A Course Recommendation Method Based on the Integration of Curriculum Knowledge Graph and Collaborative Filtering

Hu, Jingyi; Wang, Qingqing

doi:10.2478/ijanmc-2025-0020

Abstract

To address the problems of data sparsity and cold start in collaborative filtering algorithms, this paper proposes an improved course recommendation method that integrates knowledge graphs and collaborative filtering. First, the RippleNet model is used to construct a knowledge graph based on course-attribute-relation triples and generate a recommendation list. Then, an item-based collaborative filtering algorithm utilizes users’ historical interaction behavior to produce another recommendation list. Finally, a weighted linear method is employed to fuse the recommendation list generated by the RippleNet-based course knowledge graph and the one generated by collaborative filtering, resulting in the final course recommendation list. Experiments conducted on the public dataset MOOCCube demonstrate that the RippleNet-CF method improves precision, recall, and F1-score, while also effectively mitigating the issue of data sparsity.

References

S. Wu, F. Sun, W. Zhang, et al., “Graph neural networks in recommender systems: a survey,” ACM Computing Surveys, vol. 55, no. 5, May 2022, pp. 1–37, doi:10.1145/3519724.
Open DOI Search in Google Scholar Back to article
S. Wang, L. Cao, Y. Wang, et al., “A survey on session-based recommender systems,” ACM Computing Surveys (CSUR), vol. 54, no. 7, Aug. 2021, pp. 1–38, doi:10.1145/3460951.
Open DOI Search in Google Scholar Back to article
J. Li, Z. Ye, “Course recommendations in online education based on collaborative filtering recommendation algorithm,” Complexity, vol. 2020, Apr. 2020, Article ID 8813370, doi:10.1155/2020/8813370.
Open DOI Search in Google Scholar Back to article
P. K. Singh, R. Ahmed, I. S. Rajput, et al., “A comparative study on prediction approaches of itembased collaborative filtering in neighborhood-based recommendations,” Wireless Personal Communications, vol. 121, no. 6, Nov. 2021, pp. 857–877, doi:10.1007/s11265-021-01696-1.
Open DOI Search in Google Scholar Back to article
G. Piao, J. G. Breslin, “A study of the similarities of entity embeddings learned from different aspects of a knowledge base for item recommendations,” in Proceedings of the European Semantic Web Conference (ESWC 2018), Springer, Cham, June 2018, pp. 345– 359, doi:10.1007/978-3-319-93417-4_21.
Open DOI Search in Google Scholar Back to article
M. J. Pazani, D. Billsus, “Content-based recommendation systems,” in The Adaptive Web: Methods and Strategies of Web Personalization, Springer, Berlin, Heidelberg, May 2007, pp. 325–341, doi:10.1007/978-3-540-72079-9_10.
Open DOI Search in Google Scholar Back to article
H. Wang, F. Zhang, J. Wang, et al., “Ripplenet: Propagating user preferences on the knowledge graph for recommender systems,” in Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM 2018), ACM Press, Oct. 2018, pp. 417–426, doi:10.1145/3269206.3271764.
Open DOI Search in Google Scholar Back to article
W. Jiang, Y. Sun, “Social-RippleNet: Jointly modeling of ripple net and social information for recommendation,” Applied Intelligence, vol. 53, no. 3, Mar. 2023, pp. 3472–3487, doi:10.1007/s10489-021-03214-7.
Open DOI Search in Google Scholar Back to article
Y. Q. Wang, L. Y. Dong, Y. L. Li, et al., “Multitask feature learning approach for knowledge graph enhanced recommendations with RippleNet,” Plos One, vol. 16, no. 5, May 2021, e0251162, doi:10.1371/journal. pone. 0251162.
Open DOI Search in Google Scholar Back to article
H. Wang, F. Zhang, X. Xie, et al., “DKN: Deep knowledge-aware network for news recommendation,” in Proceedings of the 2018 World Wide Web Conference (WWW 2018), ACM Press, Apr. 2018, pp. 1835–1844, doi:10.1145/3178876.3186143.
Open DOI Search in Google Scholar Back to article
H. Wang, F. Zhang, M. Hou, et al., “Shine: Signed heterogeneous information network embedding for sentiment like prediction,” in Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining (WSDM 2018), ACM Press, Feb. 2018, pp. 592–600, doi:10.1145/3159652.3159668.
Open DOI Search in Google Scholar Back to article
X. Yu, X. Ren, Y. Sun, et al., “Personalized entity recommendation: A heterogeneous information network approach,” in Proceedings of the 7th ACM International Conference on Web Search and Data Mining (WSDM 2014), ACM Press, Feb. 2014, pp. 283–292, doi:10.1145/2556195.2556222.
Open DOI Search in Google Scholar Back to article
Y. Cao, X. Wang, X. He, et al., “Unifying knowledge graph learning and recommendation: Towards a better understanding of user preferences,” in The World Wide Web Conference (WWW 2019), ACM Press, May 2019, pp. 151–161, doi:10.1145/3308558.3313433.
Open DOI Search in Google Scholar Back to article
F. M. Harper, J. A. Konstan, “The MovieLens Datasets: History and Context,” ACM Transactions on Interactive Intelligent Systems, vol. 5, no. 4, Dec. 2016, Article No. 19, doi:10.1145/2827872.
Open DOI Search in Google Scholar Back to article

A Course Recommendation Method Based on the Integration of Curriculum Knowledge Graph and Collaborative Filtering

Abstract

Paradigm

My account