Privacy-Preserving Synthetic Educational Data Generation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

Privacy-Preserving Synthetic Educational Data Generation

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.
Fichier principal
Vignette du fichier
EC_TEL_2022_paper_83_Vie.pdf (480.09 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03715416 , version 1 (06-07-2022)

Identifiers

Cite

Jill-Jênn Vie, Tomas Rigaux, Sein Minn. Privacy-Preserving Synthetic Educational Data Generation. EC-TEL 2022 - 17th European Conference on Technology Enhanced Learning, Sep 2022, Toulouse, France. ⟨hal-03715416⟩
277 View
171 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More