<?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-01325212</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="2026-05-13T02:32:28+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Short Text Classification Using Semantic Random Forest</title>
            <author role="aut">
              <persName>
                <forename type="first">Ameni</forename>
                <surname>Bouaziz</surname>
              </persName>
              <idno type="halauthorid">1032987-0</idno>
              <affiliation ref="#struct-205299"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Christel</forename>
                <surname>Dartigues-Pallez</surname>
              </persName>
              <email type="md5">cc4437ae256ad0c863be7ef272dfc0f8</email>
              <email type="domain">unice.fr</email>
              <idno type="idhal" notation="string">christel-dartigues-pallez</idno>
              <idno type="idhal" notation="numeric">8939</idno>
              <idno type="halauthorid" notation="string">30183-8939</idno>
              <idno type="IDREF">https://www.idref.fr/081359535</idno>
              <affiliation ref="#struct-205299"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Célia</forename>
                <surname>da Costa Pereira</surname>
              </persName>
              <email type="md5">80528e59c442110652c2c3609e201931</email>
              <email type="domain">unice.fr</email>
              <idno type="idhal" notation="string">celia-da-costa-pereira</idno>
              <idno type="idhal" notation="numeric">8874</idno>
              <idno type="halauthorid" notation="string">27310-8874</idno>
              <idno type="IDREF">https://www.idref.fr/204083907</idno>
              <orgName ref="#struct-117617"/>
              <affiliation ref="#struct-205299"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Frédéric</forename>
                <surname>Precioso</surname>
              </persName>
              <email type="md5">24474122907efd77f911aa34ca8a9fe8</email>
              <email type="domain">univ-cotedazur.fr</email>
              <idno type="idhal" notation="string">frederic-precioso</idno>
              <idno type="idhal" notation="numeric">9244</idno>
              <idno type="halauthorid" notation="string">7893-9244</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-8712-1443</idno>
              <idno type="IDREF">https://www.idref.fr/087273934</idno>
              <affiliation ref="#struct-205299"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Patrick</forename>
                <surname>Lloret</surname>
              </persName>
              <idno type="halauthorid">852753-0</idno>
              <affiliation ref="#struct-263659"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Frédéric</forename>
                <surname>Precioso</surname>
              </persName>
              <email type="md5">24474122907efd77f911aa34ca8a9fe8</email>
              <email type="domain">univ-cotedazur.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2016-06-02 00:54:53</date>
              <date type="whenWritten">2014-09</date>
              <date type="whenModified">2025-10-07 15:32:03</date>
              <date type="whenReleased">2016-06-02 00:54:53</date>
              <date type="whenProduced">2014-09-02</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="130015">
                <persName>
                  <forename>Frédéric</forename>
                  <surname>Precioso</surname>
                </persName>
                <email type="md5">24474122907efd77f911aa34ca8a9fe8</email>
                <email type="domain">univ-cotedazur.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01325212</idno>
            <idno type="halUri">https://hal.science/hal-01325212</idno>
            <idno type="halBibtex">bouaziz:hal-01325212</idno>
            <idno type="halRefHtml">&lt;i&gt;Data Warehousing and Knowledge Discovery&lt;/i&gt;, Sep 2014, Munich, Germany. &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-3-319-10160-6_26"&gt;&amp;#x27E8;10.1007/978-3-319-10160-6_26&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Data Warehousing and Knowledge Discovery, Sep 2014, Munich, Germany. &amp;#x27E8;10.1007/978-3-319-10160-6_26&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNICE">Université Nice Sophia Antipolis</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="I3S">Laboratoire d'Informatique, Signaux et Systèmes de Sophia-Antipolis</idno>
            <idno type="stamp" n="UNIV-COTEDAZUR">Université Côte d'Azur</idno>
            <idno type="stamp" n="TEST-NICE">test nice</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">Short Text Classification Using Semantic Random Forest</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Ameni</forename>
                    <surname>Bouaziz</surname>
                  </persName>
                  <idno type="halauthorid">1032987-0</idno>
                  <affiliation ref="#struct-205299"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Christel</forename>
                    <surname>Dartigues-Pallez</surname>
                  </persName>
                  <email type="md5">cc4437ae256ad0c863be7ef272dfc0f8</email>
                  <email type="domain">unice.fr</email>
                  <idno type="idhal" notation="string">christel-dartigues-pallez</idno>
                  <idno type="idhal" notation="numeric">8939</idno>
                  <idno type="halauthorid" notation="string">30183-8939</idno>
                  <idno type="IDREF">https://www.idref.fr/081359535</idno>
                  <affiliation ref="#struct-205299"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Célia</forename>
                    <surname>da Costa Pereira</surname>
                  </persName>
                  <email type="md5">80528e59c442110652c2c3609e201931</email>
                  <email type="domain">unice.fr</email>
                  <idno type="idhal" notation="string">celia-da-costa-pereira</idno>
                  <idno type="idhal" notation="numeric">8874</idno>
                  <idno type="halauthorid" notation="string">27310-8874</idno>
                  <idno type="IDREF">https://www.idref.fr/204083907</idno>
                  <orgName ref="#struct-117617"/>
                  <affiliation ref="#struct-205299"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Frédéric</forename>
                    <surname>Precioso</surname>
                  </persName>
                  <email type="md5">24474122907efd77f911aa34ca8a9fe8</email>
                  <email type="domain">univ-cotedazur.fr</email>
                  <idno type="idhal" notation="string">frederic-precioso</idno>
                  <idno type="idhal" notation="numeric">9244</idno>
                  <idno type="halauthorid" notation="string">7893-9244</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-8712-1443</idno>
                  <idno type="IDREF">https://www.idref.fr/087273934</idno>
                  <affiliation ref="#struct-205299"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Patrick</forename>
                    <surname>Lloret</surname>
                  </persName>
                  <idno type="halauthorid">852753-0</idno>
                  <affiliation ref="#struct-263659"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Data Warehousing and Knowledge Discovery</title>
                  <date type="start">2014-09-02</date>
                  <date type="end">2014-09-04</date>
                  <settlement>Munich</settlement>
                  <country key="DE">Germany</country>
                </meeting>
                <imprint>
                  <biblScope unit="serie">Lecture Notes in Computer Science</biblScope>
                  <biblScope unit="volume">8646</biblScope>
                  <date type="datePub">2014-09</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/978-3-319-10160-6_26</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Semantics</term>
                <term xml:lang="en">Latent Dirichlet Allocation</term>
                <term xml:lang="en">Random Forest</term>
                <term xml:lang="en">Short text classification</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</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>Using traditional Random Forests in short text classification revealed a performance degradation compared to using them for standard texts. Shortness, sparseness and lack of contextual information in short texts are the reasons of this degradation. Existing solutions to overcome these issues are mainly based on data enrichment. However, data enrichment can also introduce noise. We propose a new approach that combines data enrichment with the introduction of semantics in Random Forests. Each short text is enriched with data semantically similar to its words. These data come from an external source of knowledge distributed into topics thanks to the Latent Dirichlet Allocation model. Learning process in Random Forests is adapted to consider semantic relations between words while building the trees. Tests performed on search-snippets using the new method showed significant improvements in the classification. The accuracy has increased by 34% compared to traditional Random Forests and by 20% compared to MaxEnt.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-205299" status="OLD">
          <orgName>Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Equipe KEIA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://keia.i3s.unice.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-452156" type="direct"/>
            <relation active="#struct-13009" type="indirect"/>
            <relation active="#struct-117617" type="indirect"/>
            <relation name="UMR7271" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1039632" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-263659" status="VALID">
          <orgName>Succeed Together</orgName>
          <desc>
            <address>
              <addrLine>60, rue de Maubeuge, 75009 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.succeed-together.eu</ref>
          </desc>
          <listRelation>
            <relation active="#struct-362598" type="direct"/>
          </listRelation>
        </org>
        <org type="department" xml:id="struct-452156" status="VALID">
          <orgName>Scalable and Pervasive softwARe and Knowledge Systems</orgName>
          <orgName type="acronym">Laboratoire I3S - SPARKS</orgName>
          <date type="start">2016-03-03</date>
          <desc>
            <address>
              <addrLine>Laboratoire I3SCS 4012106903 Sophia Antipolis Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.i3s.unice.fr/sparks</ref>
          </desc>
          <listRelation>
            <relation active="#struct-13009" type="direct"/>
            <relation active="#struct-117617" type="indirect"/>
            <relation name="UMR7271" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1039632" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-13009" status="VALID">
          <idno type="IdRef">050320491</idno>
          <idno type="ISNI">0000000105613840</idno>
          <idno type="RNSR">201220432L</idno>
          <idno type="ROR">https://ror.org/01215r597</idno>
          <orgName>Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis</orgName>
          <orgName type="acronym">I3S</orgName>
          <desc>
            <address>
              <addrLine>2000, route des Lucioles - Les Algorithmes - bât. Euclide B 06900 Sophia Antipolis</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.i3s.unice.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-117617" type="direct"/>
            <relation name="UMR7271" active="#struct-441569" type="direct"/>
            <relation active="#struct-1039632" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-117617" status="VALID">
          <idno type="IdRef">026403498</idno>
          <idno type="ISNI">0000000123372892</idno>
          <idno type="ROR">https://ror.org/02k9vew78</idno>
          <orgName>Université Nice Sophia Antipolis (1965 - 2019)</orgName>
          <orgName type="acronym">UNS</orgName>
          <date type="start">1965-10-23</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Parc Valrose, 06100 Nice</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://unice.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="regroupinstitution" xml:id="struct-1039632" status="VALID">
          <idno type="IdRef">241035694</idno>
          <idno type="ROR">https://ror.org/019tgvf94</idno>
          <orgName>Université Côte d'Azur</orgName>
          <orgName type="acronym">UniCA</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Parc Valrose, 28, avenue Valrose 06108 Nice Cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://univ-cotedazur.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-362598" status="INCOMING">
          <orgName>Succeed Together</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>