@inproceedings{aupi-etal-2025-wonbias,
title = "{W}o{NB}ias: A Dataset for Classifying Bias {\&} Prejudice Against Women in {B}engali Text",
author = "Aupi, Md. Raisul Islam and
Tafannum, Nishat and
Rahman, Md. Shahidur and
Hassan, Kh Mahmudul and
Rahman, Naimur",
editor = "Fale{\'n}ska, Agnieszka and
Basta, Christine and
Costa-juss{\`a}, Marta and
Sta{\'n}czak, Karolina and
Nozza, Debora",
booktitle = "Proceedings of the 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP)",
month = aug,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.gebnlp-1.10/",
doi = "10.18653/v1/2025.gebnlp-1.10",
pages = "105--110",
ISBN = "979-8-89176-277-0",
abstract = "This paper presents WoNBias, a curated Bengali dataset to identify gender-based biases, stereotypes, and harmful language directed at women. It merges digital sources- social media, blogs, news- with offline tactics comprising surveys and focus groups, alongside some existing corpora to compile a total of 31,484 entries (10,656 negative; 10,170 positive; 10,658 neutral). WoNBias reflects the sociocultural subtleties of bias in both Bengali digital and offline conversations. By bridging online and offline biased contexts, the dataset supports content moderation, policy interventions, and equitable NLP research for Bengali, a low-resource language critically underserved by existing tools. WoNBias aims to combat systemic gender discrimination against women on digital platforms, empowering researchers and practitioners to combat harmful narratives in Bengali-speaking communities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aupi-etal-2025-wonbias">
<titleInfo>
<title>WoNBias: A Dataset for Classifying Bias & Prejudice Against Women in Bengali Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Raisul</namePart>
<namePart type="given">Islam</namePart>
<namePart type="family">Aupi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nishat</namePart>
<namePart type="family">Tafannum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Shahidur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kh</namePart>
<namePart type="given">Mahmudul</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naimur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Faleńska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Basta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karolina</namePart>
<namePart type="family">Stańczak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-277-0</identifier>
</relatedItem>
<abstract>This paper presents WoNBias, a curated Bengali dataset to identify gender-based biases, stereotypes, and harmful language directed at women. It merges digital sources- social media, blogs, news- with offline tactics comprising surveys and focus groups, alongside some existing corpora to compile a total of 31,484 entries (10,656 negative; 10,170 positive; 10,658 neutral). WoNBias reflects the sociocultural subtleties of bias in both Bengali digital and offline conversations. By bridging online and offline biased contexts, the dataset supports content moderation, policy interventions, and equitable NLP research for Bengali, a low-resource language critically underserved by existing tools. WoNBias aims to combat systemic gender discrimination against women on digital platforms, empowering researchers and practitioners to combat harmful narratives in Bengali-speaking communities.</abstract>
<identifier type="citekey">aupi-etal-2025-wonbias</identifier>
<identifier type="doi">10.18653/v1/2025.gebnlp-1.10</identifier>
<location>
<url>https://aclanthology.org/2025.gebnlp-1.10/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>105</start>
<end>110</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WoNBias: A Dataset for Classifying Bias & Prejudice Against Women in Bengali Text
%A Aupi, Md. Raisul Islam
%A Tafannum, Nishat
%A Rahman, Md. Shahidur
%A Hassan, Kh Mahmudul
%A Rahman, Naimur
%Y Faleńska, Agnieszka
%Y Basta, Christine
%Y Costa-jussà, Marta
%Y Stańczak, Karolina
%Y Nozza, Debora
%S Proceedings of the 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-277-0
%F aupi-etal-2025-wonbias
%X This paper presents WoNBias, a curated Bengali dataset to identify gender-based biases, stereotypes, and harmful language directed at women. It merges digital sources- social media, blogs, news- with offline tactics comprising surveys and focus groups, alongside some existing corpora to compile a total of 31,484 entries (10,656 negative; 10,170 positive; 10,658 neutral). WoNBias reflects the sociocultural subtleties of bias in both Bengali digital and offline conversations. By bridging online and offline biased contexts, the dataset supports content moderation, policy interventions, and equitable NLP research for Bengali, a low-resource language critically underserved by existing tools. WoNBias aims to combat systemic gender discrimination against women on digital platforms, empowering researchers and practitioners to combat harmful narratives in Bengali-speaking communities.
%R 10.18653/v1/2025.gebnlp-1.10
%U https://aclanthology.org/2025.gebnlp-1.10/
%U https://doi.org/10.18653/v1/2025.gebnlp-1.10
%P 105-110
Markdown (Informal)
[WoNBias: A Dataset for Classifying Bias & Prejudice Against Women in Bengali Text](https://aclanthology.org/2025.gebnlp-1.10/) (Aupi et al., GeBNLP 2025)
ACL