Back
Journal article Open Access Scopus Source The journal / series is indexed in Scopus (SCImago list). The article itself has not been verified. 12 Citations Quartil Q2

Strategies to improve fairness in artificial intelligence:A systematic literature review

António Rui Trigo Ribeiro , Stein, Nubia , Belfo, Fernando Paulo dos Santos Rodrigues
ISLA — Instituto Politécnico de Gestão e Tecnologia
Education for Information, Volume 40, Issue 3, 27 08 2024, pp. 323–346
DOI: 10.3233/efi-240045

Resume

Abstract
Decisions based on artificial intelligence can reproduce biases or prejudices present in biased historical data and poorly formulated systems, presenting serious social consequences for underrepresented groups of individuals. This paper presents a systematic literature review of technical, feasible, and practicable solutions to improve fairness in artificial intelligence classified according to different perspectives: fairness metrics, moment of intervention (pre-processing, processing, or post-processing), research area, datasets, and algorithms used in the research. The main contribution of this paper is to establish common ground regarding the techniques to be used to improve fairness in artificial intelligence, defined as the absence of bias or discrimination in the decisions made by artificial intelligence systems.

Keywords

#algorithmic fairness #Artificial Intelligence #machine learning bias #discrimination #fairness metrics #data preprocessing #in-processing #post-processing #underrepresented groups #fairness interventions #Computer science #Applications of artificial intelligence #Intervention (counseling)

Bibliographic Details

Publication Type Journal article
Publication Year 2024
Journal / Conference / Work Education for Information
ISSN 0167-8329
Volume / Issue Vol. 40 (3)
Pagination pp. 323–346
Publication Status Published
Quartile (SCImago) Q2
Scopus Indexing Indexed source (via SCImago)

ISLA Authors & Affiliations

A
António Rui Trigo Ribeiro
antonio.trigo@gmail.com ID: 761E-282F-2F8C
Profile
F
Fernando Paulo dos Santos Rodrigues Belfo
fpbelfo@gmail.com ID: 681D-E551-EF22
Profile