<?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-02507577</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="2026-05-18T03:20:37+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="fr">Web Content Data Mining : la classification croisée pour l'analyse textuelle d'un site Web</title>
            <author role="aut">
              <persName>
                <forename type="first">Malika</forename>
                <surname>Charrad</surname>
              </persName>
              <email type="md5">33f2b4edb0a303bbedccf8e616de3698</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">malika-charrad</idno>
              <idno type="idhal" notation="numeric">1343595</idno>
              <idno type="halauthorid" notation="string">895021-1343595</idno>
              <idno type="ORCID">https://orcid.org/0009-0004-0360-5926</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=YDE6K-AAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/145469905</idno>
              <affiliation ref="#struct-16574"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Yves</forename>
                <surname>Lechevallier</surname>
              </persName>
              <email type="md5">adf69fe1c6f31d9e7b877998cf44f522</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="numeric">830029</idno>
              <idno type="halauthorid" notation="string">104963-830029</idno>
              <orgName ref="#struct-300009"/>
              <affiliation ref="#struct-2446"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gilbert</forename>
                <surname>Saporta</surname>
              </persName>
              <email type="md5">6298c57098dc5d21247fd35757d2103d</email>
              <email type="domain">cnam.fr</email>
              <idno type="idhal" notation="string">gilbert-saporta</idno>
              <idno type="idhal" notation="numeric">180161</idno>
              <idno type="halauthorid" notation="string">4563-180161</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3406-5887</idno>
              <idno type="IDREF">https://www.idref.fr/027122565</idno>
              <idno type="ARXIV">https://arxiv.org/a/saporta_g_1</idno>
              <affiliation ref="#struct-390785"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mohamed</forename>
                <surname>Ben Ahmed</surname>
              </persName>
              <email type="md5">7e61740047c2fe2ec55e92d746bcee92</email>
              <email type="domain">riadi.rnu.tn</email>
              <idno type="idhal" notation="numeric">885593</idno>
              <idno type="halauthorid" notation="string">3049-885593</idno>
              <affiliation ref="#struct-421707"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Gilbert</forename>
                <surname>Saporta</surname>
              </persName>
              <email type="md5">6298c57098dc5d21247fd35757d2103d</email>
              <email type="domain">cnam.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-12-16 13:30:35</date>
              <date type="whenModified">2025-08-26 15:21:01</date>
              <date type="whenReleased">2021-01-19 10:40:48</date>
              <date type="whenProduced">2008</date>
              <date type="whenEndEmbargoed">2020-12-16</date>
              <ref type="file" target="https://cnam.hal.science/hal-02507577v1/document">
                <date notBefore="2020-12-16"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://cnam.hal.science/hal-02507577v1/file/1000555.pdf" id="file-3075329-2726556">
                <date notBefore="2020-12-16"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="167713">
                <persName>
                  <forename>Gilbert</forename>
                  <surname>Saporta</surname>
                </persName>
                <email type="md5">6298c57098dc5d21247fd35757d2103d</email>
                <email type="domain">cnam.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02507577</idno>
            <idno type="halUri">https://cnam.hal.science/hal-02507577</idno>
            <idno type="halBibtex">charrad:hal-02507577</idno>
            <idno type="halRefHtml">&lt;i&gt;Revue des Nouvelles Technologies de l'Information&lt;/i&gt;, 2008, RNTI-E11, pp.43-54</idno>
            <idno type="halRef">Revue des Nouvelles Technologies de l'Information, 2008, RNTI-E11, pp.43-54</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3075329-2726556"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="CNAM">Conservatoire National des Arts et Métiers</idno>
            <idno type="stamp" n="INRIA-SOPHIA">INRIA Sophia Antipolis - Méditerranée</idno>
            <idno type="stamp" n="INRIA-ROCQ">INRIA Paris - Rocquencourt</idno>
            <idno type="stamp" n="INRIASO">INRIA-SOPHIA</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="LORIA2">Publications du LORIA</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="UNIV-COTEDAZUR">Université Côte d'Azur</idno>
            <idno type="stamp" n="INRIA-300009">Inria 300009</idno>
            <idno type="stamp" n="CEDRIC-CNAM" corresp="CNAM">Centre d'études et de recherche en informatique et communications </idno>
            <idno type="stamp" n="INRIA_WEB">Inria &amp; web</idno>
            <idno type="stamp" n="TEST3-HALCNRS">TEST3-HALCNRS</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="fr">Web Content Data Mining : la classification croisée pour l'analyse textuelle d'un site Web</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Malika</forename>
                    <surname>Charrad</surname>
                  </persName>
                  <email type="md5">33f2b4edb0a303bbedccf8e616de3698</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">malika-charrad</idno>
                  <idno type="idhal" notation="numeric">1343595</idno>
                  <idno type="halauthorid" notation="string">895021-1343595</idno>
                  <idno type="ORCID">https://orcid.org/0009-0004-0360-5926</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=YDE6K-AAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/145469905</idno>
                  <affiliation ref="#struct-16574"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Yves</forename>
                    <surname>Lechevallier</surname>
                  </persName>
                  <email type="md5">adf69fe1c6f31d9e7b877998cf44f522</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="numeric">830029</idno>
                  <idno type="halauthorid" notation="string">104963-830029</idno>
                  <orgName ref="#struct-300009"/>
                  <affiliation ref="#struct-2446"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gilbert</forename>
                    <surname>Saporta</surname>
                  </persName>
                  <email type="md5">6298c57098dc5d21247fd35757d2103d</email>
                  <email type="domain">cnam.fr</email>
                  <idno type="idhal" notation="string">gilbert-saporta</idno>
                  <idno type="idhal" notation="numeric">180161</idno>
                  <idno type="halauthorid" notation="string">4563-180161</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3406-5887</idno>
                  <idno type="IDREF">https://www.idref.fr/027122565</idno>
                  <idno type="ARXIV">https://arxiv.org/a/saporta_g_1</idno>
                  <affiliation ref="#struct-390785"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mohamed</forename>
                    <surname>Ben Ahmed</surname>
                  </persName>
                  <email type="md5">7e61740047c2fe2ec55e92d746bcee92</email>
                  <email type="domain">riadi.rnu.tn</email>
                  <idno type="idhal" notation="numeric">885593</idno>
                  <idno type="halauthorid" notation="string">3049-885593</idno>
                  <affiliation ref="#struct-421707"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">49831</idno>
                <idno type="issn">1764-1667</idno>
                <title level="j">Revue des Nouvelles Technologies de l'Information</title>
                <imprint>
                  <publisher>Editions RNTI</publisher>
                  <biblScope unit="volume">RNTI-E11</biblScope>
                  <biblScope unit="pp">43-54</biblScope>
                  <date type="datePub">2008</date>
                </imprint>
              </monogr>
              <ref type="publisher">https://editions-rnti.fr/?inprocid=1000555</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="fr">French</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Natural Language Processing</term>
                <term xml:lang="en">Biclustering</term>
                <term xml:lang="en">Text Mining</term>
                <term xml:lang="en">Clustering</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</classCode>
              <classCode scheme="halDomain" n="info.info-wb">Computer Science [cs]/Web</classCode>
              <classCode scheme="halDomain" n="stat">Statistics [stat]</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="fr">
              <p>Notre objectif dans cet article est l'analyse textuelle d'un site Web indépendamment de son usage. Notre approche se déroule en trois étapes. La première étape consiste au typage des pages afin de distinguer les pages de navigation ou pages « auxiliaires » des pages de contenu. La deuxième étape consiste au prétraitement du contenu des pages de contenu afin de représenter chaque page par un vecteur de descripteurs. La dernière étape consiste au block clustering ou la classification simultanée des lignes et des colonnes de la matrice croisant les pages aux descripteurs de pages afin de découvrir des biclasses de pages et de descripteurs. L'application de cette approche au site de tourisme de Metz prouve son efficacité et son applicabilité. L'ensemble de classes de pages groupés en thèmes facilitera l'analyse ultérieure de l'usage du site.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-16574" status="VALID">
          <idno type="IdRef">155463381</idno>
          <idno type="RNSR">201119480F</idno>
          <idno type="ROR">https://ror.org/044j5mm75</idno>
          <orgName>Centre d'études et de recherche en informatique et communications</orgName>
          <orgName type="acronym">CEDRIC</orgName>
          <desc>
            <address>
              <addrLine>292 rue Saint-Martin 75141 PARIS Cedex 03Case courrier 2D4P30</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://cedric.cnam.fr/</ref>
          </desc>
          <listRelation>
            <relation name="EA4629" active="#struct-179741" type="direct"/>
            <relation name="EA4629" active="#struct-300351" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-2446" status="OLD">
          <idno type="RNSR">200318386B</idno>
          <orgName>Usage-centered design, analysis and improvement of information systems</orgName>
          <orgName type="acronym">AxIS</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-34586" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-86790" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-390785" status="VALID">
          <orgName>CEDRIC. Méthodes statistiques de data-mining et apprentissage</orgName>
          <orgName type="acronym">CEDRIC - MSDMA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-16574" type="direct"/>
            <relation name="EA4629" active="#struct-179741" type="indirect"/>
            <relation name="EA4629" active="#struct-300351" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-421707" status="VALID">
          <orgName>Laboratoire de recherche en Génie Logiciel, Applications distribuées, Systèmes décisionnels et Imagerie intelligente [Manouba]</orgName>
          <orgName type="acronym">RIADI</orgName>
          <desc>
            <address>
              <addrLine>École Nationale des Sciences de l'Informatique (ENSI), Campus Universitaire de la Manouba, 2010 Manouba, Tunisia</addrLine>
              <country key="TN"/>
            </address>
            <ref type="url">http://www.riadi.rnu.tn/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-230633" type="direct"/>
            <relation active="#struct-193244" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-179741" status="VALID">
          <orgName>Ecole Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise</orgName>
          <orgName type="acronym">ENSIIE</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ensiie.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300351" status="VALID">
          <idno type="IdRef">027404978</idno>
          <idno type="ISNI">0000000121690459</idno>
          <idno type="ROR">https://ror.org/0175hh227</idno>
          <orgName>Conservatoire National des Arts et Métiers [Cnam]</orgName>
          <orgName type="acronym">Cnam</orgName>
          <desc>
            <address>
              <addrLine>292 Rue Saint-Martin, 75003 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.cnam.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-34586" status="VALID">
          <idno type="RNSR">198318250R</idno>
          <idno type="ROR">https://ror.org/01nzkaw91</idno>
          <orgName>Centre Inria d'Université Côte d'Azur</orgName>
          <desc>
            <address>
              <addrLine>2004 route des Lucioles BP 93 06902 Sophia Antipolis</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/sophia/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-86790" status="OLD">
          <orgName>Inria Paris-Rocquencourt</orgName>
          <date type="end">2016-03-30</date>
          <desc>
            <address>
              <addrLine>INRIA Rocquencourt : Domaine de Voluceau, Rocquencourt B.P. 105 78153 le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/paris-rocquencourt</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-230633" status="VALID">
          <orgName>École Nationale des Sciences de l'Informatique [Manouba]</orgName>
          <orgName type="acronym">ENSI</orgName>
          <date type="start">1984-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Universitaire de la Manouba, 2010 Manouba</addrLine>
              <country key="TN"/>
            </address>
            <ref type="url">http://www.ensi-uma.tn/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-193244" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-193244" status="VALID">
          <idno type="ROR">https://ror.org/0503ejf32</idno>
          <orgName>Université de la Manouba [Tunisie]</orgName>
          <orgName type="acronym">UMA</orgName>
          <desc>
            <address>
              <addrLine>Campus Universitaire de la Manouba - la Manouba 2010</addrLine>
              <country key="TN"/>
            </address>
            <ref type="url">http://www.uma.rnu.tn</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>