@inproceedings{vasquez-etal-2023-homo,
title = "{HOMO}-{MEX}: A {M}exican {S}panish Annotated Corpus for {LGBT}+phobia Detection on {T}witter",
author = "V{\'a}squez, Juan and
Andersen, Scott and
Bel-enguix, Gemma and
G{\'o}mez-adorno, Helena and
Ojeda-trueba, Sergio-luis",
editor = {Chung, Yi-ling and
R{{\textbackslash}"ottger}, Paul and
Nozza, Debora and
Talat, Zeerak and
Mostafazadeh Davani, Aida},
booktitle = "The 7th Workshop on Online Abuse and Harms (WOAH)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.woah-1.20",
doi = "10.18653/v1/2023.woah-1.20",
pages = "202--214",
abstract = "In the past few years, the NLP community has actively worked on detecting LGBT+Phobia in online spaces, using textual data publicly available Most of these are for the English language and its variants since it is the most studied language by the NLP community. Nevertheless, efforts towards creating corpora in other languages are active worldwide. Despite this, the Spanish language is an understudied language regarding digital LGBT+Phobia. The only corpus we found in the literature was for the Peninsular Spanish dialects, which use LGBT+phobic terms different than those in the Mexican dialect. For this reason, we present Homo-MEX, a novel corpus for detecting LGBT+Phobia in Mexican Spanish. In this paper, we describe our data-gathering and annotation process. Also, we present a classification benchmark using various traditional machine learning algorithms and two pre-trained deep learning models to showcase our corpus classification potential.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vasquez-etal-2023-homo">
<titleInfo>
<title>HOMO-MEX: A Mexican Spanish Annotated Corpus for LGBT+phobia Detection on Twitter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Vásquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Andersen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gemma</namePart>
<namePart type="family">Bel-enguix</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gómez-adorno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergio-luis</namePart>
<namePart type="family">Ojeda-trueba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The 7th Workshop on Online Abuse and Harms (WOAH)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi-ling</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">R\textbackslash”ottger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</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>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Mostafazadeh Davani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the past few years, the NLP community has actively worked on detecting LGBT+Phobia in online spaces, using textual data publicly available Most of these are for the English language and its variants since it is the most studied language by the NLP community. Nevertheless, efforts towards creating corpora in other languages are active worldwide. Despite this, the Spanish language is an understudied language regarding digital LGBT+Phobia. The only corpus we found in the literature was for the Peninsular Spanish dialects, which use LGBT+phobic terms different than those in the Mexican dialect. For this reason, we present Homo-MEX, a novel corpus for detecting LGBT+Phobia in Mexican Spanish. In this paper, we describe our data-gathering and annotation process. Also, we present a classification benchmark using various traditional machine learning algorithms and two pre-trained deep learning models to showcase our corpus classification potential.</abstract>
<identifier type="citekey">vasquez-etal-2023-homo</identifier>
<identifier type="doi">10.18653/v1/2023.woah-1.20</identifier>
<location>
<url>https://aclanthology.org/2023.woah-1.20</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>202</start>
<end>214</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HOMO-MEX: A Mexican Spanish Annotated Corpus for LGBT+phobia Detection on Twitter
%A Vásquez, Juan
%A Andersen, Scott
%A Bel-enguix, Gemma
%A Gómez-adorno, Helena
%A Ojeda-trueba, Sergio-luis
%Y Chung, Yi-ling
%Y R\textbackslash”ottger, Paul
%Y Nozza, Debora
%Y Talat, Zeerak
%Y Mostafazadeh Davani, Aida
%S The 7th Workshop on Online Abuse and Harms (WOAH)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F vasquez-etal-2023-homo
%X In the past few years, the NLP community has actively worked on detecting LGBT+Phobia in online spaces, using textual data publicly available Most of these are for the English language and its variants since it is the most studied language by the NLP community. Nevertheless, efforts towards creating corpora in other languages are active worldwide. Despite this, the Spanish language is an understudied language regarding digital LGBT+Phobia. The only corpus we found in the literature was for the Peninsular Spanish dialects, which use LGBT+phobic terms different than those in the Mexican dialect. For this reason, we present Homo-MEX, a novel corpus for detecting LGBT+Phobia in Mexican Spanish. In this paper, we describe our data-gathering and annotation process. Also, we present a classification benchmark using various traditional machine learning algorithms and two pre-trained deep learning models to showcase our corpus classification potential.
%R 10.18653/v1/2023.woah-1.20
%U https://aclanthology.org/2023.woah-1.20
%U https://doi.org/10.18653/v1/2023.woah-1.20
%P 202-214
Markdown (Informal)
[HOMO-MEX: A Mexican Spanish Annotated Corpus for LGBT+phobia Detection on Twitter](https://aclanthology.org/2023.woah-1.20) (Vásquez et al., WOAH 2023)
ACL