@inproceedings{guillen-pacho-etal-2024-vulnerable,
title = "The Vulnerable Identities Recognition Corpus ({VIRC}) for Hate Speech Analysis",
author = "Guill{\'e}n-Pacho, Ibai and
Longo, Arianna and
Stranisci, Marco Antonio and
Patti, Viviana and
Badenes-Olmedo, Carlos",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.50/",
pages = "417--424",
ISBN = "979-12-210-7060-6",
abstract = "This paper presents the Vulnerable Identities Recognition Corpus (VIRC), a novel resource designed to enhance hate speech analysis in Italian and Spanish news headlines. VIRC comprises 921 headlines, manually annotated for vulnerable identities, dangerous discourse, derogatory expressions, and entities. Our experiments reveal that large language models (LLMs) struggle significantly with the fine-grained identification of these elements, underscoring the complexity of detecting hate speech. VIRC stands out as the first resource of its kind in these languages, offering a richer annotation schema compared to existing corpora. The insights derived from VIRC can inform the development of sophisticated detection tools and the creation of policies and regulations to combat hate speech on social media, promoting a safer online environment. Future work will focus on expanding the corpus and refining annotation guidelines to further enhance its comprehensiveness and reliability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guillen-pacho-etal-2024-vulnerable">
<titleInfo>
<title>The Vulnerable Identities Recognition Corpus (VIRC) for Hate Speech Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ibai</namePart>
<namePart type="family">Guillén-Pacho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Longo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="family">Stranisci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviana</namePart>
<namePart type="family">Patti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Badenes-Olmedo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>This paper presents the Vulnerable Identities Recognition Corpus (VIRC), a novel resource designed to enhance hate speech analysis in Italian and Spanish news headlines. VIRC comprises 921 headlines, manually annotated for vulnerable identities, dangerous discourse, derogatory expressions, and entities. Our experiments reveal that large language models (LLMs) struggle significantly with the fine-grained identification of these elements, underscoring the complexity of detecting hate speech. VIRC stands out as the first resource of its kind in these languages, offering a richer annotation schema compared to existing corpora. The insights derived from VIRC can inform the development of sophisticated detection tools and the creation of policies and regulations to combat hate speech on social media, promoting a safer online environment. Future work will focus on expanding the corpus and refining annotation guidelines to further enhance its comprehensiveness and reliability.</abstract>
<identifier type="citekey">guillen-pacho-etal-2024-vulnerable</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.50/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>417</start>
<end>424</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Vulnerable Identities Recognition Corpus (VIRC) for Hate Speech Analysis
%A Guillén-Pacho, Ibai
%A Longo, Arianna
%A Stranisci, Marco Antonio
%A Patti, Viviana
%A Badenes-Olmedo, Carlos
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F guillen-pacho-etal-2024-vulnerable
%X This paper presents the Vulnerable Identities Recognition Corpus (VIRC), a novel resource designed to enhance hate speech analysis in Italian and Spanish news headlines. VIRC comprises 921 headlines, manually annotated for vulnerable identities, dangerous discourse, derogatory expressions, and entities. Our experiments reveal that large language models (LLMs) struggle significantly with the fine-grained identification of these elements, underscoring the complexity of detecting hate speech. VIRC stands out as the first resource of its kind in these languages, offering a richer annotation schema compared to existing corpora. The insights derived from VIRC can inform the development of sophisticated detection tools and the creation of policies and regulations to combat hate speech on social media, promoting a safer online environment. Future work will focus on expanding the corpus and refining annotation guidelines to further enhance its comprehensiveness and reliability.
%U https://aclanthology.org/2024.clicit-1.50/
%P 417-424
Markdown (Informal)
[The Vulnerable Identities Recognition Corpus (VIRC) for Hate Speech Analysis](https://aclanthology.org/2024.clicit-1.50/) (Guillén-Pacho et al., CLiC-it 2024)
ACL