@inproceedings{cignarella-etal-2024-queereotypes-multi,
title = "{QUEEREOTYPES}: A Multi-Source {I}talian Corpus of Stereotypes towards {LGBTQIA}+ Community Members",
author = "Cignarella, Alessandra Teresa and
Sanguinetti, Manuela and
Frenda, Simona and
Marra, Andrea and
Bosco, Cristina and
Basile, Valerio",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1176",
pages = "13429--13441",
abstract = "The paper describes a dataset composed of two sub-corpora from two different sources in Italian. The QUEEREOTYPES corpus includes social media texts regarding LGBTQIA+ individuals, behaviors, ideology and events. The texts were collected from Facebook and Twitter in 2018 and were annotated for the presence of stereotypes, and orthogonal dimensions (such as hate speech, aggressiveness, offensiveness, and irony in one sub-corpus, and stance in the other). The resource was developed by Natural Language Processing researchers together with activists from an Italian LGBTQIA+ not-for-profit organization. The creation of the dataset allows the NLP community to study stereotypes against marginalized groups, individuals and, ultimately, to develop proper tools and measures to reduce the online spread of such stereotypes. A test for the robustness of the language resource has been performed by means of 5-fold cross-validation experiments. Finally, text classification experiments have been carried out with a fine-tuned version of AlBERTo (a BERT-based model pre-trained on Italian tweets) and mBERT, obtaining good results on the task of stereotype detection, suggesting that stereotypes towards different targets might share common traits.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cignarella-etal-2024-queereotypes-multi">
<titleInfo>
<title>QUEEREOTYPES: A Multi-Source Italian Corpus of Stereotypes towards LGBTQIA+ Community Members</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alessandra</namePart>
<namePart type="given">Teresa</namePart>
<namePart type="family">Cignarella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuela</namePart>
<namePart type="family">Sanguinetti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simona</namePart>
<namePart type="family">Frenda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Marra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Bosco</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>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</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">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper describes a dataset composed of two sub-corpora from two different sources in Italian. The QUEEREOTYPES corpus includes social media texts regarding LGBTQIA+ individuals, behaviors, ideology and events. The texts were collected from Facebook and Twitter in 2018 and were annotated for the presence of stereotypes, and orthogonal dimensions (such as hate speech, aggressiveness, offensiveness, and irony in one sub-corpus, and stance in the other). The resource was developed by Natural Language Processing researchers together with activists from an Italian LGBTQIA+ not-for-profit organization. The creation of the dataset allows the NLP community to study stereotypes against marginalized groups, individuals and, ultimately, to develop proper tools and measures to reduce the online spread of such stereotypes. A test for the robustness of the language resource has been performed by means of 5-fold cross-validation experiments. Finally, text classification experiments have been carried out with a fine-tuned version of AlBERTo (a BERT-based model pre-trained on Italian tweets) and mBERT, obtaining good results on the task of stereotype detection, suggesting that stereotypes towards different targets might share common traits.</abstract>
<identifier type="citekey">cignarella-etal-2024-queereotypes-multi</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1176</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13429</start>
<end>13441</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QUEEREOTYPES: A Multi-Source Italian Corpus of Stereotypes towards LGBTQIA+ Community Members
%A Cignarella, Alessandra Teresa
%A Sanguinetti, Manuela
%A Frenda, Simona
%A Marra, Andrea
%A Bosco, Cristina
%A Basile, Valerio
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F cignarella-etal-2024-queereotypes-multi
%X The paper describes a dataset composed of two sub-corpora from two different sources in Italian. The QUEEREOTYPES corpus includes social media texts regarding LGBTQIA+ individuals, behaviors, ideology and events. The texts were collected from Facebook and Twitter in 2018 and were annotated for the presence of stereotypes, and orthogonal dimensions (such as hate speech, aggressiveness, offensiveness, and irony in one sub-corpus, and stance in the other). The resource was developed by Natural Language Processing researchers together with activists from an Italian LGBTQIA+ not-for-profit organization. The creation of the dataset allows the NLP community to study stereotypes against marginalized groups, individuals and, ultimately, to develop proper tools and measures to reduce the online spread of such stereotypes. A test for the robustness of the language resource has been performed by means of 5-fold cross-validation experiments. Finally, text classification experiments have been carried out with a fine-tuned version of AlBERTo (a BERT-based model pre-trained on Italian tweets) and mBERT, obtaining good results on the task of stereotype detection, suggesting that stereotypes towards different targets might share common traits.
%U https://aclanthology.org/2024.lrec-main.1176
%P 13429-13441
Markdown (Informal)
[QUEEREOTYPES: A Multi-Source Italian Corpus of Stereotypes towards LGBTQIA+ Community Members](https://aclanthology.org/2024.lrec-main.1176) (Cignarella et al., LREC-COLING 2024)
ACL