Sexismo no Brasil: Análise de um Word Embedding por meio de testes baseados em associação implícita

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Standard

Sexismo no Brasil: Análise de um Word Embedding por meio de testes baseados em associação implícita. / Quadros dos Reis, Valéria.
BRAZILIAN SYMPOSIUM IN INFORMATION AND HUMAN LANGUAGE TECHNOLOGY (STIL). Hrsg. / Helena Caseli; Maria Jose Bocorny Finatto. Sociedade Brasileira de Computação (SBC), 2023. S. 53-62.

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Harvard

Quadros dos Reis, V 2023, Sexismo no Brasil: Análise de um Word Embedding por meio de testes baseados em associação implícita. in H Caseli & MJB Finatto (Hrsg.), BRAZILIAN SYMPOSIUM IN INFORMATION AND HUMAN LANGUAGE TECHNOLOGY (STIL). Sociedade Brasileira de Computação (SBC), S. 53-62, 14th Brazilian Symposium in Information and Human Language Technology - STIL 2023, Brasilien, 25.09.23. https://doi.org/10.5753/stil.2023.233845

APA

Quadros dos Reis, V. (2023). Sexismo no Brasil: Análise de um Word Embedding por meio de testes baseados em associação implícita. In H. Caseli, & M. J. B. Finatto (Hrsg.), BRAZILIAN SYMPOSIUM IN INFORMATION AND HUMAN LANGUAGE TECHNOLOGY (STIL) (S. 53-62). Sociedade Brasileira de Computação (SBC). https://doi.org/10.5753/stil.2023.233845

Vancouver

Quadros dos Reis V. Sexismo no Brasil: Análise de um Word Embedding por meio de testes baseados em associação implícita. in Caseli H, Finatto MJB, Hrsg., BRAZILIAN SYMPOSIUM IN INFORMATION AND HUMAN LANGUAGE TECHNOLOGY (STIL). Sociedade Brasileira de Computação (SBC). 2023. S. 53-62 doi: 10.5753/stil.2023.233845

Bibtex

@inbook{8deadf8ee7e24a918c1031c005f39ee6,
title = "Sexismo no Brasil: An{\'a}lise de um Word Embedding por meio de testes baseados em associa{\c c}{\~a}o impl{\'i}cita",
abstract = "This work reports experiments based on the Psychology Implicit Association Test to identify and quantify biases in a Word Embeding (WE) of the Portuguese language. For this, we use a GloVe model trained on an Internet corpus collection. The results show that several common sense and gender stereotypes can be found in WE. Within the context of professions, we note a historical sexism, since the identified bias often reflects the statistics of gender performance in occupation groups in Brazil. The results show discrimination similar to those of international studies and allow discussing the impact of the use of language models in our society",
keywords = "Informatics, Artificial Intelligence, Natural Language Processing, Word Embedding, Implicit Association, Gender bias, Discrimination analysis",
author = "{Quadros dos Reis}, Val{\'e}ria",
year = "2023",
month = sep,
day = "25",
doi = "10.5753/stil.2023.233845",
language = "Portuguese",
pages = "53--62",
editor = "Helena Caseli and Finatto, {Maria Jose Bocorny}",
booktitle = "BRAZILIAN SYMPOSIUM IN INFORMATION AND HUMAN LANGUAGE TECHNOLOGY (STIL)",
publisher = "Sociedade Brasileira de Computa{\c c}{\~a}o (SBC)",
address = "Brazil",
note = "14th Brazilian Symposium in Information and Human Language Technology - STIL 2023 ; Conference date: 25-09-2023 Through 29-09-2023",
url = "https://www.bracis.dcc.ufmg.br/collocated-events/stil",

}

RIS

TY - CHAP

T1 - Sexismo no Brasil

T2 - 14th Brazilian Symposium in Information and Human Language Technology - STIL 2023

AU - Quadros dos Reis, Valéria

N1 - Conference code: 14

PY - 2023/9/25

Y1 - 2023/9/25

N2 - This work reports experiments based on the Psychology Implicit Association Test to identify and quantify biases in a Word Embeding (WE) of the Portuguese language. For this, we use a GloVe model trained on an Internet corpus collection. The results show that several common sense and gender stereotypes can be found in WE. Within the context of professions, we note a historical sexism, since the identified bias often reflects the statistics of gender performance in occupation groups in Brazil. The results show discrimination similar to those of international studies and allow discussing the impact of the use of language models in our society

AB - This work reports experiments based on the Psychology Implicit Association Test to identify and quantify biases in a Word Embeding (WE) of the Portuguese language. For this, we use a GloVe model trained on an Internet corpus collection. The results show that several common sense and gender stereotypes can be found in WE. Within the context of professions, we note a historical sexism, since the identified bias often reflects the statistics of gender performance in occupation groups in Brazil. The results show discrimination similar to those of international studies and allow discussing the impact of the use of language models in our society

KW - Informatics

KW - Artificial Intelligence

KW - Natural Language Processing

KW - Word Embedding

KW - Implicit Association

KW - Gender bias

KW - Discrimination analysis

U2 - 10.5753/stil.2023.233845

DO - 10.5753/stil.2023.233845

M3 - Aufsätze in Konferenzbänden

SP - 53

EP - 62

BT - BRAZILIAN SYMPOSIUM IN INFORMATION AND HUMAN LANGUAGE TECHNOLOGY (STIL)

A2 - Caseli, Helena

A2 - Finatto, Maria Jose Bocorny

PB - Sociedade Brasileira de Computação (SBC)

Y2 - 25 September 2023 through 29 September 2023

ER -

DOI