Article: English learning behaviour analysis and intelligent recommendation system driven by big data Journal: International Journal of Continuing Engineering Education and Life-Long Learning (IJCEELL) 2026 Vol.36 No.9 pp.214 - 239 Abstract: This paper proposes a dynamic privacy preserving intelligent recommendation method under a joint learning framework to address the contradiction between privacy protection and recommendation accuracy caused by cross platform data silos in English learning recommendations. Firstly, this paper conducts an in-depth analysis of multimodal English learning behaviour and uses transformers to capture cross modal semantic associations. Secondly, this paper innovatively designs a data sensitivity evaluation mechanism based on Kullback Leibler (KL) divergence to achieve dynamic allocation of differential privacy budget. Finally, this paper proposes a federated attention mechanism to achieve cross platform user interest transfer. The experiment shows that this method increases the hit rate by 37% in cold start scenarios, reduces communication overhead by 76%, and controls the success rate of member inference attacks at 0.13, effectively solving the collaborative optimisation problems of privacy security, recommendation accuracy, and communication efficiency in cross platform English learning recommendations. Inderscience Publishers - linking academia, business and industry through research

Title: English learning behaviour analysis and intelligent recommendation system driven by big data

Authors: Shuling Yang; Dongqing Hao

Addresses: School of Foreign Languages, Jilin Normal University, Siping 136000, Jilin, China ' School of Foreign Language Studies, Inner Mongolia Medical University, Hohhot 010110, Inner Mongolia Autonomous Region, China

Abstract: This paper proposes a dynamic privacy preserving intelligent recommendation method under a joint learning framework to address the contradiction between privacy protection and recommendation accuracy caused by cross platform data silos in English learning recommendations. Firstly, this paper conducts an in-depth analysis of multimodal English learning behaviour and uses transformers to capture cross modal semantic associations. Secondly, this paper innovatively designs a data sensitivity evaluation mechanism based on Kullback Leibler (KL) divergence to achieve dynamic allocation of differential privacy budget. Finally, this paper proposes a federated attention mechanism to achieve cross platform user interest transfer. The experiment shows that this method increases the hit rate by 37% in cold start scenarios, reduces communication overhead by 76%, and controls the success rate of member inference attacks at 0.13, effectively solving the collaborative optimisation problems of privacy security, recommendation accuracy, and communication efficiency in cross platform English learning recommendations.

Keywords: dynamic privacy protection; English learning behaviour analysis; cross-platform recommendation; intelligent recommendation system; federated learning.

DOI: 10.1504/IJCEELL.2026.153608

International Journal of Continuing Engineering Education and Life-Long Learning, 2026 Vol.36 No.9, pp.214 - 239

Received: 30 Jul 2025
Accepted: 29 Jan 2026
Published online: 18 May 2026 *

Title: English learning behaviour analysis and intelligent recommendation system driven by big data

Keep up-to-date