Privacy-Preserving Synthetic Educational Data Generation

Jill-Jênn Vie; Tomas Rigaux; Sein Minn

Conference papers

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

Inria Saclay - Ile de France

2 CEDAR - Rich Data Analytics at Cloud Scale

LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau], Inria Saclay - Ile de France

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 : Privacy Item response theory Generative models

Document type :

Conference papers

Domain :

Computer Science [cs] / Artificial Intelligence [cs.AI]

Computer Science [cs] / Technology for Human Learning

Computer Science [cs] / Cryptography and Security [cs.CR]

Complete list of metadata

https://hal.inria.fr/hal-03715416
Contributor : Jill-Jênn Vie Connect in order to contact the contributor
Submitted on : Wednesday, July 6, 2022 - 1:41:10 PM
Last modification on : Saturday, July 9, 2022 - 3:32:56 AM

Privacy-Preserving Synthetic Educational Data Generation

Files

Identifiers

Collections

Citation

Export

Metrics

1

0

Privacy-Preserving Synthetic Educational Data Generation

Files

Identifiers

Collections

Citation

Export

Share

Metrics

1

0