@inproceedings{almanea-poesio-2022-armis,
title = "{A}r{MIS} - The {A}rabic Misogyny and Sexism Corpus with Annotator Subjective Disagreements",
author = "Almanea, Dina and
Poesio, Massimo",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.244/",
pages = "2282--2291",
abstract = "The use of misogynistic and sexist language has increased in recent years in social media, and is increasing in the Arabic world in reaction to reforms attempting to remove restrictions on women lives. However, there are few benchmarks for Arabic misogyny and sexism detection, and in those the annotations are in aggregated form even though misogyny and sexism judgments are found to be highly subjective. In this paper we introduce an Arabic misogyny and sexism dataset (ArMIS) characterized by providing annotations from annotators with different degree of religious beliefs, and provide evidence that such differences do result in disagreements. To the best of our knowledge, this is the first dataset to study in detail the effect of beliefs on misogyny and sexism annotation. We also discuss proof-of-concept experiments showing that a dataset in which disagreements have not been reconciled can be used to train state-of-the-art models for misogyny and sexism detection; and consider different ways in which such models could be evaluated."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almanea-poesio-2022-armis">
<titleInfo>
<title>ArMIS - The Arabic Misogyny and Sexism Corpus with Annotator Subjective Disagreements</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Almanea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Poesio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The use of misogynistic and sexist language has increased in recent years in social media, and is increasing in the Arabic world in reaction to reforms attempting to remove restrictions on women lives. However, there are few benchmarks for Arabic misogyny and sexism detection, and in those the annotations are in aggregated form even though misogyny and sexism judgments are found to be highly subjective. In this paper we introduce an Arabic misogyny and sexism dataset (ArMIS) characterized by providing annotations from annotators with different degree of religious beliefs, and provide evidence that such differences do result in disagreements. To the best of our knowledge, this is the first dataset to study in detail the effect of beliefs on misogyny and sexism annotation. We also discuss proof-of-concept experiments showing that a dataset in which disagreements have not been reconciled can be used to train state-of-the-art models for misogyny and sexism detection; and consider different ways in which such models could be evaluated.</abstract>
<identifier type="citekey">almanea-poesio-2022-armis</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.244/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2282</start>
<end>2291</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArMIS - The Arabic Misogyny and Sexism Corpus with Annotator Subjective Disagreements
%A Almanea, Dina
%A Poesio, Massimo
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F almanea-poesio-2022-armis
%X The use of misogynistic and sexist language has increased in recent years in social media, and is increasing in the Arabic world in reaction to reforms attempting to remove restrictions on women lives. However, there are few benchmarks for Arabic misogyny and sexism detection, and in those the annotations are in aggregated form even though misogyny and sexism judgments are found to be highly subjective. In this paper we introduce an Arabic misogyny and sexism dataset (ArMIS) characterized by providing annotations from annotators with different degree of religious beliefs, and provide evidence that such differences do result in disagreements. To the best of our knowledge, this is the first dataset to study in detail the effect of beliefs on misogyny and sexism annotation. We also discuss proof-of-concept experiments showing that a dataset in which disagreements have not been reconciled can be used to train state-of-the-art models for misogyny and sexism detection; and consider different ways in which such models could be evaluated.
%U https://aclanthology.org/2022.lrec-1.244/
%P 2282-2291
Markdown (Informal)
[ArMIS - The Arabic Misogyny and Sexism Corpus with Annotator Subjective Disagreements](https://aclanthology.org/2022.lrec-1.244/) (Almanea & Poesio, LREC 2022)
ACL