An Empirical Study on Knowledge Graph-Enhanced Adaptive Learning Path Recommendation for Higher Education Students

HUANG Yang, LIU Ping, YU Yan, MA Hai, GAO Shan

Abstract

With the in-depth advancement of the digital transformation of higher education in Guizhou Province, personalized learning has become an important direction to solve the problems of "one-size-fits-all" teaching and mismatched learning needs. Knowledge Graph (KG), as a structured knowledge representation method, has unique advantages in organizing disciplinary knowledge and optimizing adaptive learning paths. However, most existing studies focus on theoretical modeling and lack empirical verification in specific regional higher education scenarios. This study takes 2000 undergraduate students from 4 representative universities in Guizhou Province as research subjects, combines questionnaire surveys and semi-structured interviews, and adopts a quasi-experimental design to explore the effectiveness of KG-enhanced adaptive learning path recommendation. The results show that KG-enhanced adaptive learning paths can significantly improve students' academic performance, learning engagement and satisfaction, and reduce cognitive load. The core enhancement mechanisms include structured knowledge organization, cognitive adaptation, dynamic adjustment, and interpretability. This study provides empirical evidence for the application of KG in the digital transformation of higher education in Guizhou and enriches the theoretical system of intelligent education.

Keywords

Knowledge graphAdaptive learning pathHigher educationEmpirical studyGuizhou Province

References

  1. Google. Introducing the knowledge graph: Things, not strings. Google Blog, 2012,16(5), 1-5.
  2. Wang Y, Li J, Zhang H. Knowledge graph-based adaptive learning path recommendation for higher education[J]. Journal of Educational Technology & Society, 2020, 23(3), 124-136.
  3. Zhang L, Chen X. Construction of disciplinary knowledge graph for adaptive learning in computer science[J]. Journal of Computer-Assisted Learning, 2019, 35(4), 489-502.
  4. Li M, Wang H, Liu Z. Empirical study on the impact of knowledge graph on students' learning engagement in adaptive learning[J]. British Journal of Educational Technology, 2021, 52(2), 789-806.
  5. Chen Y, Zhang Q, Li J. Knowledge graph-enhanced collaborative filtering for adaptive learning path recommendation[J]. IEEE Transactions on Learning Technologies, 2022, 15(3), 456-468.
  6. Brown A L, Palincsar A S. Adaptive learning systems: A review of theoretical foundations and practical applications[J]. Educational Psychologist, 2018, 53(2), 103-124.
  7. Zhao J, Liu M, Wang H. Digital transformation of higher education in underdeveloped regions: Evidence from Guizhou, China[J]. Journal of Educational Computing Research, 2023, 61(4), 987-1012.
  8. Liu C, Li Y, Zhang Z. A knowledge graph-based framework for personalized learning path generation[J]. Computers & Education, 2020, 156, 103987.
  9. Peterson J C, Pennington N. Cognitive load theory and adaptive learning: Implications for instructional design[J]. Journal of Educational Psychology, 2019, 111(3), 452-468.
  10. Wang Z, Chen L, Li S. Evaluating the effectiveness of knowledge graph-enhanced adaptive learning in higher education[J]. Journal of Educational Technology Research and Development, 2021, 69(4), 1234-1256.