An Empirical Study on Group Fairness Metrics of Judicial Data

Group fairness means that different groups have an equal probability of being predicted for one aspect. It is a significant fairness definition, which is conducive to maintaining social harmony and stability. Fairness is a vital issue when an artificial intelligence software system is used to make j...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yanjun Li, Huan Huang, Xinwei Guo, Yuyu Yuan
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Data fairness sensitive attributes metric judicial data Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/323a755c0f0e469d89410f64af96cce6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:323a755c0f0e469d89410f64af96cce6
record_format	dspace
spelling	oai:doaj.org-article:323a755c0f0e469d89410f64af96cce62021-11-18T00:07:24ZAn Empirical Study on Group Fairness Metrics of Judicial Data2169-353610.1109/ACCESS.2021.3122443https://doaj.org/article/323a755c0f0e469d89410f64af96cce62021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9585119/https://doaj.org/toc/2169-3536Group fairness means that different groups have an equal probability of being predicted for one aspect. It is a significant fairness definition, which is conducive to maintaining social harmony and stability. Fairness is a vital issue when an artificial intelligence software system is used to make judicial decisions. Either data or algorithm alone may lead to unfair results. Determining the fairness of the dataset is a prerequisite for studying the fairness of algorithms. This paper focuses on the dataset to research group fairness from both micro and macro views. We propose a framework to determine the sensitive attributes of a dataset and metrics to measure the fair degree of sensitive attributes. We conducted experiments and statistical analysis of the judicial data to demonstrate the framework and metric approach better. The framework and metric approach can be applied to datasets of other domains, providing persuasive evidence for the effectiveness and availability of algorithmic fairness research. It opens up a new way for the research of the fairness of the dataset.Yanjun LiHuan HuangXinwei GuoYuyu YuanIEEEarticleData fairnesssensitive attributesmetricjudicial dataElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 149043-149049 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Data fairness sensitive attributes metric judicial data Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Data fairness sensitive attributes metric judicial data Electrical engineering. Electronics. Nuclear engineering TK1-9971 Yanjun Li Huan Huang Xinwei Guo Yuyu Yuan An Empirical Study on Group Fairness Metrics of Judicial Data
description	Group fairness means that different groups have an equal probability of being predicted for one aspect. It is a significant fairness definition, which is conducive to maintaining social harmony and stability. Fairness is a vital issue when an artificial intelligence software system is used to make judicial decisions. Either data or algorithm alone may lead to unfair results. Determining the fairness of the dataset is a prerequisite for studying the fairness of algorithms. This paper focuses on the dataset to research group fairness from both micro and macro views. We propose a framework to determine the sensitive attributes of a dataset and metrics to measure the fair degree of sensitive attributes. We conducted experiments and statistical analysis of the judicial data to demonstrate the framework and metric approach better. The framework and metric approach can be applied to datasets of other domains, providing persuasive evidence for the effectiveness and availability of algorithmic fairness research. It opens up a new way for the research of the fairness of the dataset.
format	article
author	Yanjun Li Huan Huang Xinwei Guo Yuyu Yuan
author_facet	Yanjun Li Huan Huang Xinwei Guo Yuyu Yuan
author_sort	Yanjun Li
title	An Empirical Study on Group Fairness Metrics of Judicial Data
title_short	An Empirical Study on Group Fairness Metrics of Judicial Data
title_full	An Empirical Study on Group Fairness Metrics of Judicial Data
title_fullStr	An Empirical Study on Group Fairness Metrics of Judicial Data
title_full_unstemmed	An Empirical Study on Group Fairness Metrics of Judicial Data
title_sort	empirical study on group fairness metrics of judicial data
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/323a755c0f0e469d89410f64af96cce6
work_keys_str_mv	AT yanjunli anempiricalstudyongroupfairnessmetricsofjudicialdata AT huanhuang anempiricalstudyongroupfairnessmetricsofjudicialdata AT xinweiguo anempiricalstudyongroupfairnessmetricsofjudicialdata AT yuyuyuan anempiricalstudyongroupfairnessmetricsofjudicialdata AT yanjunli empiricalstudyongroupfairnessmetricsofjudicialdata AT huanhuang empiricalstudyongroupfairnessmetricsofjudicialdata AT xinweiguo empiricalstudyongroupfairnessmetricsofjudicialdata AT yuyuyuan empiricalstudyongroupfairnessmetricsofjudicialdata
_version_	1718425215339331584

An Empirical Study on Group Fairness Metrics of Judicial Data

Ejemplares similares