@inproceedings{mohr-etal-2022-covert,
title = "{C}o{VERT}: A Corpus of Fact-checked Biomedical {COVID}-19 Tweets",
author = {Mohr, Isabelle and
W{\"u}hrl, Amelie and
Klinger, Roman},
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-1.26",
pages = "244--257",
abstract = "During the first two years of the COVID-19 pandemic, large volumes of biomedical information concerning this new disease have been published on social media. Some of this information can pose a real danger, particularly when false information is shared, for instance recommendations how to treat diseases without professional medical advice. Therefore, automatic fact-checking resources and systems developed specifically for medical domain are crucial. While existing fact-checking resources cover COVID-19 related information in news or quantify the amount of misinformation in tweets, there is no dataset providing fact-checked COVID-19 related Twitter posts with detailed annotations for biomedical entities, relations and relevant evidence. We contribute CoVERT, a fact-checked corpus of tweets with a focus on the domain of biomedicine and COVID-19 related (mis)information. The corpus consists of 300 tweets, each annotated with named entities and relations. We employ a novel crowdsourcing methodology to annotate all tweets with fact-checking labels and supporting evidence, which crowdworkers search for online. This methodology results in substantial inter-annotator agreement. Furthermore, we use the retrieved evidence extracts as part of a fact-checking pipeline, finding that the real-world evidence is more useful than the knowledge directly available in pretrained language models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohr-etal-2022-covert">
<titleInfo>
<title>CoVERT: A Corpus of Fact-checked Biomedical COVID-19 Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Mohr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amelie</namePart>
<namePart type="family">Wührl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</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>During the first two years of the COVID-19 pandemic, large volumes of biomedical information concerning this new disease have been published on social media. Some of this information can pose a real danger, particularly when false information is shared, for instance recommendations how to treat diseases without professional medical advice. Therefore, automatic fact-checking resources and systems developed specifically for medical domain are crucial. While existing fact-checking resources cover COVID-19 related information in news or quantify the amount of misinformation in tweets, there is no dataset providing fact-checked COVID-19 related Twitter posts with detailed annotations for biomedical entities, relations and relevant evidence. We contribute CoVERT, a fact-checked corpus of tweets with a focus on the domain of biomedicine and COVID-19 related (mis)information. The corpus consists of 300 tweets, each annotated with named entities and relations. We employ a novel crowdsourcing methodology to annotate all tweets with fact-checking labels and supporting evidence, which crowdworkers search for online. This methodology results in substantial inter-annotator agreement. Furthermore, we use the retrieved evidence extracts as part of a fact-checking pipeline, finding that the real-world evidence is more useful than the knowledge directly available in pretrained language models.</abstract>
<identifier type="citekey">mohr-etal-2022-covert</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.26</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>244</start>
<end>257</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoVERT: A Corpus of Fact-checked Biomedical COVID-19 Tweets
%A Mohr, Isabelle
%A Wührl, Amelie
%A Klinger, Roman
%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 mohr-etal-2022-covert
%X During the first two years of the COVID-19 pandemic, large volumes of biomedical information concerning this new disease have been published on social media. Some of this information can pose a real danger, particularly when false information is shared, for instance recommendations how to treat diseases without professional medical advice. Therefore, automatic fact-checking resources and systems developed specifically for medical domain are crucial. While existing fact-checking resources cover COVID-19 related information in news or quantify the amount of misinformation in tweets, there is no dataset providing fact-checked COVID-19 related Twitter posts with detailed annotations for biomedical entities, relations and relevant evidence. We contribute CoVERT, a fact-checked corpus of tweets with a focus on the domain of biomedicine and COVID-19 related (mis)information. The corpus consists of 300 tweets, each annotated with named entities and relations. We employ a novel crowdsourcing methodology to annotate all tweets with fact-checking labels and supporting evidence, which crowdworkers search for online. This methodology results in substantial inter-annotator agreement. Furthermore, we use the retrieved evidence extracts as part of a fact-checking pipeline, finding that the real-world evidence is more useful than the knowledge directly available in pretrained language models.
%U https://aclanthology.org/2022.lrec-1.26
%P 244-257
Markdown (Informal)
[CoVERT: A Corpus of Fact-checked Biomedical COVID-19 Tweets](https://aclanthology.org/2022.lrec-1.26) (Mohr et al., LREC 2022)
ACL