<?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-05334503</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="2026-05-19T15:25:31+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Semantic Analysis Experiments for French Citizens' Contribution : Combinations of Language Models and Community Detection Algorithms</title>
            <author role="aut">
              <persName>
                <forename type="first">Sami</forename>
                <surname>Guembour</surname>
              </persName>
              <email type="md5">24511cfc2c7e5b2f97511229d347baa7</email>
              <email type="domain">hotmail.fr</email>
              <idno type="idhal" notation="string">sami-guembour</idno>
              <idno type="idhal" notation="numeric">1298312</idno>
              <idno type="halauthorid" notation="string">2931124-1298312</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5204-2374</idno>
              <affiliation ref="#struct-300101"/>
              <affiliation ref="#struct-1008455"/>
              <affiliation ref="#struct-1003089"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Catherine</forename>
                <surname>Dominguès</surname>
              </persName>
              <email type="md5">b8b73150e26970776a6d2ff32f87a0da</email>
              <email type="domain">ign.fr</email>
              <idno type="idhal" notation="string">catherine-domingues</idno>
              <idno type="idhal" notation="numeric">19721</idno>
              <idno type="halauthorid" notation="string">26258-19721</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0362-6805</idno>
              <idno type="IDREF">https://www.idref.fr/119915057</idno>
              <affiliation ref="#struct-1003089"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sabine</forename>
                <surname>Ploux</surname>
              </persName>
              <email type="md5">452023ea3164e6688815ef1c37e36205</email>
              <email type="domain">isc.cnrs.fr</email>
              <idno type="idhal" notation="string">sabine-ploux</idno>
              <idno type="idhal" notation="numeric">1062259</idno>
              <idno type="halauthorid" notation="string">132350-1062259</idno>
              <affiliation ref="#struct-1318"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Sami</forename>
                <surname>Guembour</surname>
              </persName>
              <email type="md5">24511cfc2c7e5b2f97511229d347baa7</email>
              <email type="domain">hotmail.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-10-28 10:15:30</date>
              <date type="whenModified">2026-04-30 10:54:03</date>
              <date type="whenReleased">2025-10-29 13:01:18</date>
              <date type="whenProduced">2025-09-22</date>
              <date type="whenEndEmbargoed">2025-10-28</date>
              <ref type="file" target="https://hal.science/hal-05334503v1/document">
                <date notBefore="2025-10-28"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-05334503v1/file/2025.iwcs-1.21.pdf" id="file-5334503-4569123">
                <date notBefore="2025-10-28"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1467064">
                <persName>
                  <forename>Sami</forename>
                  <surname>Guembour</surname>
                </persName>
                <email type="md5">24511cfc2c7e5b2f97511229d347baa7</email>
                <email type="domain">hotmail.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05334503</idno>
            <idno type="halUri">https://hal.science/hal-05334503</idno>
            <idno type="halBibtex">guembour:hal-05334503</idno>
            <idno type="halRefHtml">&lt;i&gt;16th International Conference on Computational Semantics (IWCS)&lt;/i&gt;, Sep 2025, Düsseldorf, Germany</idno>
            <idno type="halRef">16th International Conference on Computational Semantics (IWCS), Sep 2025, Düsseldorf, Germany</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-5334503-4569123"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="EHESS">Ecole des Hautes Etudes en Sciences Sociales</idno>
            <idno type="stamp" n="IGN-ENSG">Institut national de l’information géographique et forestière - Ecole nationale des sciences géographiques</idno>
            <idno type="stamp" n="UNIV-EIFFEL">Université Gustave Eiffel</idno>
            <idno type="stamp" n="U-EIFFEL">Université Gustave Eiffel</idno>
            <idno type="stamp" n="CAMS" corresp="EHESS">Collection HAL du Centre d'Analyse et de Mathématique Sociales (CAMS, UMR CNRS-EHESS)</idno>
            <idno type="stamp" n="GEODATA-PARIS">Géodata Paris</idno>
            <idno type="stamp" n="IGN">Institut National de l'Information Géographique et Forestière</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="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Semantic Analysis Experiments for French Citizens' Contribution : Combinations of Language Models and Community Detection Algorithms</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Sami</forename>
                    <surname>Guembour</surname>
                  </persName>
                  <email type="md5">24511cfc2c7e5b2f97511229d347baa7</email>
                  <email type="domain">hotmail.fr</email>
                  <idno type="idhal" notation="string">sami-guembour</idno>
                  <idno type="idhal" notation="numeric">1298312</idno>
                  <idno type="halauthorid" notation="string">2931124-1298312</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5204-2374</idno>
                  <affiliation ref="#struct-300101"/>
                  <affiliation ref="#struct-1008455"/>
                  <affiliation ref="#struct-1003089"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Catherine</forename>
                    <surname>Dominguès</surname>
                  </persName>
                  <email type="md5">b8b73150e26970776a6d2ff32f87a0da</email>
                  <email type="domain">ign.fr</email>
                  <idno type="idhal" notation="string">catherine-domingues</idno>
                  <idno type="idhal" notation="numeric">19721</idno>
                  <idno type="halauthorid" notation="string">26258-19721</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0362-6805</idno>
                  <idno type="IDREF">https://www.idref.fr/119915057</idno>
                  <affiliation ref="#struct-1003089"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sabine</forename>
                    <surname>Ploux</surname>
                  </persName>
                  <email type="md5">452023ea3164e6688815ef1c37e36205</email>
                  <email type="domain">isc.cnrs.fr</email>
                  <idno type="idhal" notation="string">sabine-ploux</idno>
                  <idno type="idhal" notation="numeric">1062259</idno>
                  <idno type="halauthorid" notation="string">132350-1062259</idno>
                  <affiliation ref="#struct-1318"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">ACL Anthology</title>
                <meeting>
                  <title>16th International Conference on Computational Semantics (IWCS)</title>
                  <date type="start">2025-09-22</date>
                  <date type="end">2025-09-23</date>
                  <settlement>Düsseldorf</settlement>
                  <country key="DE">Germany</country>
                </meeting>
                <imprint/>
              </monogr>
              <ref type="publisher">https://preview.aclanthology.org/iwcs-25-ingestion/2025.iwcs-1.21/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Dimensionality reduction</term>
                <term xml:lang="en">Cahiers Citoyens</term>
                <term xml:lang="en">Clustering</term>
                <term xml:lang="en">Community detection</term>
                <term xml:lang="en">Language models</term>
                <term xml:lang="en">Semantic analysis</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</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>Following the Yellow Vest crisis that occurred in France in 2018, the French government launched the Grand Débat National, which gathered citizens' contributions. This paper presents a semantic analysis of these contributions by segmenting them into sentences and identifying the topics addressed using clustering techniques. The study tests several combinations of French language models and community detection algorithms, aiming to identify the most effective pairing for grouping sentences based on thematic similarity. Performance is evaluated using the number of clusters generated and standard clustering metrics. Principal Component Analysis (PCA) is employed to assess the impact of dimensionality reduction on sentence embeddings and clustering quality. Cluster merging methods are also developed to reduce redundancy and improve the relevance of the identified topics. Finally, the results help refine semantic analysis and shed light on the main concerns expressed by citizens.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-300101" status="VALID">
          <idno type="IdRef">160332346</idno>
          <idno type="ROR">https://ror.org/05jxfge78</idno>
          <orgName>Institut National de l'Information Géographique et Forestière [IGN]</orgName>
          <orgName type="acronym">IGN</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>73 avenue de Paris, 94165 SAINT-MANDÉ CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ign.fr</ref>
          </desc>
        </org>
        <org type="regrouplaboratory" xml:id="struct-1008455" status="VALID">
          <idno type="ROR">https://ror.org/03r3n3715</idno>
          <orgName>École nationale des sciences géographiques</orgName>
          <orgName type="acronym">ENSG</orgName>
          <date type="start">2020-01-01</date>
          <date type="end">2025-10-01</date>
          <desc>
            <address>
              <addrLine>6 et 8 Avenue Blaise Pascal - Cité Descartes - Champs-sur-Marne - 77455 Marne la Vallée Cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ensg.eu/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300101" type="direct"/>
            <relation active="#struct-580722" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1003089" status="OLD">
          <orgName>Laboratoire en Sciences et Technologies de l'Information Géographique</orgName>
          <orgName type="acronym">LaSTIG</orgName>
          <date type="start">2020-01-01</date>
          <date type="end">2025-10-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-424408" type="direct"/>
            <relation active="#struct-1008455" type="direct"/>
            <relation active="#struct-300101" type="indirect"/>
            <relation active="#struct-580722" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1318" status="VALID">
          <idno type="RNSR">199812885U</idno>
          <idno type="ROR">00vb8fc53</idno>
          <orgName>Centre d'Analyse et de Mathématique sociales</orgName>
          <orgName type="acronym">CAMS</orgName>
          <date type="start">1998-01-01</date>
          <desc>
            <address>
              <addrLine>54 boulevard Raspail 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://cams.ehess.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-99539" type="direct"/>
            <relation name="UMR8557" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-580722" status="VALID">
          <idno type="ROR">https://ror.org/03x42jk29</idno>
          <orgName>Université Gustave Eiffel</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Cité Descartes, 5 Boulevard Descartes • Champs-sur-Marne, 77454 Marne-la-Vallée Cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-gustave-eiffel.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-424408" status="VALID">
          <idno type="ROR">https://ror.org/038k8pw28</idno>
          <orgName>Ecole des Ingénieurs de la Ville de Paris</orgName>
          <orgName type="acronym">EIVP</orgName>
          <desc>
            <address>
              <addrLine>Lab'Urba, Université Paris Est, 80 rue Rébeval, 75019 Paris, France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.eivp-paris.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-99539" status="VALID">
          <idno type="IdRef">026374889</idno>
          <idno type="ROR">https://ror.org/02d9dg697</idno>
          <orgName>École des hautes études en sciences sociales</orgName>
          <orgName type="acronym">EHESS</orgName>
          <date type="start">1975-01-01</date>
          <desc>
            <address>
              <addrLine>54, boulevard Raspail 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ehess.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>
      </listOrg>
    </back>
  </text>
</TEI>