Discriminação Algorítmica de Gênero: Estudo de Caso e Análise no Contexto Brasileiro
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Standard
Discriminação Algorítmica de Gênero : Estudo de Caso e Análise no Contexto Brasileiro. / Taso, Fernanda Tiemi de S.; Quadros dos Reis, Valéria; Martinez, Fábio H. V.
Anais do IV Workshop sobre as Implicações da Computação na Sociedade . Porto Alegre : Sociedade Brasileira de Computação (SBC), 2023. p. 13-25 (Anais do Workshop sobre as Implicações da Computação na Sociedade.; No. 4).Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - Discriminação Algorítmica de Gênero
AU - Taso, Fernanda Tiemi de S.
AU - Quadros dos Reis, Valéria
AU - Martinez, Fábio H. V.
N1 - Conference code: 4
PY - 2023/8/6
Y1 - 2023/8/6
N2 - This paper aims to identify discriminatory trends in Natural Language Processing models that represent words through vectors called Word Embeddings. Pre-defined metrics for identifying bias were adapted and exposed the existence of gender stereotypes in traditional occupations and their correlation with the women’s proportion in the national labor market. Moreover, stereotyped analogies between feminine and masculine pronouns were found. Results reveal sexism similar to other studies and allow us to discuss the impact of the use of language models in our society. Finally, the work paves the way for the use of metrics to identify other types of discrimination in the Brazilian context.
AB - This paper aims to identify discriminatory trends in Natural Language Processing models that represent words through vectors called Word Embeddings. Pre-defined metrics for identifying bias were adapted and exposed the existence of gender stereotypes in traditional occupations and their correlation with the women’s proportion in the national labor market. Moreover, stereotyped analogies between feminine and masculine pronouns were found. Results reveal sexism similar to other studies and allow us to discuss the impact of the use of language models in our society. Finally, the work paves the way for the use of metrics to identify other types of discrimination in the Brazilian context.
KW - Business informatics
U2 - 10.5753/wics.2023.229980
DO - 10.5753/wics.2023.229980
M3 - Article in conference proceedings
T3 - Anais do Workshop sobre as Implicações da Computação na Sociedade.
SP - 13
EP - 25
BT - Anais do IV Workshop sobre as Implicações da Computação na Sociedade
PB - Sociedade Brasileira de Computação (SBC)
CY - Porto Alegre
Y2 - 6 August 2023 through 11 August 2023
ER -