Research on The Learning Path of Database Courses Based on Question-oriented Knowledge Graph

Pengfei Song; Xinan Yue

doi:10.6918/IJOSSER.202605_9(5).0005

Authors

Pengfei Song
Xinan Yue

DOI:

https://doi.org/10.6918/IJOSSER.202605_9(5).0005

Keywords:

Knowledge graph, Database course, Learning path recommendation, Problem-oriented learning, Personalized learning.

Abstract

With the rapid development of information technology, database technology has become a central foundational discipline in the field of computer science and technology. However, traditional teaching methods for database courses often follow a linear, fixed knowledge delivery approach, which hardly meets the individual learning needs of students and fails to effectively bridge the gap between theoretical knowledge and the ability to solve practical problems. To address these challenges, this article presents a model for recommending learning paths for database courses based on a problem-knowledge graph (Problem-Knowledge Graph based Learning Path, P-KGLP). First, a Database Problem-Knowledge Graph (DB-PKG) is created by conducting in-depth analysis of textbooks, online courses (MOOCs), technical forums, and project examples in the field of database courses, integrating the three-part relationship of "knowledge point – problem – resource." This graph not only reveals logical dependencies between knowledge points but primarily establishes a mapping between knowledge content and real-world problems. Based on this, a personalized algorithm for generating learning paths is developed, which takes into account the current knowledge level and interests of students. The algorithm employs graph traversal techniques and dynamically plans a problem-oriented learning sequence that both deepens weak knowledge areas and enhances student motivation, while adhering to the prerequisites of the knowledge points. To verify the effectiveness of the model, experiments were conducted using publicly available MOOC datasets (such as MOOCCube). The results show that the proposed P-KGLP model significantly outperforms classical methods like the collaborative filtering algorithm (BPR), knowledge graph embedding-based recommendation approaches (TransE), and modern graph neural network models (LightGCN) in key metrics such as recommendation accuracy (Hits@10) and normalized discounted cumulative gain (NDCG@10). This study thus provides a new and effective approach for intelligent, personalized, and problem-based teaching in database courses.

Downloads

Download data is not yet available.

References

[1] Teaching Guidance Committee for Computer Specialties in Colleges and Universities, Ministry of Education. National Standards for Teaching Quality of Computer Specialties in Colleges and Universities [M]. Beijing: Tsinghua University Press, 2018.

[2] Li Xiaoming. MOOCs and the Teaching Reform of Core Courses in Computer Science [J]. Teaching in Chinese Universities, 2014 (5): 7-11. DOI: 10.16298/j.cnki.1005-0450.2014.05.002.

[3] BARROWS H S. Problem-based learning in medicine and beyond: A brief overview [J]. New Directions for Teaching and Learning, 1996, 1996 (68): 3-12. DOI:10.1002/tl.37219966803.

[4] Liu Zhiyuan, Han Xu, Sun Maosong. Overview and Future Prospects of Educational Knowledge Graph Research [J]. Science China: Information Sciences, 2022, 52(2): 205-246. DOI: 10.1360/SSI-2020-0337

[5] Wu Linjing, Huang Jingxiu, Liu Qingtang, et al. Construction of Knowledge Graph and Learning Path Recommendation for Data Structure Courses [J]. China Educational Technology, 2020 (3): 89-97. DOI: 10.13541/j.cnki.chinade.2020.03.012

[6] Zhang Jinbao, Zhang Sheng, Wang Jijun. Research Status and Trends of Personalized Learning Path Recommendation Based on Knowledge Graphs [J]. Journal of Educational Technology Research, 2021, 42(8): 77-85. DOI: 10.13811/j.cnki.eer.2021.08.010

[7] SHI D, WANG T, XING H, et al. A survey of knowledge graph-based adaptive learning systems for personalized recommendation [J]. IEEE Access, 2020, 8: 200454-200476. DOI:10.1109/ACCESS.2020.3035540.

[8] Silberschatz, Kress, Sudalshan. Database System Concepts (7th Edition)[M]. Translated by Yang Dongqing, Li Hongyan, Zhang Jinbo, et al. Beijing: China Machine Press, 2020

[9] Wang Haofen, Qi Guilin, Chen Huajun. Knowledge Graph: Methods, Practice, and Applications [M]. Beijing: Publishing House of Electronics Industry, 2019

[10] DEVLIN J, CHANG M W, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding [C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Minneapolis: Association for Computational Linguistics, 2019: 4171-4186. DOI:10.18653/v1/N19-1423.

[11] VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph attention networks [C]//International Conference on Learning Representations. Vancouver: OpenReview, 2018.

[12] PAGE L, BRIN S, MOTWANI R, et al. The pagerank citation ranking: Bringing order to the web [R]. Stanford: Stanford InfoLab, 1999.

[13] BORDES A, USUNIER N, GARCIA-DURAN A, et al. Translating embeddings for modeling multi-relational data [C]//Advances in Neural Information Processing Systems 26. Lake Tahoe: Curran Associates, 2013: 2787-2795.

[14] YU J, YIN Y, LIU H, et al. MOOCCube: A large-scale data repository for NLP applications in MOOCs [C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop. Online: Association for Computational Linguistics, 2020: 169-175. DOI:10.18653/v1/2020.acl-srw.23.

[15] RICCI F, ROKACH L, SHAPIRA B. Introduction to recommender systems handbook [M]. 2nd ed. Boston: Springer, 2011: 1-35. DOI:10.1007/978-0-387-85820-3_1.

[16] RENDLE S, FREUDENTHALER C, GANTNER Z, et al. BPR: Bayesian personalized ranking from implicit feedback [C]//Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence. Montreal: AUAI Press, 2009: 452-461.

[17] HE X, DENG K, WANG X, et al. LightGCN: Simplifying and powering graph convolution network for recommendation [C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Virtual Event: ACM, 2020: 639-648. DOI:10.1145/3397271.3401063.