<?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-03947820</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="2026-05-17T03:02:11+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A French Corpus for Event Detection on Twitter</title>
            <author role="aut">
              <persName>
                <forename type="first">Béatrice</forename>
                <surname>Mazoyer</surname>
              </persName>
              <email type="md5">e265a05c3d0c93843c825b0b0cb751b5</email>
              <email type="domain">sciencespo.fr</email>
              <idno type="idhal" notation="string">beatrice-mazoyer</idno>
              <idno type="idhal" notation="numeric">178192</idno>
              <idno type="halauthorid" notation="string">46596-178192</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4074-2976</idno>
              <idno type="IDREF">https://www.idref.fr/250144468</idno>
              <affiliation ref="#struct-394361"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Julia</forename>
                <surname>Cagé</surname>
              </persName>
              <email type="md5">e6abfe7d59e4e925d02979e4d2f1ac56</email>
              <email type="domain">sciences-po.org</email>
              <ptr type="url" target="https://juliacage.com/"/>
              <idno type="idhal" notation="string">julia-cage</idno>
              <idno type="idhal" notation="numeric">1101763</idno>
              <idno type="halauthorid" notation="string">2177727-1101763</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/AAA-1522-2019</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-7085-5774</idno>
              <idno type="IDREF">https://www.idref.fr/160569524</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/AAA-1522-2019</idno>
              <affiliation ref="#struct-226874"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Nicolas</forename>
                <surname>Hervé</surname>
              </persName>
              <email type="md5">011790117311eb662f90698ede6eb84a</email>
              <email type="domain">ina.fr</email>
              <idno type="idhal" notation="string">nherve75</idno>
              <idno type="idhal" notation="numeric">1217619</idno>
              <idno type="halauthorid" notation="string">121388-1217619</idno>
              <affiliation ref="#struct-300215"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Céline</forename>
                <surname>Hudelot</surname>
              </persName>
              <email type="md5">f47c8e3cb17a2bf7d43f2c152bb86885</email>
              <email type="domain">centralesupelec.fr</email>
              <idno type="idhal" notation="string">celine-hudelot</idno>
              <idno type="idhal" notation="numeric">20877</idno>
              <idno type="halauthorid" notation="string">30850-20877</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3849-4133</idno>
              <idno type="ARXIV">https://arxiv.org/a/hudelot_c_1</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=gFlAh6MAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/113366744</idno>
              <affiliation ref="#struct-1042590"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Melissa</forename>
                <surname>Mundell</surname>
              </persName>
              <email type="md5">c85913c7751c142b289de0b5c7e37e87</email>
              <email type="domain">sciencespo.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-01-19 19:14:10</date>
              <date type="whenModified">2024-07-16 11:56:20</date>
              <date type="whenReleased">2023-01-27 15:33:13</date>
              <date type="whenProduced">2020</date>
              <date type="whenEndEmbargoed">2023-01-19</date>
              <ref type="file" target="https://sciencespo.hal.science/hal-03947820v1/document">
                <date notBefore="2023-01-19"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://sciencespo.hal.science/hal-03947820v1/file/2020_mazoyer_cage_herve_hudelot_a_french_corpus_for_event_detection_on_twitter.pdf" id="file-3947820-3448650">
                <date notBefore="2023-01-19"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1077673">
                <persName>
                  <forename>Melissa</forename>
                  <surname>Mundell</surname>
                </persName>
                <email type="md5">c85913c7751c142b289de0b5c7e37e87</email>
                <email type="domain">sciencespo.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03947820</idno>
            <idno type="halUri">https://sciencespo.hal.science/hal-03947820</idno>
            <idno type="halBibtex">mazoyer:hal-03947820</idno>
            <idno type="halRefHtml">&lt;i&gt;Twelfth Language Resources and Evaluation Conference&lt;/i&gt;, 2020, Marseille, France. pp.6220-6227</idno>
            <idno type="halRef">Twelfth Language Resources and Evaluation Conference, 2020, Marseille, France. pp.6220-6227</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by-nc/4.0/">CC BY-NC 4.0 - Attribution - Non-commercial use<ref corresp="#file-3947820-3448650"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SHS">Sciences de l'Homme et de la Société</idno>
            <idno type="stamp" n="SCIENCESPO">Sciences Po</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="AO-ECONOMIE">Archives ouvertes de l'Economie</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="MICS">Mathématiques et Informatique pour la Complexité et les Systèmes</idno>
            <idno type="stamp" n="USPC">Université Sorbonne Paris Cité</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="GS-COMPUTER-SCIENCE">Graduate School Computer Science</idno>
            <idno type="stamp" n="HUB-IA">Hub Intelligence Artificielle de CentraleSupélec</idno>
            <idno type="stamp" n="MEDIALAB" corresp="SCIENCESPO">Les publications du medialab</idno>
            <idno type="stamp" n="ECON-SCPO" corresp="SCIENCESPO">Les publications du Département d'économie de Sciences Po</idno>
            <idno type="stamp" n="SCPO_OA" corresp="SCIENCESPO">Sciences Po Open Access</idno>
            <idno type="stamp" n="SCPO-REPEC" corresp="SCIENCESPO">Publications de Sciences Po en économie</idno>
          </seriesStmt>
          <notesStmt>
            <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>
            <note type="proceedings" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">A French Corpus for Event Detection on Twitter</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Béatrice</forename>
                    <surname>Mazoyer</surname>
                  </persName>
                  <email type="md5">e265a05c3d0c93843c825b0b0cb751b5</email>
                  <email type="domain">sciencespo.fr</email>
                  <idno type="idhal" notation="string">beatrice-mazoyer</idno>
                  <idno type="idhal" notation="numeric">178192</idno>
                  <idno type="halauthorid" notation="string">46596-178192</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4074-2976</idno>
                  <idno type="IDREF">https://www.idref.fr/250144468</idno>
                  <affiliation ref="#struct-394361"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Julia</forename>
                    <surname>Cagé</surname>
                  </persName>
                  <email type="md5">e6abfe7d59e4e925d02979e4d2f1ac56</email>
                  <email type="domain">sciences-po.org</email>
                  <ptr type="url" target="https://juliacage.com/"/>
                  <idno type="idhal" notation="string">julia-cage</idno>
                  <idno type="idhal" notation="numeric">1101763</idno>
                  <idno type="halauthorid" notation="string">2177727-1101763</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/AAA-1522-2019</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-7085-5774</idno>
                  <idno type="IDREF">https://www.idref.fr/160569524</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/AAA-1522-2019</idno>
                  <affiliation ref="#struct-226874"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Nicolas</forename>
                    <surname>Hervé</surname>
                  </persName>
                  <email type="md5">011790117311eb662f90698ede6eb84a</email>
                  <email type="domain">ina.fr</email>
                  <idno type="idhal" notation="string">nherve75</idno>
                  <idno type="idhal" notation="numeric">1217619</idno>
                  <idno type="halauthorid" notation="string">121388-1217619</idno>
                  <affiliation ref="#struct-300215"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Céline</forename>
                    <surname>Hudelot</surname>
                  </persName>
                  <email type="md5">f47c8e3cb17a2bf7d43f2c152bb86885</email>
                  <email type="domain">centralesupelec.fr</email>
                  <idno type="idhal" notation="string">celine-hudelot</idno>
                  <idno type="idhal" notation="numeric">20877</idno>
                  <idno type="halauthorid" notation="string">30850-20877</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3849-4133</idno>
                  <idno type="ARXIV">https://arxiv.org/a/hudelot_c_1</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=gFlAh6MAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/113366744</idno>
                  <affiliation ref="#struct-1042590"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Twelfth Language Resources and Evaluation Conference</title>
                  <date type="start">2020</date>
                  <date type="end">2020</date>
                  <settlement>Marseille</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <publisher>European Language Resources Association (ELRA)</publisher>
                  <pubPlace>Marseille</pubPlace>
                  <biblScope unit="pp">6220–6227</biblScope>
                  <date type="datePub">2020-05</date>
                </imprint>
              </monogr>
              <ref target="https://aclanthology.org/2020.lrec-1.763" type="seeAlso"/>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Natural Language Processing</term>
                <term xml:lang="en">Twitter</term>
                <term xml:lang="en">Topic Detection and Tracking</term>
                <term xml:lang="en">Event detection</term>
                <term xml:lang="en">Dataset</term>
                <term xml:lang="en">French</term>
              </keywords>
              <classCode scheme="halDomain" n="shs.eco">Humanities and Social Sciences/Economics and Finance</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>We present Event2018, a corpus annotated for event detection tasks, consisting of 38 million tweets in French (retweets excluded) including more than 130,000 tweets manually annotated by three annotators as related or unrelated to a given event. The 257 events were selected both from press articles and from subjects trending on Twitter during the annotation period (July to August 2018). In total, more than 95,000 tweets were annotated as related to one of the selected events. We also provide the titles and URLs of 15,500 news articles automatically detected as related to these events. In addition to this corpus, we detail the results of our event detection experiments on both this dataset and another publicly available dataset of tweets in English. We ran extensive tests with different types of text embeddings and a standard Topic Detection and Tracking algorithm, and detail our evaluation method. We show that tf-idf vectors allow the best performance for this task on both corpora. These results are intended to serve as a baseline for researchers wishing to test their own event detection systems on our corpus.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-394361" status="VALID">
          <orgName>médialab (Sciences Po)</orgName>
          <orgName type="acronym">médialab</orgName>
          <date type="start">2009-01-01</date>
          <desc>
            <address>
              <addrLine>27 rue Saint-Guillaume - 75337 Paris Cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.medialab.sciencespo.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301587" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-226874" status="VALID">
          <idno type="RNSR">200820915D</idno>
          <orgName>Département d'économie (Sciences Po)</orgName>
          <orgName type="acronym">ECON</orgName>
          <desc>
            <address>
              <addrLine>28 rue des Saints-Pères - 75007 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://econ.sciences-po.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301587" type="direct"/>
            <relation name="UMR8259" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-300215" status="VALID">
          <idno type="ROR">https://ror.org/02zwkwz55</idno>
          <orgName>Institut National de l'Audiovisuel</orgName>
          <orgName type="acronym">INA</orgName>
          <desc>
            <address>
              <addrLine>4 avenue de l'Europe, 94366 Bry-sur-Marne Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.institut-national-audiovisuel.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-1042590" status="VALID">
          <idno type="IdRef">14797299X</idno>
          <idno type="RNSR">200615286U</idno>
          <idno type="ROR">https://ror.org/03q29s414</idno>
          <orgName>Mathématiques et Informatique pour la Complexité et les Systèmes</orgName>
          <orgName type="acronym">MICS</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Plateau de Moulon 3 rue Joliot Curie 91192 GIF SUR YVETTE CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://mics.centralesupelec.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-419361" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-301587" status="VALID">
          <idno type="IdRef">027918459</idno>
          <idno type="ROR">https://ror.org/05fe7ax82</idno>
          <orgName>Sciences Po</orgName>
          <orgName type="acronym">Sciences Po</orgName>
          <desc>
            <address>
              <addrLine>27, rue Saint-Guillaume - 75337 Paris cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.sciencespo.fr/</ref>
          </desc>
        </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-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-419361" status="VALID">
          <idno type="IdRef">241345251</idno>
          <idno type="ROR">https://ror.org/03xjwb503</idno>
          <orgName>Université Paris-Saclay</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment Bréguet, 3 Rue Joliot Curie 2e ét, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-paris-saclay.fr/fr</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>