Recommendation Model for Learning Materials Using Graph Neural Networks Based on Conceptual Relationships and Difficulty Level of the Materials

Faisal Faisal

doi:10.31004/riggs.v4i3.3247

Authors

Faisal Faisal Universitas Pejuang Republik Indonesia

DOI:

https://doi.org/10.31004/riggs.v4i3.3247

Keywords:

Recommendation System, Graph Neural Network (GNN), E-learning, Collaborative Filtering, Content-based Filtering, Precision@K, Recall@K, NDCG@K

Abstract

The recommendation system in online learning plays a crucial role in supporting personalized and adaptive learning. However, traditional approaches often overlook the relationships between material concepts and the difficulty level of the learning content. This study proposes a recommendation model based on Graph Neural Networks (GNN), utilizing a graph representation of learning materials with difficulty level attributes. A dummy dataset with 100 materials and 200 conceptual relationships was used for testing. The evaluation results show that the proposed GNN model achieves a Precision@3 of 0.01, Recall@3 of 0.375, and NDCG@3 of 0.01, which are higher than baseline methods such as collaborative filtering and content-based filtering. This indicates that GNN can enhance the relevance of learning material recommendations. Future research will focus on using real-world datasets and exploring heterogeneous GNN models to improve recommendation performance. This model also contributes to designing a recommendation system that can adjust to the abilities and needs of learners. Future research is expected to test this model with larger and real datasets and explore the application of GNN models on heterogeneous data to examine the potential for improving recommendation performance. By considering the difficulty level of materials, this model has the potential to improve the learning experience, making it more relevant and adaptive for users.

Downloads

Download data is not yet available.

References

S. Zhang & Chen, X., “Graph-based collaborative filtering for recommendation: A review and perspective,” J. Intell. Fuzzy Syst., vol. 41, no. 5, pp. 6191–6203, 2021, doi: 10.3233/JIFS-189047.

X. Sun & Zhang, L., “Incorporating graph neural networks into collaborative filtering for personalized recommendations,” Knowledge-Based Syst., vol. 212, p. 106590, 2021, doi: 10.1016/j.knosys.2020.106590.

L. Yao & Zhang, W., “Learning graph-based representations for recommendation systems: A survey,” ACM Comput. Surv., vol. 55, no. 1, pp. 1–35, 2022, doi: 10.1145/3458800.

L. Wang & Li, Y., “Graph convolutional networks for recommender systems: A case study in e-commerce,” Inf. Sci. (Ny)., vol. 545, pp. 390–406, 2021, doi: 10.1016/j.ins.2020.11.053.

X. Zhang & Zhou, Y., “Personalized recommendation with graph neural networks and content-based filtering,” Comput. Intell. Neurosci., vol. 2023, p. 182834, 2023, doi: 10.1155/2023/182834.

H. Li Zhang, C., & Wang, X., “Graph neural networks for personalized recommendation: A review,” IEEE Trans. Neural Networks Learn. Syst., vol. 33, no. 9, pp. 4537–4551, 2022, doi: 10.1109/TNNLS.2021.3082691.

H. Kim & Han, M., “Graph neural networks for recommendation systems: A tutorial and survey,” J. Mach. Learn. Res., vol. 23, no. 1, pp. 76–105, 2022, doi: 10.1109/JMLR.2021.9071771.

Z. Zhang & Liu, M., “Multi-level graph convolutional networks for recommendation systems,” Inf. Sci. (Ny)., vol. 555, pp. 308–324, 2021, doi: 10.1016/j.ins.2021.03.062.

X. Zhou & Liu, Z., “A survey on graph neural networks for recommender systems,” J. Comput. Sci. Technol., vol. 36, no. 3, pp. 415–439, 2021, doi: 10.1007/s11390-021-1089-3.

Y. Li & Liu, P., “Hybrid graph convolutional networks for recommender systems: A novel approach,” Neural Networks, vol. 148, pp. 214–226, 2022, doi: 10.1016/j.neunet.2022.05.013.

H. Lu & Huang, Q., “A deep learning approach for graph-based recommendation systems: Architecture and applications,” J. Mach. Learn. Comput., vol. 11, no. 4, pp. 356–370, 2021, doi: 10.18178/jmlc.2021.11.4.790.

Y. Tang & Lu, Z., “A review on graph neural networks for recommender systems: Challenges, advances, and future directions,” Computers, vol. 11, no. 1, pp. 4–29, 2022, doi: 10.3390/computers11010004.

S. Wang & Xu, Y., “A novel graph-based model for enhancing recommendation systems,” IEEE Access, vol. 9, pp. 417–431, 2021, doi: 10.1109/ACCESS.2020.3030198.

Z. Wu & Zhang, J., “Efficient recommendation via graph convolutional networks: A case study in e-learning platforms,” Expert Syst. Appl., vol. 186, p. 115764, 2022, doi: 10.1016/j.eswa.2021.115764.

X. Zhang & Liu, M., “Enhancing recommendation performance using Graph Neural Networks,” Int. J. Comput. Appl., vol. 175, no. 3, pp. 1–7, 2021, doi: 10.5120/ijca2021922367.

Y. Wang & Zhang, J., “A graph neural network approach to enhance the performance of recommender systems,” Inf. Process. Manag., vol. 60, no. 4, p. 102748, 2023, doi: 10.1016/j.ipm.2023.102748.

C. Lin & Chen, Y., “Personalized recommendation using graph convolutional networks: A systematic review,” Futur. Gener. Comput. Syst., vol. 139, pp. 1245–1260, 2023, doi: 10.1016/j.future.2023.02.007.