Analysis of Student Performance Based on Differential Privacy Protection

DOI

10.2991/assehr.k.211220.301How to use a DOI?

Keywords

Differential privacy; association rule mining; student performance analysis

Abstract

In the context of the information age, the use of data has greatly promoted the development of society. Education is inseparable from the development of the country, and education has become an area of close concern to society. How to maximize the useful value of mining data while protecting the privacy contained in the data is a problem we need to pay attention to. Based on the test scores of students in multiple courses, this paper analyzes the Apriori algorithm in the correlation analysis and mining, and obtains the correlation between the courses and the interval distribution of test scores. On this basis, we filter the obtained association rules, and use the Laplacian mechanism to increase noise interference to the filtered association rules, and protect the privacy of students through differential privacy. While using the maximum value of data as much as possible to promote the development of targeted teaching work, the privacy of students’ performance is protected.

Copyright

© 2021 The Authors. Published by Atlantis Press SARL.

Open Access

This is an open access article under the CC BY-NC license.

Download article (PDF)

TY  - CONF
AU  - Zhao Lin
AU  - Sun Yingping
PY  - 2021
DA  - 2021/12/24
TI  - Analysis of Student Performance Based on Differential Privacy Protection
BT  - Proceedings of the 2021 4th International Conference on Humanities Education and Social Sciences (ICHESS 2021)
PB  - Atlantis Press
SP  - 1779
EP  - 1784
SN  - 2352-5398
UR  - https://doi.org/10.2991/assehr.k.211220.301
DO  - 10.2991/assehr.k.211220.301
ID  - Lin2021
ER  -