@inproceedings{nozza-etal-2022-hate,
title = "{HATE}-{ITA}: Hate Speech Detection in {I}talian Social Media Text",
author = "Nozza, Debora and
Bianchi, Federico and
Attanasio, Giuseppe",
editor = "Narang, Kanika and
Mostafazadeh Davani, Aida and
Mathias, Lambert and
Vidgen, Bertie and
Talat, Zeerak",
booktitle = "Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)",
month = jul,
year = "2022",
address = "Seattle, Washington (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.woah-1.24",
doi = "10.18653/v1/2022.woah-1.24",
pages = "252--260",
abstract = "Online hate speech is a dangerous phenomenon that can (and should) be promptly counteracted properly. While Natural Language Processing supplies appropriate algorithms for trying to reach this objective, all research efforts are directed toward the English language. This strongly limits the classification power on non-English languages. In this paper, we test several learning frameworks for identifying hate speech in Italian text. We release HATE-ITA, a multi-language model trained on a large set of English data and available Italian datasets. HATE-ITA performs better than mono-lingual models and seems to adapt well also on language-specific slurs. We hope our findings will encourage the research in other mid-to-low resource communities and provide a valuable benchmarking tool for the Italian community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nozza-etal-2022-hate">
<titleInfo>
<title>HATE-ITA: Hate Speech Detection in Italian Social Media Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Bianchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Attanasio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kanika</namePart>
<namePart type="family">Narang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Mostafazadeh Davani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lambert</namePart>
<namePart type="family">Mathias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bertie</namePart>
<namePart type="family">Vidgen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Talat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Online hate speech is a dangerous phenomenon that can (and should) be promptly counteracted properly. While Natural Language Processing supplies appropriate algorithms for trying to reach this objective, all research efforts are directed toward the English language. This strongly limits the classification power on non-English languages. In this paper, we test several learning frameworks for identifying hate speech in Italian text. We release HATE-ITA, a multi-language model trained on a large set of English data and available Italian datasets. HATE-ITA performs better than mono-lingual models and seems to adapt well also on language-specific slurs. We hope our findings will encourage the research in other mid-to-low resource communities and provide a valuable benchmarking tool for the Italian community.</abstract>
<identifier type="citekey">nozza-etal-2022-hate</identifier>
<identifier type="doi">10.18653/v1/2022.woah-1.24</identifier>
<location>
<url>https://aclanthology.org/2022.woah-1.24</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>252</start>
<end>260</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HATE-ITA: Hate Speech Detection in Italian Social Media Text
%A Nozza, Debora
%A Bianchi, Federico
%A Attanasio, Giuseppe
%Y Narang, Kanika
%Y Mostafazadeh Davani, Aida
%Y Mathias, Lambert
%Y Vidgen, Bertie
%Y Talat, Zeerak
%S Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington (Hybrid)
%F nozza-etal-2022-hate
%X Online hate speech is a dangerous phenomenon that can (and should) be promptly counteracted properly. While Natural Language Processing supplies appropriate algorithms for trying to reach this objective, all research efforts are directed toward the English language. This strongly limits the classification power on non-English languages. In this paper, we test several learning frameworks for identifying hate speech in Italian text. We release HATE-ITA, a multi-language model trained on a large set of English data and available Italian datasets. HATE-ITA performs better than mono-lingual models and seems to adapt well also on language-specific slurs. We hope our findings will encourage the research in other mid-to-low resource communities and provide a valuable benchmarking tool for the Italian community.
%R 10.18653/v1/2022.woah-1.24
%U https://aclanthology.org/2022.woah-1.24
%U https://doi.org/10.18653/v1/2022.woah-1.24
%P 252-260
Markdown (Informal)
[HATE-ITA: Hate Speech Detection in Italian Social Media Text](https://aclanthology.org/2022.woah-1.24) (Nozza et al., WOAH 2022)
ACL