<?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-01355397</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="2026-05-18T13:32:56+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">WhichStreams: A Dynamic Approach for Focused Data Capture from Large Social Media</title>
            <author role="aut">
              <persName>
                <forename type="first">Thibault</forename>
                <surname>Gisselbrecht</surname>
              </persName>
              <email type="md5">7771a8651114b8940820cbb1e005f56e</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="numeric">987816</idno>
              <idno type="halauthorid" notation="string">1052454-987816</idno>
              <affiliation ref="#struct-363822"/>
              <affiliation ref="#struct-408311"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Patrick</forename>
                <surname>Gallinari</surname>
              </persName>
              <email type="md5">d928d788b4143b63dbc87c6175a152be</email>
              <email type="domain">sorbonne-universite.fr</email>
              <idno type="idhal" notation="string">patrick-gallinari</idno>
              <idno type="idhal" notation="numeric">751615</idno>
              <idno type="halauthorid" notation="string">1778-751615</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-9060-9001</idno>
              <idno type="IDREF">https://www.idref.fr/070709076</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/CSF-2807-2022</idno>
              <idno type="VIAF">https://viaf.org/viaf/6686337</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/CSF-2807-2022</idno>
              <affiliation ref="#struct-408311"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sylvain</forename>
                <surname>Lamprier</surname>
              </persName>
              <email type="md5">942471cad263f780de2404e093709852</email>
              <email type="domain">yahoo.fr</email>
              <idno type="idhal" notation="string">sylvain-lamprier</idno>
              <idno type="idhal" notation="numeric">740402</idno>
              <idno type="halauthorid" notation="string">30958-740402</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-2508-922X</idno>
              <idno type="IDREF">https://www.idref.fr/142632201</idno>
              <idno type="ISNI">http://isni.org/isni/0000000140859141</idno>
              <idno type="VIAF">https://viaf.org/viaf/200144138</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/DYO-1764-2022</idno>
              <affiliation ref="#struct-408311"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ludovic</forename>
                <surname>Denoyer</surname>
              </persName>
              <email type="md5">5a966f98d3670909f62ad2f0e0a0ec3f</email>
              <email type="domain">lip6.fr</email>
              <idno type="idhal" notation="string">ludovic-denoyer</idno>
              <idno type="idhal" notation="numeric">9178</idno>
              <idno type="halauthorid" notation="string">5171-9178</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7348-788X</idno>
              <idno type="IDREF">https://www.idref.fr/089291255</idno>
              <orgName ref="#struct-93591"/>
              <affiliation ref="#struct-408311"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Thibault</forename>
                <surname>Gisselbrecht</surname>
              </persName>
              <email type="md5">7771a8651114b8940820cbb1e005f56e</email>
              <email type="domain">gmail.com</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2016-08-23 13:43:40</date>
              <date type="whenModified">2023-04-11 15:16:28</date>
              <date type="whenReleased">2016-08-23 13:43:40</date>
              <date type="whenProduced">2015-05-26</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="402785">
                <persName>
                  <forename>Thibault</forename>
                  <surname>Gisselbrecht</surname>
                </persName>
                <email type="md5">7771a8651114b8940820cbb1e005f56e</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01355397</idno>
            <idno type="halUri">https://hal.science/hal-01355397</idno>
            <idno type="halBibtex">gisselbrecht:hal-01355397</idno>
            <idno type="halRefHtml">&lt;i&gt;Ninth International Conference on Web and Social Media, ICWSM 2015&lt;/i&gt;, May 2015, Oxford, United Kingdom. pp.130-139</idno>
            <idno type="halRef">Ninth International Conference on Web and Social Media, ICWSM 2015, May 2015, Oxford, United Kingdom. pp.130-139</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UPMC" corresp="SORBONNE-UNIVERSITE">Université Pierre et Marie Curie</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="LIP6" corresp="SORBONNE-UNIVERSITE">Laboratoire d'Informatique de Paris 6</idno>
            <idno type="stamp" n="IRT-SYSTEMX">IRT SystemX</idno>
            <idno type="stamp" n="UPMC_POLE_1" corresp="UPMC">UPMC Pôle 1</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SU-SCIENCES" corresp="SORBONNE-UNIVERSITE">Faculté des Sciences de Sorbonne Université</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</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">WhichStreams: A Dynamic Approach for Focused Data Capture from Large Social Media</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Thibault</forename>
                    <surname>Gisselbrecht</surname>
                  </persName>
                  <email type="md5">7771a8651114b8940820cbb1e005f56e</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="numeric">987816</idno>
                  <idno type="halauthorid" notation="string">1052454-987816</idno>
                  <affiliation ref="#struct-363822"/>
                  <affiliation ref="#struct-408311"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Patrick</forename>
                    <surname>Gallinari</surname>
                  </persName>
                  <email type="md5">d928d788b4143b63dbc87c6175a152be</email>
                  <email type="domain">sorbonne-universite.fr</email>
                  <idno type="idhal" notation="string">patrick-gallinari</idno>
                  <idno type="idhal" notation="numeric">751615</idno>
                  <idno type="halauthorid" notation="string">1778-751615</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-9060-9001</idno>
                  <idno type="IDREF">https://www.idref.fr/070709076</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/CSF-2807-2022</idno>
                  <idno type="VIAF">https://viaf.org/viaf/6686337</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/CSF-2807-2022</idno>
                  <affiliation ref="#struct-408311"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sylvain</forename>
                    <surname>Lamprier</surname>
                  </persName>
                  <email type="md5">942471cad263f780de2404e093709852</email>
                  <email type="domain">yahoo.fr</email>
                  <idno type="idhal" notation="string">sylvain-lamprier</idno>
                  <idno type="idhal" notation="numeric">740402</idno>
                  <idno type="halauthorid" notation="string">30958-740402</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-2508-922X</idno>
                  <idno type="IDREF">https://www.idref.fr/142632201</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000140859141</idno>
                  <idno type="VIAF">https://viaf.org/viaf/200144138</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/DYO-1764-2022</idno>
                  <affiliation ref="#struct-408311"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ludovic</forename>
                    <surname>Denoyer</surname>
                  </persName>
                  <email type="md5">5a966f98d3670909f62ad2f0e0a0ec3f</email>
                  <email type="domain">lip6.fr</email>
                  <idno type="idhal" notation="string">ludovic-denoyer</idno>
                  <idno type="idhal" notation="numeric">9178</idno>
                  <idno type="halauthorid" notation="string">5171-9178</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7348-788X</idno>
                  <idno type="IDREF">https://www.idref.fr/089291255</idno>
                  <orgName ref="#struct-93591"/>
                  <affiliation ref="#struct-408311"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Ninth International Conference on Web and Social Media, ICWSM 2015</title>
                  <date type="start">2015-05-26</date>
                  <date type="end">2015-05-29</date>
                  <settlement>Oxford</settlement>
                  <country key="GB">United Kingdom</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">130-139</biblScope>
                  <date type="datePub">2015-05-26</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halDomain" n="info.info-wb">Computer Science [cs]/Web</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>Due to the huge amount of data produced on large social media, capturing useful content usually implies to focus on subsets of data that fit with a pre-specified need. Considering the usual API restrictions of these media, we formulate this task of focused capture as a dynamic data sources selection problem. We then propose a machine learning methodology, named WhichStreams, which is based on an extension of a recently proposed combinatorial bandit algorithm. The evaluation of our approach on various Twitter datasets, with both offline and online settings, demonstrates the relevance of the proposal for leveraging the real-time data streaming APIs offered by most of the main social media.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-363822" status="VALID">
          <idno type="ROR">https://ror.org/03crmsn52</idno>
          <orgName>IRT SystemX</orgName>
          <desc>
            <address>
              <addrLine>Institut de recherche technologique SystemX - 8 Avenue de la Vauve, 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.irt-systemx.fr/</ref>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-408311" status="OLD">
          <orgName>Machine Learning and Information Access</orgName>
          <orgName type="acronym">MLIA</orgName>
          <date type="start">2013-01-01</date>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-233" type="direct"/>
            <relation active="#struct-93591" type="indirect"/>
            <relation name="UMR7606" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-233" status="OLD">
          <idno type="RNSR">199712651U</idno>
          <idno type="ROR">https://ror.org/05krcen59</idno>
          <orgName>Laboratoire d'Informatique de Paris 6</orgName>
          <orgName type="acronym">LIP6</orgName>
          <date type="start">1997-01-01</date>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>4 Place JUSSIEU 75252 PARIS CEDEX 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lip6.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-93591" type="direct"/>
            <relation name="UMR7606" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-93591" status="OLD">
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Université Pierre et Marie Curie - Paris 6</orgName>
          <orgName type="acronym">UPMC</orgName>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>4 place Jussieu - 75005 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.upmc.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>