@inproceedings{davenia-etal-2026-hurtlens,
title = "{H}urt{L}ens: A Perspectivist Corpus Analysis of Hurtful Language",
author = "D{'}Avenia, Samuele and
Di Palma, Eliana and
Marchiori Manerba, Marta and
Basile, Valerio",
editor = "Dudy, Shiran and
Abercrombie, Gavin and
Basile, Valerio and
Leonardelli, Elisa and
Frenda, Simona",
booktitle = "Proceedings of the the fifth edition of {NLP}erspectives",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nlperspectives-1.5/",
doi = "10.63317/483mhsjprvmo",
pages = "44--55",
abstract = "Offensive language detection systems often rely on majority-aggregated annotations, overlooking the diversity of perspectives that shape how different communities perceive harm. In this contribution, we introduce HurtLens, a perspectivist corpus of hurtful language leveraging four disaggregated datasets which are automatically enriched through HurtLex lemmas, a multilingual resource of offensive and derogatory terms. Using mixed-effects modeling, we investigate how annotators' sociodemographic backgrounds, the presence of specific types of offensive language (through Hurtlex categories) and their interaction influence offensiveness ratings. Our analysis reveals that offensiveness ratings are influenced both by annotators' sociodemographic characteristics (particularly when considering them in intersection) and by the presence of specific types of offensive language. Additionally, we identify significant interaction effects showing that different demographic groups vary in their sensitivity to texts containing particular types of offensive language."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="davenia-etal-2026-hurtlens">
<titleInfo>
<title>HurtLens: A Perspectivist Corpus Analysis of Hurtful Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samuele</namePart>
<namePart type="family">D’Avenia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eliana</namePart>
<namePart type="family">Di Palma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Marchiori Manerba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the the fifth edition of NLPerspectives</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shiran</namePart>
<namePart type="family">Dudy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gavin</namePart>
<namePart type="family">Abercrombie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Leonardelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simona</namePart>
<namePart type="family">Frenda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Offensive language detection systems often rely on majority-aggregated annotations, overlooking the diversity of perspectives that shape how different communities perceive harm. In this contribution, we introduce HurtLens, a perspectivist corpus of hurtful language leveraging four disaggregated datasets which are automatically enriched through HurtLex lemmas, a multilingual resource of offensive and derogatory terms. Using mixed-effects modeling, we investigate how annotators’ sociodemographic backgrounds, the presence of specific types of offensive language (through Hurtlex categories) and their interaction influence offensiveness ratings. Our analysis reveals that offensiveness ratings are influenced both by annotators’ sociodemographic characteristics (particularly when considering them in intersection) and by the presence of specific types of offensive language. Additionally, we identify significant interaction effects showing that different demographic groups vary in their sensitivity to texts containing particular types of offensive language.</abstract>
<identifier type="citekey">davenia-etal-2026-hurtlens</identifier>
<identifier type="doi">10.63317/483mhsjprvmo</identifier>
<location>
<url>https://aclanthology.org/2026.nlperspectives-1.5/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>44</start>
<end>55</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HurtLens: A Perspectivist Corpus Analysis of Hurtful Language
%A D’Avenia, Samuele
%A Di Palma, Eliana
%A Marchiori Manerba, Marta
%A Basile, Valerio
%Y Dudy, Shiran
%Y Abercrombie, Gavin
%Y Basile, Valerio
%Y Leonardelli, Elisa
%Y Frenda, Simona
%S Proceedings of the the fifth edition of NLPerspectives
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F davenia-etal-2026-hurtlens
%X Offensive language detection systems often rely on majority-aggregated annotations, overlooking the diversity of perspectives that shape how different communities perceive harm. In this contribution, we introduce HurtLens, a perspectivist corpus of hurtful language leveraging four disaggregated datasets which are automatically enriched through HurtLex lemmas, a multilingual resource of offensive and derogatory terms. Using mixed-effects modeling, we investigate how annotators’ sociodemographic backgrounds, the presence of specific types of offensive language (through Hurtlex categories) and their interaction influence offensiveness ratings. Our analysis reveals that offensiveness ratings are influenced both by annotators’ sociodemographic characteristics (particularly when considering them in intersection) and by the presence of specific types of offensive language. Additionally, we identify significant interaction effects showing that different demographic groups vary in their sensitivity to texts containing particular types of offensive language.
%R 10.63317/483mhsjprvmo
%U https://aclanthology.org/2026.nlperspectives-1.5/
%U https://doi.org/10.63317/483mhsjprvmo
%P 44-55
Markdown (Informal)
[HurtLens: A Perspectivist Corpus Analysis of Hurtful Language](https://aclanthology.org/2026.nlperspectives-1.5/) (D’Avenia et al., NLPerspectives 2026)
ACL