Privacy-Preserving Learning Analytics: A Comprehensive Framework for Ethical Data Governance in Educational Environments
Keywords:
Algorithmic fairness, Differential privacy, Educational data mining, Federated learning, GDPR, Homomorphic encryption, Learning analytics, Privacy-by-designAbstract
Learning analytics, which involves using student data to improve the education process, is extensively implemented in modern educational organizations including schools and colleges. It facilitates personalization of teaching, prediction of at-risk students, and decision-making on the basis of analytics results. Despite the mentioned benefits, learning analytics brings about significant privacy concerns. Moreover, the existing systems are incapable of providing the necessary level of security for the data involved. The current research thoroughly investigates and analyzes the Privacy-Preserving Learning Analytics (PPLA) Framework. The framework consists of multiple layers and utilizes complex technologies including differential privacy, homomorphic encryption, federated learning, SMPC and access control. The study tested the system on the UCI Student Performance dataset using a sample of 649 students and achieved the optimal balance of privacy and utility. At the differential privacy parameter ɛ=1.5, the data utility is equal to 78.1%, whereas re-identification risk is decreased by up to 0.4%, and model bias is equal to 0.08%. In comparison with basic techniques, PPLA shows better performance by achieving the user satisfaction of 72.3%, saving on processing time/costs of 41.2% and complying with the requirements of GDPR, FERPA and emerging PDPA regulations. The present study can be considered one of the most comprehensive and in-depth analyses of the system in question, and also includes recommendations for schools and colleges.
References
Y. Yan, H. Liu, H. Zhang, T. Chau and J. Li, J. “Designing a generalist education AI framework for multimodal learning and ethical data governance,” Applied Sciences, vol. 15, no. 14, Jul. 2025.
E. Gaisie, O. Owusu-Boateng, I. Yidana, and B. Ghansah, “Unlocking the potential: artificial intelligence in education,” in Unlocking the Potential: Artificial Intelligence in Education, O. Owusu-Boateng, Ed., Deep Science Publishing, 2025, pp. 58–81.
A. Barthwal, M. Campbell and A. K. Shrestha, “Privacy ethics alignment in AI: A stakeholder-centric framework for ethical ai,” Systems, vol. 13, no. 6, Jun. 2025.
I. D. Mienye, and T. G. Swart, “ChatGPT in education: A review of ethical challenges and approaches to enhancing transparency and privacy,” Procedia Computer Science, vol. 254, pp. 181–190, 2025.
M. Selvam and R. G. Vallejo, “Ethical and privacy considerations in AI-driven language learning,” LatIA, vol. 3, Mar. 2025.
M. M. Hasan, “Federated learning models for privacy-preserving AI in enterprise decision systems,” International Journal of Business and Economics Insights, vol. 5, no. 3, pp. 238–269, 2025.
S. Ashfaq, “Artificial intelligence based models for secure data analytics and privacy-preserving data sharing in US healthcare and hospital networks,” International Journal of Business and Economics Insights, vol. 5, no. 3, pp. 65–99, Sept. 2025.
Q. Liu, R. Shakya, M. Khalil, J. Jovanovic, “Advancing privacy in learning analytics using differential privacy,” in Proceedings of the 15th International Learning Analytics and Knowledge Conference, Mar. 2025, pp. 181–191.
R. Sajja, Y. Sermet, D. Cwiertny and I. Demir, “Integrating AI and learning analytics for data-driven pedagogical decisions and personalized interventions in education,” Technology, knowledge and learning, 2025.
H. Hong, L. Dai and X. Zheng, “Advances in wearable sensors for learning analytics: trends, challenges, and prospects,” Sensors, vol. 25, no. 9, Apr. 2025.
J. Barach, “Federated learning for privacy-preserving employee performance analytics,” IEEE Access, vol. 13, pp. 132724–132738, 2025.
N. Li et al., “Privacy‐preserving federated data access and federated learning: Improved data sharing and AI model development in transfusion medicine,” Transfusion, vol. 65, no. 1, pp. 22–28, Nov. 2024.
S. Prabowo et al., “Privacy-preserving tools and technologies: Government adoption and challenges,” in IEEE Access, vol. 13, pp. 33904–33934, 2025.
M. M. U. Mithun, R. Tarannum and S. H. Tanim, “Privacy-aware analytics for managing patient data in SMB healthcare projects,” International Journal of Informatics and Data Science Research, vol. 2, no. 10, pp. 27–57, Oct. 2025.
F. S. Alrayes et al., “Privacy-preserving approach for IoT networks using statistical learning with optimization algorithm on high-dimensional big data environment,” Scientific Reports, vol. 15, no. 1, Jan. 2025.
