@inproceedings{schaefer-stede-2022-gercct,
title = "{G}er{CCT}: An Annotated Corpus for Mining Arguments in {G}erman Tweets on Climate Change",
author = "Schaefer, Robin and
Stede, Manfred",
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-1.658",
pages = "6121--6130",
abstract = "While the field of argument mining has grown notably in the last decade, research on the Twitter medium remains relatively understudied. Given the difficulty of mining arguments in tweets, recent work on creating annotated resources mainly utilized simplified annotation schemes that focus on single argument components, i.e., on claim or evidence. In this paper we strive to fill this research gap by presenting GerCCT, a new corpus of German tweets on climate change, which was annotated for a set of different argument components and properties. Additionally, we labelled sarcasm and toxic language to facilitate the development of tools for filtering out non-argumentative content. This, to the best of our knowledge, renders our corpus the first tweet resource annotated for argumentation, sarcasm and toxic language. We show that a comparatively complex annotation scheme can still yield promising inter-annotator agreement. We further present first good supervised classification results yielded by a fine-tuned BERT architecture.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schaefer-stede-2022-gercct">
<titleInfo>
<title>GerCCT: An Annotated Corpus for Mining Arguments in German Tweets on Climate Change</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Schaefer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manfred</namePart>
<namePart type="family">Stede</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>While the field of argument mining has grown notably in the last decade, research on the Twitter medium remains relatively understudied. Given the difficulty of mining arguments in tweets, recent work on creating annotated resources mainly utilized simplified annotation schemes that focus on single argument components, i.e., on claim or evidence. In this paper we strive to fill this research gap by presenting GerCCT, a new corpus of German tweets on climate change, which was annotated for a set of different argument components and properties. Additionally, we labelled sarcasm and toxic language to facilitate the development of tools for filtering out non-argumentative content. This, to the best of our knowledge, renders our corpus the first tweet resource annotated for argumentation, sarcasm and toxic language. We show that a comparatively complex annotation scheme can still yield promising inter-annotator agreement. We further present first good supervised classification results yielded by a fine-tuned BERT architecture.</abstract>
<identifier type="citekey">schaefer-stede-2022-gercct</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.658</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6121</start>
<end>6130</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GerCCT: An Annotated Corpus for Mining Arguments in German Tweets on Climate Change
%A Schaefer, Robin
%A Stede, Manfred
%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 schaefer-stede-2022-gercct
%X While the field of argument mining has grown notably in the last decade, research on the Twitter medium remains relatively understudied. Given the difficulty of mining arguments in tweets, recent work on creating annotated resources mainly utilized simplified annotation schemes that focus on single argument components, i.e., on claim or evidence. In this paper we strive to fill this research gap by presenting GerCCT, a new corpus of German tweets on climate change, which was annotated for a set of different argument components and properties. Additionally, we labelled sarcasm and toxic language to facilitate the development of tools for filtering out non-argumentative content. This, to the best of our knowledge, renders our corpus the first tweet resource annotated for argumentation, sarcasm and toxic language. We show that a comparatively complex annotation scheme can still yield promising inter-annotator agreement. We further present first good supervised classification results yielded by a fine-tuned BERT architecture.
%U https://aclanthology.org/2022.lrec-1.658
%P 6121-6130
Markdown (Informal)
[GerCCT: An Annotated Corpus for Mining Arguments in German Tweets on Climate Change](https://aclanthology.org/2022.lrec-1.658) (Schaefer & Stede, LREC 2022)
ACL