<?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-04006239</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="2026-05-24T08:42:43+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Hierarchical Topic Model Inference by Community Discovery on Word Co-occurrence Networks</title>
            <author role="aut">
              <persName>
                <forename type="first">Eric</forename>
                <surname>Austin</surname>
              </persName>
              <idno type="halauthorid">1839422-0</idno>
              <affiliation ref="#struct-552656"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Amine</forename>
                <surname>Trabelsi</surname>
              </persName>
              <idno type="idhal" notation="numeric">1231643</idno>
              <idno type="halauthorid" notation="string">1359122-1231643</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1852-5265</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Christine</forename>
                <surname>Largeron</surname>
              </persName>
              <email type="md5">74abe502db975476802cb7b7b409ed60</email>
              <email type="domain">univ-st-etienne.fr</email>
              <idno type="idhal" notation="string">christine-largeron</idno>
              <idno type="idhal" notation="numeric">5702</idno>
              <idno type="halauthorid" notation="string">3566-5702</idno>
              <idno type="IDREF">https://www.idref.fr/029304121</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1059-4095</idno>
              <affiliation ref="#struct-17835"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Osmar</forename>
                <surname>Zaïane</surname>
              </persName>
              <idno type="idhal" notation="numeric">1231644</idno>
              <idno type="halauthorid" notation="string">2740451-1231644</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0060-5988</idno>
              <affiliation ref="#struct-552656"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Christine</forename>
                <surname>Largeron</surname>
              </persName>
              <email type="md5">df167e4a5fffe34c4632445127163217</email>
              <email type="domain">univ-st-etienne.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-02-27 12:45:19</date>
              <date type="whenModified">2026-04-23 14:50:05</date>
              <date type="whenReleased">2023-02-27 12:45:20</date>
              <date type="whenProduced">2022-12-12</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="113829">
                <persName>
                  <forename>Christine</forename>
                  <surname>Largeron</surname>
                </persName>
                <email type="md5">df167e4a5fffe34c4632445127163217</email>
                <email type="domain">univ-st-etienne.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04006239</idno>
            <idno type="halUri">https://cnrs.hal.science/hal-04006239</idno>
            <idno type="halBibtex">austin:hal-04006239</idno>
            <idno type="halRefHtml">&lt;i&gt;20th Australasian Conference, AusDM 2022&lt;/i&gt;, Dec 2022, Western Sydney, Australia. pp.148-162, &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-981-19-8746-5_11"&gt;&amp;#x27E8;10.1007/978-981-19-8746-5_11&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">20th Australasian Conference, AusDM 2022, Dec 2022, Western Sydney, Australia. pp.148-162, &amp;#x27E8;10.1007/978-981-19-8746-5_11&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-ST-ETIENNE">Université Jean Monnet - Saint-Etienne</idno>
            <idno type="stamp" n="IOGS" corresp="PARISTECH">Institut d'Optique Graduate School</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="PARISTECH">ParisTech</idno>
            <idno type="stamp" n="UDL">UDL</idno>
            <idno type="stamp" n="LABORATOIRE-HUBERT-CURIEN" corresp="UNIV-ST-ETIENNE">LAboratoire Hubert Curien</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">Hierarchical Topic Model Inference by Community Discovery on Word Co-occurrence Networks</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Eric</forename>
                    <surname>Austin</surname>
                  </persName>
                  <idno type="halauthorid">1839422-0</idno>
                  <affiliation ref="#struct-552656"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Amine</forename>
                    <surname>Trabelsi</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1231643</idno>
                  <idno type="halauthorid" notation="string">1359122-1231643</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1852-5265</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Christine</forename>
                    <surname>Largeron</surname>
                  </persName>
                  <email type="md5">74abe502db975476802cb7b7b409ed60</email>
                  <email type="domain">univ-st-etienne.fr</email>
                  <idno type="idhal" notation="string">christine-largeron</idno>
                  <idno type="idhal" notation="numeric">5702</idno>
                  <idno type="halauthorid" notation="string">3566-5702</idno>
                  <idno type="IDREF">https://www.idref.fr/029304121</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1059-4095</idno>
                  <affiliation ref="#struct-17835"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Osmar</forename>
                    <surname>Zaïane</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1231644</idno>
                  <idno type="halauthorid" notation="string">2740451-1231644</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0060-5988</idno>
                  <affiliation ref="#struct-552656"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>20th Australasian Conference, AusDM 2022</title>
                  <date type="start">2022-12-12</date>
                  <date type="end">2022-12-15</date>
                  <settlement>Western Sydney</settlement>
                  <country key="AU">Australia</country>
                </meeting>
                <imprint>
                  <publisher>Springer Nature Singapore</publisher>
                  <pubPlace>Singapore</pubPlace>
                  <biblScope unit="serie">Communications in Computer and Information Science</biblScope>
                  <biblScope unit="volume">1741</biblScope>
                  <biblScope unit="pp">148-162</biblScope>
                  <date type="datePub">2022-12-05</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/978-981-19-8746-5_11</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <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>The most popular topic modelling algorithm, Latent Dirichlet Allocation, produces a simple set of topics. However, topics naturally exist in a hierarchy with larger, more general super-topics and smaller, more specific sub-topics. We develop a novel topic modelling algorithm, Community Topic, that mines communities from word co-occurrence networks to produce topics. The fractal structure of networks provides a natural topic hierarchy where sub-topics can be found by iteratively mining the sub-graph formed by a single topic. Similarly, super-topics can by found by mining the network of topic hyper-nodes. We compare the topic hierarchies discovered by Community Topic to those produced by two probabilistic graphical topic models and find that Community Topic uncovers a topic hierarchy with a more coherent structure and a tighter relationship between parent and child topics. Community Topic is able to find this hierarchy more quickly and allows for on-demand sub- and super-topic discovery, facilitating corpus exploration by researchers.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-552656" status="VALID">
          <orgName>Alberta Machine Intelligence Institut</orgName>
          <orgName type="acronym">AMII</orgName>
          <desc>
            <address>
              <country key="CA"/>
            </address>
            <ref type="url">https://albertainnovates.ca/programs/alberta-machine-intelligence-institute/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-551658" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-17835" status="VALID">
          <idno type="IdRef">164609741</idno>
          <idno type="ISNI">0000 0000 9955 0977</idno>
          <idno type="RNSR">199511960B</idno>
          <idno type="ROR">https://ror.org/0028p8r67</idno>
          <orgName>Laboratoire Hubert Curien</orgName>
          <orgName type="acronym">LabHC</orgName>
          <date type="start">2006-01-01</date>
          <desc>
            <address>
              <addrLine>Bâtiment F 18 Rue du Professeur Benoît Lauras42000 Saint-Etienne</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://laboratoirehubertcurien.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300036" type="direct"/>
            <relation active="#struct-300284" type="direct"/>
            <relation active="#struct-1327915" type="indirect"/>
            <relation name="UMR5516" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-551658" status="VALID">
          <orgName>Alberta Innovates – Technology Future</orgName>
          <desc>
            <address>
              <addrLine>250 Karl Clark Road, Edmonton</addrLine>
              <country key="CA"/>
            </address>
            <ref type="url">https://albertainnovates.ca/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300036" status="VALID">
          <idno type="IdRef">110047702</idno>
          <orgName>Institut d'Optique Graduate School</orgName>
          <orgName type="acronym">IOGS</orgName>
          <desc>
            <address>
              <addrLine>2 avenue Augustin Fresnel, 91127 Palaiseau Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.institutoptique.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300284" status="VALID">
          <idno type="IdRef">028209966</idno>
          <idno type="ISNI">0000 0001 2158 1682</idno>
          <idno type="ROR">https://ror.org/04yznqr36</idno>
          <idno type="Wikidata">Q623154</idno>
          <orgName>Université Jean Monnet - Saint-Étienne</orgName>
          <orgName type="acronym">UJM</orgName>
          <date type="start">1969-03-27</date>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>10, Rue Tréfilerie – CS 8230142023 Saint-Étienne Cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-st-etienne.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1327915" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-1327915" status="VALID">
          <idno type="IdRef">285395831</idno>
          <orgName>Université Jean Monnet (EPSCPE)</orgName>
          <orgName type="acronym">UJM EPE</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>10 rue Tréfilerie42100 Saint-Etienne</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-st-etienne.fr/fr/index.html</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>