@inproceedings{vaz-etal-2026-racismobr,
title = "{R}acismo{BR}: A Manually Annotated Dataset for Racist Discourse Detection in {B}razilian {P}ortuguese",
author = "Vaz, Jo{\~a}o V{\'i}tor and
Benevenuto, Fabr{\'i}cio and
Gon{\c{c}}alves, Marcos Andr{\'e}",
editor = "Souza, Marlo and
de-Dios-Flores, Iria and
Santos, Diana and
Freitas, Larissa and
Souza, Jackson Wilke da Cruz and
Ribeiro, Eug{\'e}nio",
booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
month = apr,
year = "2026",
address = "Salvador, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.propor-1.76/",
pages = "770--779",
ISBN = "979-8-89176-387-6",
abstract = "Racist discourse on social media appears both through explicit attacks and subtle, context-dependent forms, remaining a challenge for Natural Language Processing. We introduce RacismoBR, a culturally grounded dataset for detecting racist discourse in Brazilian Portuguese, manually annotated exclusively by Black researchers to ensure sociolinguistic validity and epistemic representativeness. We conduct a controlled evaluation of binary racism classification in our dataset considering several classification modeling paradigms: classical machine learning, supervised Transformer-based (Small) Language Models, and Large Language models under in-context, few-shot learning. Results show that GPT-4.1 and BERTimbau yield the highest Macro-F1 scores; however, Wilcoxon signed-rank tests reveal no statistically significant differences across models, mostly due to high variability. Across paradigms, classifiers consistently display higher precision for non-racist content and higher recall for racist content. A qualitative analysis highlights persistent difficulties with implicit, euphemized, and context-dependent racism. These findings indicate that culturally grounded annotation plays a more decisive role than architectural sophistication alone in advancing racism detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vaz-etal-2026-racismobr">
<titleInfo>
<title>RacismoBR: A Manually Annotated Dataset for Racist Discourse Detection in Brazilian Portuguese</title>
</titleInfo>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="given">Vítor</namePart>
<namePart type="family">Vaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabrício</namePart>
<namePart type="family">Benevenuto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="given">André</namePart>
<namePart type="family">Gonçalves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marlo</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iria</namePart>
<namePart type="family">de-Dios-Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larissa</namePart>
<namePart type="family">Freitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jackson</namePart>
<namePart type="given">Wilke</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Cruz</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugénio</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Salvador, Brazil</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-387-6</identifier>
</relatedItem>
<abstract>Racist discourse on social media appears both through explicit attacks and subtle, context-dependent forms, remaining a challenge for Natural Language Processing. We introduce RacismoBR, a culturally grounded dataset for detecting racist discourse in Brazilian Portuguese, manually annotated exclusively by Black researchers to ensure sociolinguistic validity and epistemic representativeness. We conduct a controlled evaluation of binary racism classification in our dataset considering several classification modeling paradigms: classical machine learning, supervised Transformer-based (Small) Language Models, and Large Language models under in-context, few-shot learning. Results show that GPT-4.1 and BERTimbau yield the highest Macro-F1 scores; however, Wilcoxon signed-rank tests reveal no statistically significant differences across models, mostly due to high variability. Across paradigms, classifiers consistently display higher precision for non-racist content and higher recall for racist content. A qualitative analysis highlights persistent difficulties with implicit, euphemized, and context-dependent racism. These findings indicate that culturally grounded annotation plays a more decisive role than architectural sophistication alone in advancing racism detection.</abstract>
<identifier type="citekey">vaz-etal-2026-racismobr</identifier>
<location>
<url>https://aclanthology.org/2026.propor-1.76/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>770</start>
<end>779</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RacismoBR: A Manually Annotated Dataset for Racist Discourse Detection in Brazilian Portuguese
%A Vaz, João Vítor
%A Benevenuto, Fabrício
%A Gonçalves, Marcos André
%Y Souza, Marlo
%Y de-Dios-Flores, Iria
%Y Santos, Diana
%Y Freitas, Larissa
%Y Souza, Jackson Wilke da Cruz
%Y Ribeiro, Eugénio
%S Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1
%D 2026
%8 April
%I Association for Computational Linguistics
%C Salvador, Brazil
%@ 979-8-89176-387-6
%F vaz-etal-2026-racismobr
%X Racist discourse on social media appears both through explicit attacks and subtle, context-dependent forms, remaining a challenge for Natural Language Processing. We introduce RacismoBR, a culturally grounded dataset for detecting racist discourse in Brazilian Portuguese, manually annotated exclusively by Black researchers to ensure sociolinguistic validity and epistemic representativeness. We conduct a controlled evaluation of binary racism classification in our dataset considering several classification modeling paradigms: classical machine learning, supervised Transformer-based (Small) Language Models, and Large Language models under in-context, few-shot learning. Results show that GPT-4.1 and BERTimbau yield the highest Macro-F1 scores; however, Wilcoxon signed-rank tests reveal no statistically significant differences across models, mostly due to high variability. Across paradigms, classifiers consistently display higher precision for non-racist content and higher recall for racist content. A qualitative analysis highlights persistent difficulties with implicit, euphemized, and context-dependent racism. These findings indicate that culturally grounded annotation plays a more decisive role than architectural sophistication alone in advancing racism detection.
%U https://aclanthology.org/2026.propor-1.76/
%P 770-779
Markdown (Informal)
[RacismoBR: A Manually Annotated Dataset for Racist Discourse Detection in Brazilian Portuguese](https://aclanthology.org/2026.propor-1.76/) (Vaz et al., PROPOR 2026)
ACL