@inproceedings{bokaei-etal-2026-hate,
title = "When Does Hate Transfer? A Large-Scale Study of Cross-Lingual Hate Speech Detection",
author = "Bokaei, Zahra and
Magdy, Walid and
Webber, Bonnie",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1491/",
pages = "34086--34104",
ISBN = "979-8-89176-459-0",
abstract = "Effective detection of hate content is essential for maintaining healthy online communities, yet performance can vary substantially across languages. This work investigates a core practical question: Can training data from one language support hate-speech detection in another language with comparable performance? To answer this question, we conduct a large-scale study across 14 languages. Our analysis shows that transfer effectiveness could depend on several factors{---}including, but not limited to, dataset size, resources and temporal overlap. At the same time, we observe consistent patterns in which certain language pairs exhibit stronger transfer performance. Upon further analysis, we find that these patterns can be attributed to cultural cues or shared societal characteristics. Our analysis includes low-resource languages, offering practical insights into when cross-lingual transfer can support them and where its limitations emerge. These findings provide guidance for designing more reliable and generalizable hate detection systems.\par {Warning:} This paper includes examples of hate speech for research purposes."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bokaei-etal-2026-hate">
<titleInfo>
<title>When Does Hate Transfer? A Large-Scale Study of Cross-Lingual Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zahra</namePart>
<namePart type="family">Bokaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Effective detection of hate content is essential for maintaining healthy online communities, yet performance can vary substantially across languages. This work investigates a core practical question: Can training data from one language support hate-speech detection in another language with comparable performance? To answer this question, we conduct a large-scale study across 14 languages. Our analysis shows that transfer effectiveness could depend on several factors—including, but not limited to, dataset size, resources and temporal overlap. At the same time, we observe consistent patterns in which certain language pairs exhibit stronger transfer performance. Upon further analysis, we find that these patterns can be attributed to cultural cues or shared societal characteristics. Our analysis includes low-resource languages, offering practical insights into when cross-lingual transfer can support them and where its limitations emerge. These findings provide guidance for designing more reliable and generalizable hate detection systems.\par Warning: This paper includes examples of hate speech for research purposes.</abstract>
<identifier type="citekey">bokaei-etal-2026-hate</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1491/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>34086</start>
<end>34104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Does Hate Transfer? A Large-Scale Study of Cross-Lingual Hate Speech Detection
%A Bokaei, Zahra
%A Magdy, Walid
%A Webber, Bonnie
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F bokaei-etal-2026-hate
%X Effective detection of hate content is essential for maintaining healthy online communities, yet performance can vary substantially across languages. This work investigates a core practical question: Can training data from one language support hate-speech detection in another language with comparable performance? To answer this question, we conduct a large-scale study across 14 languages. Our analysis shows that transfer effectiveness could depend on several factors—including, but not limited to, dataset size, resources and temporal overlap. At the same time, we observe consistent patterns in which certain language pairs exhibit stronger transfer performance. Upon further analysis, we find that these patterns can be attributed to cultural cues or shared societal characteristics. Our analysis includes low-resource languages, offering practical insights into when cross-lingual transfer can support them and where its limitations emerge. These findings provide guidance for designing more reliable and generalizable hate detection systems.\par Warning: This paper includes examples of hate speech for research purposes.
%U https://aclanthology.org/2026.emnlp-main.1491/
%P 34086-34104
Markdown (Informal)
[When Does Hate Transfer? A Large-Scale Study of Cross-Lingual Hate Speech Detection](https://aclanthology.org/2026.emnlp-main.1491/) (Bokaei et al., EMNLP 2026)
ACL