<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-03380543</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-17T17:57:05+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Combating the Infodemic: A Chinese Infodemic Dataset for Misinformation Identification</title>
            <author role="aut">
              <persName>
                <forename type="first">Jia</forename>
                <surname>Luo</surname>
              </persName>
              <idno type="idhal" notation="numeric">786020</idno>
              <idno type="halauthorid" notation="string">1309593-786020</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3914-8865</idno>
              <affiliation ref="#struct-334437"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Rui</forename>
                <surname>Xue</surname>
              </persName>
              <idno type="idhal" notation="numeric">777223</idno>
              <idno type="halauthorid" notation="string">827619-777223</idno>
              <idno type="IDREF">https://www.idref.fr/200294946</idno>
              <affiliation ref="#struct-334437"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jinglu</forename>
                <surname>Hu</surname>
              </persName>
              <idno type="halauthorid">1560066-0</idno>
              <affiliation ref="#struct-168249"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Didier</forename>
                <surname>El Baz</surname>
              </persName>
              <email type="md5">69018d8e5c7e7e5f8ec67ebd0f862044</email>
              <email type="domain">laas.fr</email>
              <idno type="idhal" notation="string">didier-el-baz</idno>
              <idno type="idhal" notation="numeric">3899</idno>
              <idno type="halauthorid" notation="string">14943-3899</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0427-0692</idno>
              <idno type="IDREF">https://www.idref.fr/05072620X</idno>
              <orgName ref="#struct-391004"/>
              <affiliation ref="#struct-388967"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Didier</forename>
                <surname>EL BAZ</surname>
              </persName>
              <email type="md5">69018d8e5c7e7e5f8ec67ebd0f862044</email>
              <email type="domain">laas.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-10-15 16:03:00</date>
              <date type="whenModified">2026-02-12 16:54:04</date>
              <date type="whenReleased">2021-10-18 09:28:14</date>
              <date type="whenProduced">2021-09</date>
              <date type="whenEndEmbargoed">2021-10-15</date>
              <ref type="file" target="https://laas.hal.science/hal-03380543v1/document">
                <date notBefore="2021-10-15"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://laas.hal.science/hal-03380543v1/file/Infodemic.pdf" id="file-3380543-2969118">
                <date notBefore="2021-10-15"/>
              </ref>
              <ref type="externalLink" target="https://www.mdpi.com/2227-9032/9/9/1094/pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="314810">
                <persName>
                  <forename>Didier</forename>
                  <surname>EL BAZ</surname>
                </persName>
                <email type="md5">69018d8e5c7e7e5f8ec67ebd0f862044</email>
                <email type="domain">laas.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03380543</idno>
            <idno type="halUri">https://laas.hal.science/hal-03380543</idno>
            <idno type="halBibtex">luo:hal-03380543</idno>
            <idno type="halRefHtml">&lt;i&gt;Healthcare&lt;/i&gt;, 2021, 9 (9), pp.1094. &lt;a target="_blank" href="https://dx.doi.org/10.3390/healthcare9091094"&gt;&amp;#x27E8;10.3390/healthcare9091094&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Healthcare, 2021, 9 (9), pp.1094. &amp;#x27E8;10.3390/healthcare9091094&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3380543-2969118"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-TLSE2">Université Toulouse 2</idno>
            <idno type="stamp" n="UNIV-TLSE3">Université de Toulouse</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INSA-TOULOUSE">Institut National des Sciences Appliquées de Toulouse</idno>
            <idno type="stamp" n="LAAS">Laboratoire d'analyse et d'architecture des systèmes</idno>
            <idno type="stamp" n="LAAS-SARA" corresp="LAAS-RISC">Équipe Services et Architectures pour Réseaux Avancés</idno>
            <idno type="stamp" n="UT1-CAPITOLE">Université Toulouse 1 Capitole</idno>
            <idno type="stamp" n="LAAS-RESEAUX-ET-COMMUNICATIONS" corresp="LAAS">LAAS-Réseaux et Communications</idno>
            <idno type="stamp" n="INSA-GROUPE">Groupe INSA</idno>
            <idno type="stamp" n="LAAS-RISC" corresp="LAAS">Réseaux, Informatique, Systèmes de Confiance</idno>
            <idno type="stamp" n="TOULOUSE-INP">Toulouse - INP</idno>
            <idno type="stamp" n="UNIV-UT3">Université Toulouse 3</idno>
            <idno type="stamp" n="UT3-INP">Université de Toulouse / Toulouse INP</idno>
            <idno type="stamp" n="UT3-TOULOUSEINP">Université de Toulouse / Toulouse INP</idno>
            <idno type="stamp" n="TEST7-HALCNRS">test 7 du portail hal cnrs</idno>
          </seriesStmt>
          <notesStmt>
            <note type="commentary">This article belongs to the Special Issue Novel Coronavirus (SARS-CoV-2) Outbreak: Epidemiology, Research and Implications for Public Health</note>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Combating the Infodemic: A Chinese Infodemic Dataset for Misinformation Identification</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Jia</forename>
                    <surname>Luo</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">786020</idno>
                  <idno type="halauthorid" notation="string">1309593-786020</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3914-8865</idno>
                  <affiliation ref="#struct-334437"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Rui</forename>
                    <surname>Xue</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">777223</idno>
                  <idno type="halauthorid" notation="string">827619-777223</idno>
                  <idno type="IDREF">https://www.idref.fr/200294946</idno>
                  <affiliation ref="#struct-334437"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jinglu</forename>
                    <surname>Hu</surname>
                  </persName>
                  <idno type="halauthorid">1560066-0</idno>
                  <affiliation ref="#struct-168249"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Didier</forename>
                    <surname>El Baz</surname>
                  </persName>
                  <email type="md5">69018d8e5c7e7e5f8ec67ebd0f862044</email>
                  <email type="domain">laas.fr</email>
                  <idno type="idhal" notation="string">didier-el-baz</idno>
                  <idno type="idhal" notation="numeric">3899</idno>
                  <idno type="halauthorid" notation="string">14943-3899</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0427-0692</idno>
                  <idno type="IDREF">https://www.idref.fr/05072620X</idno>
                  <orgName ref="#struct-391004"/>
                  <affiliation ref="#struct-388967"/>
                </author>
              </analytic>
              <monogr>
                <idno type="localRef">Rapport LAAS n° 21312</idno>
                <idno type="halJournalId" status="VALID">116894</idno>
                <idno type="issn">2227-9032</idno>
                <title level="j">Healthcare</title>
                <imprint>
                  <publisher>MDPI</publisher>
                  <biblScope unit="volume">9</biblScope>
                  <biblScope unit="issue">9</biblScope>
                  <biblScope unit="pp">1094</biblScope>
                  <date type="datePub">2021-09</date>
                  <date type="dateEpub">2021-08</date>
                </imprint>
              </monogr>
              <idno type="doi">10.3390/healthcare9091094</idno>
              <ref target="https://www.dropbox.com/sh/praltzebemotd2r/AABmc1IxaKG_uZnEUN5beJFwa?dl=0" type="seeAlso"/>
              <ref type="publisher">https://www.mdpi.com/2227-9032/9/9/1094</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">deep learning</term>
                <term xml:lang="en">misinformation identification</term>
                <term xml:lang="en">infodemic data</term>
                <term xml:lang="en">COVID-19</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-si">Computer Science [cs]/Social and Information Networks [cs.SI]</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-dc">Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC]</classCode>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Misinformation posted on social media during COVID-19 is one main example of infodemic data. This phenomenon was prominent in China when COVID-19 happened at the beginning. While a lot of data can be collected from various social media platforms, publicly available infodemic detection data remains rare and is not easy to construct manually. Therefore, instead of developing techniques for infodemic detection, this paper aims at constructing a Chinese infodemic dataset, “infodemic 2019”, by collecting widely spread Chinese infodemic during the COVID-19 outbreak. Each record is labeled as true, false or questionable. After a four-time adjustment, the original imbalanced dataset is converted into a balanced dataset by exploring the properties of the collected records. The final labels achieve high intercoder reliability with healthcare workers’ annotations and the high-frequency words show a strong relationship between the proposed dataset and pandemic diseases. Finally, numerical experiments are carried out with RNN, CNN and fastText. All of them achieve reasonable performance and present baselines for future works.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-334437" status="VALID">
          <idno type="ISNI">0000 0000 9040 3743</idno>
          <idno type="ROR">https://ror.org/037b1pp87</idno>
          <orgName>Beijing University of Technology</orgName>
          <orgName type="acronym">BJUT</orgName>
          <desc>
            <address>
              <addrLine>Beijing 100124</addrLine>
              <country key="CN"/>
            </address>
            <ref type="url">https://english.bjut.edu.cn</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-168249" status="VALID">
          <idno type="ISNI">0000 0001 2158 5974</idno>
          <orgName>Waseda University [Tokyo]</orgName>
          <desc>
            <address>
              <addrLine>1-104 Totsukamachi, Shinjuku-ku, Tokyo, 169-8050</addrLine>
              <country key="JP"/>
            </address>
            <ref type="url">https://www.waseda.jp/top/en</ref>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-388967" status="OLD">
          <orgName>Équipe Services et Architectures pour Réseaux Avancés</orgName>
          <orgName type="acronym">LAAS-SARA</orgName>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.laas.fr/public/fr/sara</ref>
          </desc>
          <listRelation>
            <relation active="#struct-459" type="direct"/>
            <relation active="#struct-81148" type="indirect"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116255" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="indirect"/>
            <relation active="#struct-217752" type="indirect"/>
            <relation name="UPR8001" active="#struct-441569" type="indirect"/>
            <relation active="#struct-448187" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-459" status="OLD">
          <idno type="IdRef">199278792</idno>
          <idno type="ISNI">0000 0001 2188 216X </idno>
          <idno type="RNSR">199517454Y</idno>
          <idno type="ROR">https://ror.org/03vcm6439</idno>
          <orgName>Laboratoire d'analyse et d'architecture des systèmes</orgName>
          <orgName type="acronym">LAAS</orgName>
          <date type="start">1968-01-01</date>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>7 Av du colonel Roche 31077 TOULOUSE CEDEX 4</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.laas.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-81148" type="direct"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116255" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-217752" type="direct"/>
            <relation name="UPR8001" active="#struct-441569" type="direct"/>
            <relation active="#struct-448187" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-81148" status="VALID">
          <idno type="IdRef">026404354</idno>
          <idno type="ISNI">0000000121902837</idno>
          <idno type="ROR">https://ror.org/0443n9e75</idno>
          <orgName>Université Toulouse Capitole</orgName>
          <orgName type="acronym">UT Capitole</orgName>
          <date type="start">1970-01-01</date>
          <desc>
            <address>
              <addrLine>2 rue du Doyen-Gabriel-Marty - 31042 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ut-capitole.fr/</ref>
          </desc>
          <listRelation>
            <relation name="443875" active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-443875" status="VALID">
          <idno type="ROR">https://ror.org/017tgbk05</idno>
          <orgName>Communauté d'universités et établissements de Toulouse</orgName>
          <orgName type="acronym">Comue de Toulouse</orgName>
          <desc>
            <address>
              <addrLine>41 Allée Jules Guesde, 31000 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-toulouse.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-116255" status="VALID">
          <idno type="IdRef">026388766</idno>
          <idno type="ISNI">0000 0001 2286 8343</idno>
          <idno type="ROR">https://ror.org/01h8pf755</idno>
          <idno type="Wikidata">Q858979</idno>
          <orgName>Institut National des Sciences Appliquées - Toulouse</orgName>
          <orgName type="acronym">INSA Toulouse</orgName>
          <date type="start">1963-10-21</date>
          <desc>
            <address>
              <addrLine>135, avenue de Rangueil - 31077 Toulouse cedex 4</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-toulouse.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301232" type="direct"/>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301232" status="VALID">
          <idno type="IdRef">162105150</idno>
          <orgName>Institut National des Sciences Appliquées</orgName>
          <orgName type="acronym">INSA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-116256" status="VALID">
          <idno type="IdRef">026403994</idno>
          <idno type="ROR">https://ror.org/04ezk3x31</idno>
          <orgName>Université Toulouse - Jean Jaurès</orgName>
          <orgName type="acronym">UT2J</orgName>
          <date type="start">1971-01-01</date>
          <desc>
            <address>
              <addrLine>5 allées Antonio Machado - 31058 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tlse2.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-217752" status="OLD">
          <idno type="IdRef">026404672</idno>
          <idno type="ISNI">0000000121617331</idno>
          <idno type="ROR">https://ror.org/02v6kpv12</idno>
          <idno type="Wikidata">Q1273188</idno>
          <orgName>Université Toulouse III - Paul Sabatier</orgName>
          <orgName type="acronym">UT3</orgName>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>118 route de Narbonne - 31062 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tlse3.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-448187" status="VALID">
          <idno type="IdRef">026388820</idno>
          <idno type="ISNI">0000000121766169</idno>
          <idno type="ROR">https://ror.org/033p9g875</idno>
          <orgName>Institut National Polytechnique (Toulouse)</orgName>
          <orgName type="acronym">Toulouse INP</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.inp-toulouse.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>