@inproceedings{aich-parde-2022-telling,
title = "Telling a Lie: Analyzing the Language of Information and Misinformation during Global Health Events",
author = "Aich, Ankit and
Parde, Natalie",
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-1.439",
pages = "4135--4141",
abstract = "The COVID-19 pandemic and other global health events are unfortunately excellent environments for the creation and spread of misinformation, and the language associated with health misinformation may be typified by unique patterns and linguistic markers. Allowing health misinformation to spread unchecked can have devastating ripple effects; however, detecting and stopping its spread requires careful analysis of these linguistic characteristics at scale. We analyze prior investigations focusing on health misinformation, associated datasets, and detection of misinformation during health crises. We also introduce a novel dataset designed for analyzing such phenomena, comprised of 2.8 million news articles and social media posts spanning the early 1900s to the present. Our annotation guidelines result in strong agreement between independent annotators. We describe our methods for collecting this data and follow this with a thorough analysis of the themes and linguistic features that appear in information versus misinformation. Finally, we demonstrate a proof-of-concept misinformation detection task to establish dataset validity, achieving a strong performance benchmark (accuracy = 75{\%}; F1 = 0.7).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aich-parde-2022-telling">
<titleInfo>
<title>Telling a Lie: Analyzing the Language of Information and Misinformation during Global Health Events</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankit</namePart>
<namePart type="family">Aich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Parde</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 COVID-19 pandemic and other global health events are unfortunately excellent environments for the creation and spread of misinformation, and the language associated with health misinformation may be typified by unique patterns and linguistic markers. Allowing health misinformation to spread unchecked can have devastating ripple effects; however, detecting and stopping its spread requires careful analysis of these linguistic characteristics at scale. We analyze prior investigations focusing on health misinformation, associated datasets, and detection of misinformation during health crises. We also introduce a novel dataset designed for analyzing such phenomena, comprised of 2.8 million news articles and social media posts spanning the early 1900s to the present. Our annotation guidelines result in strong agreement between independent annotators. We describe our methods for collecting this data and follow this with a thorough analysis of the themes and linguistic features that appear in information versus misinformation. Finally, we demonstrate a proof-of-concept misinformation detection task to establish dataset validity, achieving a strong performance benchmark (accuracy = 75%; F1 = 0.7).</abstract>
<identifier type="citekey">aich-parde-2022-telling</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.439</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4135</start>
<end>4141</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Telling a Lie: Analyzing the Language of Information and Misinformation during Global Health Events
%A Aich, Ankit
%A Parde, Natalie
%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 aich-parde-2022-telling
%X The COVID-19 pandemic and other global health events are unfortunately excellent environments for the creation and spread of misinformation, and the language associated with health misinformation may be typified by unique patterns and linguistic markers. Allowing health misinformation to spread unchecked can have devastating ripple effects; however, detecting and stopping its spread requires careful analysis of these linguistic characteristics at scale. We analyze prior investigations focusing on health misinformation, associated datasets, and detection of misinformation during health crises. We also introduce a novel dataset designed for analyzing such phenomena, comprised of 2.8 million news articles and social media posts spanning the early 1900s to the present. Our annotation guidelines result in strong agreement between independent annotators. We describe our methods for collecting this data and follow this with a thorough analysis of the themes and linguistic features that appear in information versus misinformation. Finally, we demonstrate a proof-of-concept misinformation detection task to establish dataset validity, achieving a strong performance benchmark (accuracy = 75%; F1 = 0.7).
%U https://aclanthology.org/2022.lrec-1.439
%P 4135-4141
Markdown (Informal)
[Telling a Lie: Analyzing the Language of Information and Misinformation during Global Health Events](https://aclanthology.org/2022.lrec-1.439) (Aich & Parde, LREC 2022)
ACL