Bookmark Saya

Semantic Scholar Open Access 2019 553 sitasi

Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting

Maria De-Arteaga Alexey Romanov Hanna M. Wallach J. Chayes C. Borgs +4 lainnya
Lihat Sumber DOI

Abstrak

We present a large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples' lives. We analyze the potential allocation harms that can result from semantic representation bias. To do so, we study the impact on occupation classification of including explicit gender indicators---such as first names and pronouns---in different semantic representations of online biographies. Additionally, we quantify the bias that remains when these indicators are "scrubbed," and describe proxy behavior that occurs in the absence of explicit gender indicators. As we demonstrate, differences in true positive rates between genders are correlated with existing gender imbalances in occupations, which may compound these imbalances.

Topik & Kata Kunci

Computer Science Mathematics Psychology

Penulis (9)

M

Maria De-Arteaga

A

Alexey Romanov

H

Hanna M. Wallach

J

J. Chayes

C

C. Borgs

A

Alexandra Chouldechova

S

S. Geyik

K

K. Kenthapadi

A

A. Kalai

Format Sitasi

APA MLA BibTeX
De-Arteaga, M., Romanov, A., Wallach, H.M., Chayes, J., Borgs, C., Chouldechova, A. et al. (2019). Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting. https://doi.org/10.1145/3287560.3287572

Akses Cepat

Lihat di Sumber doi.org/10.1145/3287560.3287572
Informasi Jurnal
Tahun Terbit
2019
Bahasa
en
Total Sitasi
553×
Sumber Database
Semantic Scholar
DOI
10.1145/3287560.3287572
Akses
Open Access ✓