English

Privacy-Preserving Synthetic Educational Data Generation

Computers and Society 2022-07-09 v1 Artificial Intelligence Cryptography and Security Machine Learning

Abstract

Institutions collect massive learning traces but they may not disclose it for privacy issues. Synthetic data generation opens new opportunities for research in education. In this paper we present a generative model for educational data that can preserve the privacy of participants, and an evaluation framework for comparing synthetic data generators. We show how naive pseudonymization can lead to re-identification threats and suggest techniques to guarantee privacy. We evaluate our method on existing massive educational open datasets.

Keywords

Cite

@article{arxiv.2207.03202,
  title  = {Privacy-Preserving Synthetic Educational Data Generation},
  author = {Jill-Jênn Vie and Tomas Rigaux and Sein Minn},
  journal= {arXiv preprint arXiv:2207.03202},
  year   = {2022}
}
R2 v1 2026-06-24T12:17:03.352Z