Privacy-Preserving Synthetic Educational Data Generation

Jill-Jênn Vie (1) , Tomas Rigaux (1) , Sein Minn (2)

1 SODA - Méthodes computationnelles et mathématiques pour comprendre la société et la santé à partir de données
2 CEDAR - Rich Data Analytics at Cloud Scale

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.

Mots clés: Privacy; Item response theory; Generative models

Domaines: Intelligence artificielle [cs.AI]; Environnements Informatiques pour l'Apprentissage Humain; Cryptographie et sécurité [cs.CR]

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⟩