Mitigating Gender Bias in Machine Learning Data Sets

Files in This Item:
 File SizeFormat
DownloadBias2020_MitigatingGenderBias.pdf396.37 kBAdobe PDF
Title: Mitigating Gender Bias in Machine Learning Data Sets
Authors: Leavy, SusanMeaney, GerardineWade, KarenGreene, Derek
Permanent link:
Date: 12-Jul-2020
Online since: 2021-09-08T14:58:22Z
Abstract: Algorithmic bias has the capacity to amplify and perpetuate societal bias, and presents profound ethical implications for society. Gender bias in algorithms has been identified in the context of employment advertising and recruitment tools, due to their reliance on underlying language processing and recommendation algorithms. Attempts to address such issues have involved testing learned associations, integrating concepts of fairness to machine learning, and performing more rigorous analysis of training data. Mitigating bias when algorithms are trained on textual data is particularly challenging given the complex way gender ideology is embedded in language. This paper proposes a framework for the identification of gender bias in training data for machine learning. The work draws upon gender theory and sociolinguistics to systematically indicate levels of bias in textual training data and associated neural word embedding models, thus highlighting pathways for both removing bias from training data and critically assessing its impact in the context of search and recommender systems.
Funding Details: Irish Research Council
Science Foundation Ireland
Type of material: Conference Publication
Publisher: Springer
Series/Report no.: Communications in the Computer and Information Science; 1245
Copyright (published version): 2020 Springer
Keywords: Algorithmic biasGenderMachine learningNatural language processing
DOI: 10.1007/978-3-030-52485-2_2
Other versions:
Language: en
Status of Item: Peer reviewed
Is part of: Boratto, L., Farrali, S., Marras, M., Stilo, G. Bias and Social Aspects in Search and Recommendation: First International Workshop, BIAS 2020, Lisbon, Portugal, April 14, Proceedings
Conference Details: International Workshop on Algorithmic Bias in Search and Recommendation (Bias 2020), Lisbon, Portugal (held online due to coronavirus outbreak) 14 April 2020
ISBN: 978-3-030-52484-5
ISSN: 1865-0929
This item is made available under a Creative Commons License:
Appears in Collections:Information and Communication Studies Research Collection
Insight Research Collection

Show full item record

Page view(s)

checked on Sep 20, 2021


checked on Sep 20, 2021

Google ScholarTM



If you are a publisher or author and have copyright concerns for any item, please email and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.