang Wang
Zhixin Sun
author_facet Enliang Wang
Zhixin Sun
author_sort Enliang Wang
collection DOAJ
description With the rapid growth of online educational resources, existing personalized course recommendation systems face challenges in multimodal feature integration and limited recommendation interpretability when dealing with complex and diverse instructional content. This paper proposes a graph-enhanced multimodal recommendation method (GEMRec), which effectively integrates text, video, and audio features through a graph attention network and differentiable pooling. Innovatively, GEMRec introduces graph edit distance into the recommendation system to measure the structural similarity between a learner’s knowledge state and course content at the knowledge graph level. Additionally, it combines SHAP (SHapley Additive exPlanations) value computation with large language models to generate reliable and personalized recommendation explanations. Experiments on the MOOCCubeX dataset demonstrate that the GEMRec model exhibits strong convergence and generalization during training. Compared with existing methods, GEMRec achieves 0.267, 0.265, and 0.297 on the Precision@10, Recall@10, and NDCG@10 metrics, respectively, significantly outperforming traditional collaborative filtering and other deep learning models. These results validate the effectiveness of multimodal feature integration and knowledge graph enhancement in improving recommendation performance.
format Article
id doaj-art-7f583a70d697473c883a2ebcf30cead6
institution DOAJ
issn 2076-3417
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-7f583a70d697473c883a2ebcf30cead62025-08-20T03:12:34ZengMDPI AGApplied Sciences2076-34172025-01-01153107510.3390/app15031075Research on Personalized Course Resource Recommendation Method Based on GEMRecEnliang Wang0Zhixin Sun1Post Big Data Technology and Application Engineering Research Center of Jiangsu Province, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaPost Big Data Technology and Application Engineering Research Center of Jiangsu Province, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaWith the rapid growth of online educational resources, existing personalized course recommendation systems face challenges in multimodal feature integration and limited recommendation interpretability when dealing with complex and diverse instructional content. This paper proposes a graph-enhanced multimodal recommendation method (GEMRec), which effectively integrates text, video, and audio features through a graph attention network and differentiable pooling. Innovatively, GEMRec introduces graph edit distance into the recommendation system to measure the structural similarity between a learner’s knowledge state and course content at the knowledge graph level. Additionally, it combines SHAP (SHapley Additive exPlanations) value computation with large language models to generate reliable and personalized recommendation explanations. Experiments on the MOOCCubeX dataset demonstrate that the GEMRec model exhibits strong convergence and generalization during training. Compared with existing methods, GEMRec achieves 0.267, 0.265, and 0.297 on the Precision@10, Recall@10, and NDCG@10 metrics, respectively, significantly outperforming traditional collaborative filtering and other deep learning models. These results validate the effectiveness of multimodal feature integration and knowledge graph enhancement in improving recommendation performance.https://www.mdpi.com/2076-3417/15/3/1075multimodal deep learningknowledge graphpersonalized course recommendationgraph neural networkinterpretability
spellingShingle Enliang Wang
Zhixin Sun
Research on Personalized Course Resource Recommendation Method Based on GEMRec
Applied Sciences
multimodal deep learning
knowledge graph
personalized course recommendation
graph neural network
interpretability
title Research on Personalized Course Resource Recommendation Method Based on GEMRec
title_full Research on Personalized Course Resource Recommendation Method Based on GEMRec
title_fullStr Research on Personalized Course Resource Recommendation Method Based on GEMRec
title_full_unstemmed Research on Personalized Course Resource Recommendation Method Based on GEMRec
title_short Research on Personalized Course Resource Recommendation Method Based on GEMRec
title_sort research on personalized course resource recommendation method based on gemrec
topic multimodal deep learning
knowledge graph
personalized course recommendation
graph neural network
interpretability
url https://www.mdpi.com/2076-3417/15/3/1075
work_keys_str_mv AT enliangwang researchonpersonalizedcourseresourcerecommendationmethodbasedongemrec
AT zhixinsun researchonpersonalizedcourseresourcerecommendationmethodbasedongemrec