Research on the Construction of a Personalized Learning Model Based on Data Mining Technology

DOI: https://doi.org/10.62517/jbdc.202501431

Author(s)

Wenjuan Shao, Xiaoxiao Gu, Kun Liu*

Affiliation(s)

College of Applied Science and Technology, Beijing Union University, Beijing, China *Corresponding Author

Abstract

Aiming at the limitation that the existing personalized learning system relies on a single model and static path planning, an integrated learning model based on data mining technology is proposed. The model constructs dynamic learner files and subject knowledge maps, designs a hybrid recommendation engine integrating content-based filtering, collaborative filtering and association rules, and innovatively combines knowledge maps with sequential pattern mining to generate personalized learning paths. The experimental results on OULAD data set show that the model is superior to the benchmark model in recommendation accuracy (0.45) and NDCG (0.59). In addition, it achieves a significantly higher completion rate of learning path (85%) and score improvement rate (23%), which verifies its effectiveness. This study provides an innovative solution to overcome the limitations of the current personalized learning system and has important reference value for promoting the intelligent development of personalized education services.

Keywords

Personalized Learning; Data Mining; Recommender Systems; Knowledge Graph

References

[1] Zhang, J (2023). Design of a Personalized Recommendation System for Online Learning Platforms Based on Data Mining. Software, 44(12), 44-46. [2] Wang, Y. J. (2023). Research on Personalized Learning Models Based on Data Mining Technology. Journal of Anhui Open University, (03), 92-96. [3] Wang, R. X. (2022). Research on the Design of Personalized Recommendation Systems for Online Learning Platforms. Computer Knowledge and Technology, 18(32), 41-43. [4] Esteban, A., Zafra, A., Ventura, S. (2020). A clustering-based approach to support educational decision-making with multiple criteria. Computers & Education, 152, 103880. [5] Ma, H. W., Zhang, G. W., Li, P. (2009). A survey of collaborative filtering recommendation algorithms. Mini-Micro Systems, 30(7), 1282–1288. [6] Liu, R., Zhao, W. (2023). A Survey of Knowledge Tracing on Structured Knowledge Graph. ACM Transactions on Intelligent Systems and Technology, 14(4), 1-27. [7] Liu, Q., Li, Y., Duan, H., et al. (2016). A survey on knowledge graph construction techniques. Journal of Computer Research and Development, 53(3), 582–600. [8] Liu, A., Gao, W. (2024). Research on incremental learner profile construction based on reconfigurable knowledge graph. Office Informatization, 29(14), 38-41. [9] Liang, Q., Wang, B, Zhang, Q. (2024). Research on teaching cognitive diagnosis model based on SOM neural network. Modern Educational Technology, 34(9), 59–70. [10] Wang, C. (2023). An improved constrained multidimensional Apriori algorithm. Application of Electronic Technique, 49(10), 100-105. [11] Xia, S. (2025). Research on multimodal representation and analysis path for human-computer collaborative learning ability. e-Education Research, 46(11), 54-61.