<?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-03373966</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="2026-05-17T14:23:10+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Evaluation of four clustering methods used in text mining</title>
            <author role="aut">
              <persName>
                <forename type="first">Nicolas</forename>
                <surname>Turenne</surname>
              </persName>
              <email type="md5">f7f95fab80942ce079fe7e154849245c</email>
              <email type="domain">univ-eiffel.fr</email>
              <idno type="idhal" notation="string">nicolas-turenne</idno>
              <idno type="idhal" notation="numeric">749038</idno>
              <idno type="halauthorid" notation="string">1039-749038</idno>
              <idno type="ARXIV">https://arxiv.org/a/turenne_n_1</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1229-5590</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?hl=fr&amp;user=bT6mm6cAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/168615738</idno>
              <affiliation ref="#struct-199013"/>
              <affiliation ref="#struct-7210"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">François</forename>
                <surname>Rousselot</surname>
              </persName>
              <idno type="halauthorid">112088-0</idno>
              <affiliation ref="#struct-199013"/>
              <affiliation ref="#struct-7210"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>nicolas</forename>
                <surname>turenne</surname>
              </persName>
              <email type="md5">faa5544d852a059d5ab8ad2b544fd4b5</email>
              <email type="domain">ird.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-10-11 17:44:09</date>
              <date type="whenModified">2025-06-04 08:34:01</date>
              <date type="whenReleased">2021-10-14 10:54:20</date>
              <date type="whenProduced">1998-04-21</date>
              <date type="whenEndEmbargoed">2021-10-11</date>
              <ref type="file" target="https://hal.science/hal-03373966v1/document">
                <date notBefore="2021-10-11"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-03373966v1/file/10.1.1.40.1938.pdf" id="file-3373966-2965240">
                <date notBefore="2021-10-11"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="187581">
                <persName>
                  <forename>nicolas</forename>
                  <surname>turenne</surname>
                </persName>
                <email type="md5">faa5544d852a059d5ab8ad2b544fd4b5</email>
                <email type="domain">ird.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03373966</idno>
            <idno type="halUri">https://hal.science/hal-03373966</idno>
            <idno type="halBibtex">turenne:hal-03373966</idno>
            <idno type="halRefHtml">&lt;i&gt;European Conference on Machine Learning (ECML)&lt;/i&gt;, Apr 1998, chemnitz, Germany</idno>
            <idno type="halRef">European Conference on Machine Learning (ECML), Apr 1998, chemnitz, Germany</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3373966-2965240"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-STRASBG">Université de Strasbourg</idno>
            <idno type="stamp" n="INSA-STRASBOURG">Institut National des Sciences Appliquées de Strasbourg</idno>
            <idno type="stamp" n="SITE-ALSACE">Archive ouverte du site Alsace</idno>
            <idno type="stamp" n="INSA-GROUPE">Groupe INSA</idno>
            <idno type="stamp" n="UNIVOAK">UNIVOAK</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">Evaluation of four clustering methods used in text mining</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Nicolas</forename>
                    <surname>Turenne</surname>
                  </persName>
                  <email type="md5">f7f95fab80942ce079fe7e154849245c</email>
                  <email type="domain">univ-eiffel.fr</email>
                  <idno type="idhal" notation="string">nicolas-turenne</idno>
                  <idno type="idhal" notation="numeric">749038</idno>
                  <idno type="halauthorid" notation="string">1039-749038</idno>
                  <idno type="ARXIV">https://arxiv.org/a/turenne_n_1</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1229-5590</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?hl=fr&amp;user=bT6mm6cAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/168615738</idno>
                  <affiliation ref="#struct-199013"/>
                  <affiliation ref="#struct-7210"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">François</forename>
                    <surname>Rousselot</surname>
                  </persName>
                  <idno type="halauthorid">112088-0</idno>
                  <affiliation ref="#struct-199013"/>
                  <affiliation ref="#struct-7210"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>European Conference on Machine Learning (ECML)</title>
                  <date type="start">1998-04-21</date>
                  <settlement>chemnitz</settlement>
                  <country key="DE">Germany</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">conceptual clustering</term>
                <term xml:lang="en">data mining</term>
                <term xml:lang="en">knowledge structuration</term>
                <term xml:lang="en">evaluation</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>Classification systems are used more and more often in artificial intelligence, especially to analyze texts and to extract knowledge they contain. The results of general clustering methods, though, are viewed too often being an absolute reference for classifying terms. This paper's goal is to evaluate quantitatively the quality of classification. Various tools are compared with relation to the same reference medical corpus. We analyze various methods such as hierarchical clustering, neural network, partitioning, co-word analysis which occur in different software systems. The evaluation method used is based on the comparison between a conceptual classfication taken as a reference, and the resulting classifications. This reference classification was realized with the help of a medical expert. It is an handmade classification according the real-world.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-199013" status="VALID">
          <idno type="IdRef">131056549</idno>
          <idno type="ROR">https://ror.org/00pg6eq24</idno>
          <orgName>Université de Strasbourg</orgName>
          <orgName type="acronym">UNISTRA</orgName>
          <desc>
            <address>
              <addrLine>4 rue Blaise Pascal - CS 90032 - 67081 Strasbourg cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.unistra.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-7210" status="OLD">
          <orgName>Laboratoire d' Informatique et d'Intelligence Artificielle</orgName>
          <orgName type="acronym">LIIA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-261615" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-261615" status="VALID">
          <orgName>Institut National des Sciences Appliquées - Strasbourg</orgName>
          <orgName type="acronym">INSA Strasbourg</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-strasbourg.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301232" 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>
      </listOrg>
    </back>
  </text>
</TEI>