@inproceedings{hoefels-etal-2022-coroseof,
title = "{C}o{R}o{S}e{O}f - An Annotated Corpus of {R}omanian Sexist and Offensive Tweets",
author = {Hoefels, Diana Constantina and
{\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i} and
M{\u{a}}droane, Irina Diana},
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-1.243/",
pages = "2269--2281",
abstract = "This paper introduces CoRoSeOf, a large corpus of Romanian social media manually annotated for sexist and offensive language. We describe the annotation process of the corpus, provide initial analyses, and baseline classification results for sexism detection on this data set. The resulting corpus contains 39 245 tweets, annotated by multiple annotators (with an agreement rate of Fleiss'{\ensuremath{\kappa}}= 0.45), following the sexist label set of a recent study. The automatic sexism detection yields scores similar to some of the earlier studies (macro averaged F1 score of 83.07{\%} on binary classification task). We release the corpus with a permissive license."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoefels-etal-2022-coroseof">
<titleInfo>
<title>CoRoSeOf - An Annotated Corpus of Romanian Sexist and Offensive Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="given">Constantina</namePart>
<namePart type="family">Hoefels</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Çağrı</namePart>
<namePart type="family">Çöltekin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="given">Diana</namePart>
<namePart type="family">Mădroane</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>This paper introduces CoRoSeOf, a large corpus of Romanian social media manually annotated for sexist and offensive language. We describe the annotation process of the corpus, provide initial analyses, and baseline classification results for sexism detection on this data set. The resulting corpus contains 39 245 tweets, annotated by multiple annotators (with an agreement rate of Fleiss’\ensuremathąppa= 0.45), following the sexist label set of a recent study. The automatic sexism detection yields scores similar to some of the earlier studies (macro averaged F1 score of 83.07% on binary classification task). We release the corpus with a permissive license.</abstract>
<identifier type="citekey">hoefels-etal-2022-coroseof</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.243/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2269</start>
<end>2281</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoRoSeOf - An Annotated Corpus of Romanian Sexist and Offensive Tweets
%A Hoefels, Diana Constantina
%A Çöltekin, Çağrı
%A Mădroane, Irina Diana
%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 hoefels-etal-2022-coroseof
%X This paper introduces CoRoSeOf, a large corpus of Romanian social media manually annotated for sexist and offensive language. We describe the annotation process of the corpus, provide initial analyses, and baseline classification results for sexism detection on this data set. The resulting corpus contains 39 245 tweets, annotated by multiple annotators (with an agreement rate of Fleiss’\ensuremathąppa= 0.45), following the sexist label set of a recent study. The automatic sexism detection yields scores similar to some of the earlier studies (macro averaged F1 score of 83.07% on binary classification task). We release the corpus with a permissive license.
%U https://aclanthology.org/2022.lrec-1.243/
%P 2269-2281
Markdown (Informal)
[CoRoSeOf - An Annotated Corpus of Romanian Sexist and Offensive Tweets](https://aclanthology.org/2022.lrec-1.243/) (Hoefels et al., LREC 2022)
ACL