@inproceedings{mostafazadeh-davani-etal-2024-d3code,
title = "{D}3{CODE}: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation",
author = "Mostafazadeh Davani, Aida and
Diaz, Mark and
Baker, Dylan K and
Prabhakaran, Vinodkumar",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.1029",
doi = "10.18653/v1/2024.emnlp-main.1029",
pages = "18511--18526",
abstract = "While human annotations play a crucial role in language technologies, annotator subjectivity has long been overlooked in data collection. Recent studies that critically examine this issue are often focused on Western contexts, and solely document differences across age, gender, or racial groups. Consequently, NLP research on subjectivity have failed to consider that individuals within demographic groups may hold diverse values, which influence their perceptions beyond group norms. To effectively incorporate these considerations into NLP pipelines, we need datasets with extensive parallel annotations from a variety of social and cultural groups.In this paper we introduce the D3CODE dataset: a large-scale cross-cultural dataset of parallel annotations for offensive language in over 4.5K English sentences annotated by a pool of more than 4k annotators, balanced across gender and age, from across 21 countries, representing eight geo-cultural regions. The dataset captures annotators{'} moral values along six moral foundations: care, equality, proportionality, authority, loyalty, and purity. Our analyses reveal substantial regional variations in annotators{'} perceptions that are shaped by individual moral values, providing crucial insights for developing pluralistic, culturally sensitive NLP models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mostafazadeh-davani-etal-2024-d3code">
<titleInfo>
<title>D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Mostafazadeh Davani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Diaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dylan</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Baker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinodkumar</namePart>
<namePart type="family">Prabhakaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While human annotations play a crucial role in language technologies, annotator subjectivity has long been overlooked in data collection. Recent studies that critically examine this issue are often focused on Western contexts, and solely document differences across age, gender, or racial groups. Consequently, NLP research on subjectivity have failed to consider that individuals within demographic groups may hold diverse values, which influence their perceptions beyond group norms. To effectively incorporate these considerations into NLP pipelines, we need datasets with extensive parallel annotations from a variety of social and cultural groups.In this paper we introduce the D3CODE dataset: a large-scale cross-cultural dataset of parallel annotations for offensive language in over 4.5K English sentences annotated by a pool of more than 4k annotators, balanced across gender and age, from across 21 countries, representing eight geo-cultural regions. The dataset captures annotators’ moral values along six moral foundations: care, equality, proportionality, authority, loyalty, and purity. Our analyses reveal substantial regional variations in annotators’ perceptions that are shaped by individual moral values, providing crucial insights for developing pluralistic, culturally sensitive NLP models.</abstract>
<identifier type="citekey">mostafazadeh-davani-etal-2024-d3code</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.1029</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.1029</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>18511</start>
<end>18526</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation
%A Mostafazadeh Davani, Aida
%A Diaz, Mark
%A Baker, Dylan K.
%A Prabhakaran, Vinodkumar
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F mostafazadeh-davani-etal-2024-d3code
%X While human annotations play a crucial role in language technologies, annotator subjectivity has long been overlooked in data collection. Recent studies that critically examine this issue are often focused on Western contexts, and solely document differences across age, gender, or racial groups. Consequently, NLP research on subjectivity have failed to consider that individuals within demographic groups may hold diverse values, which influence their perceptions beyond group norms. To effectively incorporate these considerations into NLP pipelines, we need datasets with extensive parallel annotations from a variety of social and cultural groups.In this paper we introduce the D3CODE dataset: a large-scale cross-cultural dataset of parallel annotations for offensive language in over 4.5K English sentences annotated by a pool of more than 4k annotators, balanced across gender and age, from across 21 countries, representing eight geo-cultural regions. The dataset captures annotators’ moral values along six moral foundations: care, equality, proportionality, authority, loyalty, and purity. Our analyses reveal substantial regional variations in annotators’ perceptions that are shaped by individual moral values, providing crucial insights for developing pluralistic, culturally sensitive NLP models.
%R 10.18653/v1/2024.emnlp-main.1029
%U https://aclanthology.org/2024.emnlp-main.1029
%U https://doi.org/10.18653/v1/2024.emnlp-main.1029
%P 18511-18526
Markdown (Informal)
[D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation](https://aclanthology.org/2024.emnlp-main.1029) (Mostafazadeh Davani et al., EMNLP 2024)
ACL