<?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-01125867</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="2026-05-24T12:50:24+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Longitudinal Analytics on Web Archive Data: It's About Time!</title>
            <author role="aut">
              <persName>
                <forename type="first">Gerhard</forename>
                <surname>Weikum</surname>
              </persName>
              <idno type="halauthorid">505788-0</idno>
              <affiliation ref="#struct-54489"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Nikos</forename>
                <surname>Ntarmos</surname>
              </persName>
              <idno type="halauthorid">893252-0</idno>
              <affiliation ref="#struct-502478"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mark</forename>
                <surname>Spaniol</surname>
              </persName>
              <idno type="halauthorid">895112-0</idno>
              <affiliation ref="#struct-54489"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Peter</forename>
                <surname>Triantafillou</surname>
              </persName>
              <idno type="halauthorid">793751-0</idno>
              <affiliation ref="#struct-502478"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Scott</forename>
                <surname>Fitzpatrick</surname>
              </persName>
              <idno type="halauthorid">895113-0</idno>
              <affiliation ref="#struct-306968"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Philippe</forename>
                <surname>Rigaux</surname>
              </persName>
              <email type="md5">e00e7ca78b453979a72ba45d5594b697</email>
              <email type="domain">cnam.fr</email>
              <idno type="idhal" notation="string">philippe-rigaux</idno>
              <idno type="idhal" notation="numeric">172888</idno>
              <idno type="halauthorid" notation="string">11800-172888</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-9189-7292</idno>
              <idno type="IDREF">https://www.idref.fr/055149359</idno>
              <affiliation ref="#struct-16574"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Laboratoire</forename>
                <surname>CEDRIC</surname>
              </persName>
              <email type="md5">34e509f884b6168d15336e5a2357ce4c</email>
              <email type="domain">cnam.fr.invalid</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2015-03-06 11:31:15</date>
              <date type="whenWritten">2011-02-01</date>
              <date type="whenModified">2025-07-09 15:06:18</date>
              <date type="whenReleased">2015-03-06 11:31:15</date>
              <date type="whenProduced">2011-02-01</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="308156">
                <persName>
                  <forename>Laboratoire</forename>
                  <surname>CEDRIC</surname>
                </persName>
                <email type="md5">34e509f884b6168d15336e5a2357ce4c</email>
                <email type="domain">cnam.fr.invalid</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01125867</idno>
            <idno type="halUri">https://hal.science/hal-01125867</idno>
            <idno type="halBibtex">weikum:hal-01125867</idno>
            <idno type="halRefHtml">&lt;i&gt;Intl. Conference on Innovative Data Systems Research (CIDR)&lt;/i&gt;, Feb 2011, X, France. pp.199-202</idno>
            <idno type="halRef">Intl. Conference on Innovative Data Systems Research (CIDR), Feb 2011, X, France. pp.199-202</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNAM">Conservatoire National des Arts et Métiers</idno>
            <idno type="stamp" n="CEDRIC-CNAM" corresp="CNAM">Centre d'études et de recherche en informatique et communications </idno>
            <idno type="stamp" n="HESAM-CNAM" corresp="HESAM">Conservatoire National des Arts et Métiers - Hesam</idno>
            <idno type="stamp" n="HESAM">Hesam</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="1">Not set</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">Longitudinal Analytics on Web Archive Data: It's About Time!</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Gerhard</forename>
                    <surname>Weikum</surname>
                  </persName>
                  <idno type="halauthorid">505788-0</idno>
                  <affiliation ref="#struct-54489"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Nikos</forename>
                    <surname>Ntarmos</surname>
                  </persName>
                  <idno type="halauthorid">893252-0</idno>
                  <affiliation ref="#struct-502478"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mark</forename>
                    <surname>Spaniol</surname>
                  </persName>
                  <idno type="halauthorid">895112-0</idno>
                  <affiliation ref="#struct-54489"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Peter</forename>
                    <surname>Triantafillou</surname>
                  </persName>
                  <idno type="halauthorid">793751-0</idno>
                  <affiliation ref="#struct-502478"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Scott</forename>
                    <surname>Fitzpatrick</surname>
                  </persName>
                  <idno type="halauthorid">895113-0</idno>
                  <affiliation ref="#struct-306968"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Philippe</forename>
                    <surname>Rigaux</surname>
                  </persName>
                  <email type="md5">e00e7ca78b453979a72ba45d5594b697</email>
                  <email type="domain">cnam.fr</email>
                  <idno type="idhal" notation="string">philippe-rigaux</idno>
                  <idno type="idhal" notation="numeric">172888</idno>
                  <idno type="halauthorid" notation="string">11800-172888</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-9189-7292</idno>
                  <idno type="IDREF">https://www.idref.fr/055149359</idno>
                  <affiliation ref="#struct-16574"/>
                </author>
              </analytic>
              <monogr>
                <idno type="localRef">WNS11</idno>
                <meeting>
                  <title>Intl. Conference on Innovative Data Systems Research (CIDR)</title>
                  <date type="start">2011-02-01</date>
                  <settlement>X</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">199-202</biblScope>
                  <date type="datePub">2011-02-01</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="info.info-db">Computer Science [cs]/Databases [cs.DB]</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>Organizations like the Internet Archive have been capturing Web contents over decades, building up huge repositories of time-versioned pages. The timestamp annotations and the sheer volume of multi-modal content constitutes a gold mine for analysts of all sorts, across different application areas, from political analysts and marketing agencies to academic researchers and product developers. In contrast to traditional data analytics on click logs, the focus is on longitudinal stud- ies over very long horizons. This longitudinal aspect affects and concerns all data and metadata, from the content itself, to the indices and the statistical metadata maintained for it. Moreover, advanced analysts prefer to deal with semantically rich entities like people, places, organizations, and ideally relationships such as company acquisitions, instead of, say, Web pages containing such references. For example, tracking and analyzing a politician?s public appearances over a decade is much harder than mining frequently used query words or frequently clicked URLs for the last month. The huge size of Web archives adds to the complexity of this daunting task. This paper discusses key challenges, that we intend to take up, which are posed by this kind of longitudinal analytics: time-travel indexing and querying, entity detection and track- ing along the time axis, algorithms for advanced analyses and knowledge discovery, and scalability and platform issues.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-54489" status="VALID">
          <orgName>Max-Planck-Institut für Informatik</orgName>
          <orgName type="acronym">MPII</orgName>
          <desc>
            <address>
              <addrLine>Campus E-1 4, 66123 Saarbrücken, Germany</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">http://www.mpi-inf.mpg.de/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-5247" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-502478" status="VALID">
          <idno type="ROR">https://ror.org/04gnjpq42</idno>
          <orgName>National and Kapodistrian University of Athens</orgName>
          <orgName type="acronym">NKUA</orgName>
          <date type="start">1837-04-14</date>
          <desc>
            <address>
              <addrLine>Athens 157 72</addrLine>
              <country key="GR"/>
            </address>
            <ref type="url">https://en.uoa.gr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-306968" status="VALID">
          <orgName>Affichem</orgName>
          <desc>
            <address>
              <addrLine>Parc technologique du canalCanal Biotech 13 rue des satellites31400 Toulouse - France</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <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="institution" xml:id="struct-5247" status="VALID">
          <orgName>Max-Planck-Gesellschaft</orgName>
          <desc>
            <address>
              <addrLine>Jägerstrasse, 10-11, D-10117 Berlin</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://www.mpg.de/en</ref>
          </desc>
        </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>
      </listOrg>
    </back>
  </text>
</TEI>