@inproceedings{assenmacher-etal-2026-beyond,
title = "Beyond the Explicit: A Bilingual Dataset for Dehumanization Detection in Social Media",
author = "Assenmacher, Dennis and
Piot, Paloma and
Laken, Katarina and
Jurgens, David and
Wagner, Claudia",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1958/",
pages = "41753--41776",
ISBN = "979-8-89176-462-0",
abstract = "Digital dehumanization, although a critical issue, remains largely overlooked within the field of computational linguistics and Natural Language Processing (NLP). To our best knowledge, this work presents the most comprehensive annotated bi-lingual dataset on dehumanization, with almost 16.000 instances (44{\%} dehumanizing) that exists today and can serve as both a training resource for machine learning models and a benchmark for evaluating future dehumanization detection techniques. Our comparison of 15 methods shows that traditional hate speech detection approaches perform poorly on dehumanization detection, particularly for implicit forms. By leveraging our dataset in few-shot and fine-tuning settings, LLMs achieve comparable performance on implicit and explicit dehumanization and substantially outperform zero-shot baselines, with average gains of 39{\%} and 65{\%}, respectively. However, detection accuracy remains slightly lower for mechanistic than for animalistic dehumanization, the latter being the dominant focus of prior work."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="assenmacher-etal-2026-beyond">
<titleInfo>
<title>Beyond the Explicit: A Bilingual Dataset for Dehumanization Detection in Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dennis</namePart>
<namePart type="family">Assenmacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paloma</namePart>
<namePart type="family">Piot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katarina</namePart>
<namePart type="family">Laken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Wagner</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Digital dehumanization, although a critical issue, remains largely overlooked within the field of computational linguistics and Natural Language Processing (NLP). To our best knowledge, this work presents the most comprehensive annotated bi-lingual dataset on dehumanization, with almost 16.000 instances (44% dehumanizing) that exists today and can serve as both a training resource for machine learning models and a benchmark for evaluating future dehumanization detection techniques. Our comparison of 15 methods shows that traditional hate speech detection approaches perform poorly on dehumanization detection, particularly for implicit forms. By leveraging our dataset in few-shot and fine-tuning settings, LLMs achieve comparable performance on implicit and explicit dehumanization and substantially outperform zero-shot baselines, with average gains of 39% and 65%, respectively. However, detection accuracy remains slightly lower for mechanistic than for animalistic dehumanization, the latter being the dominant focus of prior work.</abstract>
<identifier type="citekey">assenmacher-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1958/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>41753</start>
<end>41776</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond the Explicit: A Bilingual Dataset for Dehumanization Detection in Social Media
%A Assenmacher, Dennis
%A Piot, Paloma
%A Laken, Katarina
%A Jurgens, David
%A Wagner, Claudia
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F assenmacher-etal-2026-beyond
%X Digital dehumanization, although a critical issue, remains largely overlooked within the field of computational linguistics and Natural Language Processing (NLP). To our best knowledge, this work presents the most comprehensive annotated bi-lingual dataset on dehumanization, with almost 16.000 instances (44% dehumanizing) that exists today and can serve as both a training resource for machine learning models and a benchmark for evaluating future dehumanization detection techniques. Our comparison of 15 methods shows that traditional hate speech detection approaches perform poorly on dehumanization detection, particularly for implicit forms. By leveraging our dataset in few-shot and fine-tuning settings, LLMs achieve comparable performance on implicit and explicit dehumanization and substantially outperform zero-shot baselines, with average gains of 39% and 65%, respectively. However, detection accuracy remains slightly lower for mechanistic than for animalistic dehumanization, the latter being the dominant focus of prior work.
%U https://aclanthology.org/2026.findings-emnlp.1958/
%P 41753-41776
Markdown (Informal)
[Beyond the Explicit: A Bilingual Dataset for Dehumanization Detection in Social Media](https://aclanthology.org/2026.findings-emnlp.1958/) (Assenmacher et al., Findings 2026)
ACL