<?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-01239458</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="2026-05-20T11:15:05+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Filtering with the Crowd: CrowdScreen revisited (technical report)</title>
            <author role="aut">
              <persName>
                <forename type="first">Benoît</forename>
                <surname>Groz</surname>
              </persName>
              <email type="md5">a38219368828a5f360bc67bbcf525941</email>
              <email type="domain">crans.org</email>
              <idno type="idhal" notation="string">benoit-groz</idno>
              <idno type="idhal" notation="numeric">3136</idno>
              <idno type="halauthorid" notation="string">972820-3136</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-7292-6409</idno>
              <idno type="IDREF">https://www.idref.fr/169343316</idno>
              <idno type="ISNI">http://isni.org/isni/0000000410267569</idno>
              <idno type="VIAF">https://viaf.org/viaf/304815963</idno>
              <affiliation ref="#struct-115136"/>
              <affiliation ref="#struct-400540"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ezra</forename>
                <surname>Levin</surname>
              </persName>
              <idno type="halauthorid">972821-0</idno>
              <affiliation ref="#struct-115136"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Isaac</forename>
                <surname>Meilijson</surname>
              </persName>
              <idno type="halauthorid">260795-0</idno>
              <affiliation ref="#struct-155803"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Tova</forename>
                <surname>Milo</surname>
              </persName>
              <idno type="halauthorid">126751-0</idno>
              <affiliation ref="#struct-115136"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Benoit</forename>
                <surname>Groz</surname>
              </persName>
              <email type="md5">a38219368828a5f360bc67bbcf525941</email>
              <email type="domain">crans.org</email>
            </editor>
            <funder ref="#projeurop-114634"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2015-12-07 18:02:05</date>
              <date type="whenWritten">2016</date>
              <date type="whenModified">2024-02-13 03:25:16</date>
              <date type="whenReleased">2015-12-08 14:34:13</date>
              <date type="whenProduced">2016-03-15</date>
              <date type="whenEndEmbargoed">2015-12-07</date>
              <ref type="file" target="https://hal.science/hal-01239458v1/document">
                <date notBefore="2015-12-07"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01239458v1/file/glmm-icdt16-long.pdf" id="file-1239458-1317123">
                <date notBefore="2015-12-07"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="141910">
                <persName>
                  <forename>Benoit</forename>
                  <surname>Groz</surname>
                </persName>
                <email type="md5">a38219368828a5f360bc67bbcf525941</email>
                <email type="domain">crans.org</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01239458</idno>
            <idno type="halUri">https://hal.science/hal-01239458</idno>
            <idno type="halBibtex">groz:hal-01239458</idno>
            <idno type="halRefHtml">&lt;i&gt;19th International Conference on Database Theory (ICDT 2016)&lt;/i&gt;, Mar 2016, Bordeaux, France. pp.12:1--12:18, &lt;a target="_blank" href="https://dx.doi.org/10.4230/LIPIcs.ICDT.2016.12"&gt;&amp;#x27E8;10.4230/LIPIcs.ICDT.2016.12&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">19th International Conference on Database Theory (ICDT 2016), Mar 2016, Bordeaux, France. pp.12:1--12:18, &amp;#x27E8;10.4230/LIPIcs.ICDT.2016.12&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-1239458-1317123"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-PSUD">Université Paris Sud - Paris XI</idno>
            <idno type="stamp" n="OPENAIRE">OpenAIRE</idno>
            <idno type="stamp" n="UMR8623">Laboratoire de Recherche en Informatique</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="LRI-LAHDAK" corresp="UMR8623">Publications de l'équipe LaHDAK du LRI</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="UNIV-PSUD-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris Sud pour Paris Saclay</idno>
            <idno type="stamp" n="CENTRALESUPELEC-SACLAY" corresp="UNIV-PARIS-SACLAY">CENTRALESUPELEC-SACLAY</idno>
            <idno type="stamp" n="LISN">Laboratoire Interdisciplinaire des Sciences du Numérique</idno>
            <idno type="stamp" n="GS-ENGINEERING">Graduate School Sciences de l'Ingénierie et des Systèmes</idno>
            <idno type="stamp" n="GS-COMPUTER-SCIENCE">Graduate School Computer Science</idno>
            <idno type="stamp" n="LISN-LAHDAK" corresp="LISN">Données et Connaissances Massives et Hétérogènes </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">Filtering with the Crowd: CrowdScreen revisited (technical report)</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Benoît</forename>
                    <surname>Groz</surname>
                  </persName>
                  <email type="md5">a38219368828a5f360bc67bbcf525941</email>
                  <email type="domain">crans.org</email>
                  <idno type="idhal" notation="string">benoit-groz</idno>
                  <idno type="idhal" notation="numeric">3136</idno>
                  <idno type="halauthorid" notation="string">972820-3136</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-7292-6409</idno>
                  <idno type="IDREF">https://www.idref.fr/169343316</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000410267569</idno>
                  <idno type="VIAF">https://viaf.org/viaf/304815963</idno>
                  <affiliation ref="#struct-115136"/>
                  <affiliation ref="#struct-400540"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ezra</forename>
                    <surname>Levin</surname>
                  </persName>
                  <idno type="halauthorid">972821-0</idno>
                  <affiliation ref="#struct-115136"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Isaac</forename>
                    <surname>Meilijson</surname>
                  </persName>
                  <idno type="halauthorid">260795-0</idno>
                  <affiliation ref="#struct-155803"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Tova</forename>
                    <surname>Milo</surname>
                  </persName>
                  <idno type="halauthorid">126751-0</idno>
                  <affiliation ref="#struct-115136"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>19th International Conference on Database Theory (ICDT 2016)</title>
                  <date type="start">2016-03-15</date>
                  <date type="end">2016-03-18</date>
                  <settlement>Bordeaux</settlement>
                  <country key="FR">France</country>
                </meeting>
                <editor>Wim Martens</editor>
                <editor>Thomas Zeume</editor>
                <imprint>
                  <publisher>Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik</publisher>
                  <biblScope unit="serie">19th International Conference on Database Theory, {ICDT} 2016, Bordeaux,                France, March 15-18, 2016</biblScope>
                  <biblScope unit="volume">48</biblScope>
                  <biblScope unit="pp">12:1--12:18</biblScope>
                  <date type="datePub">2016</date>
                </imprint>
              </monogr>
              <idno type="doi">10.4230/LIPIcs.ICDT.2016.12</idno>
              <ref type="publisher">http://www.dagstuhl.de/dagpub/978-3-95977-002-6</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="acm" n="H.3.3.1">H.: Information Systems/H.3: INFORMATION STORAGE AND RETRIEVAL/H.3.3: Information Search and Retrieval/H.3.3.1: Information filtering</classCode>
              <classCode scheme="halDomain" n="info.info-db">Computer Science [cs]/Databases [cs.DB]</classCode>
              <classCode scheme="halDomain" n="info.info-ds">Computer Science [cs]/Data Structures and Algorithms [cs.DS]</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>Filtering a set of items, based on a set of properties that can be verified by humans, is a common application of CrowdSourcing. When the workers are error-prone, each item is presented to multiple users, to limit the probability of misclassification. Since the Crowd is a relatively expensive resource, minimizing the number of questions per item may naturally result in big savings. Several algorithms to address this minimization problem have been presented in the CrowdScreen framework by Parameswaran et al. However, those algorithms do not scale well and therefore cannot be used in scenarios where high accuracy is required in spite of high user error rates. The goal of this paper is thus to devise algorithms that can cope with such situations. To achieve this, we provide new theoretical insights to the problem, then use them to develop a new efficient algorithm. We also propose novel optimizations for the algorithms of CrowdScreen that improve their scalability. We complement our theoretical study by an experimental evaluation of the algorithms on a large set of synthetic parameters as well as real-life crowdsourcing scenarios, demonstrating the advantages of our solution.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-115136" status="VALID">
          <orgName>School of Computer Science</orgName>
          <orgName type="acronym">TAU-CS</orgName>
          <desc>
            <address>
              <addrLine>Schreiber Building, Tel Aviv University, P.O.B. 39040, Ramat Aviv, Tel Aviv 69978</addrLine>
              <country key="IL"/>
            </address>
            <ref type="url">http://www.cs.tau.ac.il/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-63133" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-400540" status="OLD">
          <orgName>Données et Connaissances Massives et Hétérogènes (LRI)</orgName>
          <orgName type="acronym">LaHDAK - LRI</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Université Paris-Sud ; Bât. 650 Lovelace ; 91405 Orsay Cedex</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-2544" type="direct"/>
            <relation active="#struct-92966" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation name="UMR8623" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-155803" status="VALID">
          <orgName>School of Mathematical Sciences [Tel Aviv]</orgName>
          <orgName type="acronym">TAU</orgName>
          <desc>
            <address>
              <addrLine>Raymond and Beverly Sackler | Faculty of Exact Sciences |Tel Aviv University, 69978 Israel</addrLine>
              <country key="IL"/>
            </address>
            <ref type="url">https://en-exact-sciences.tau.ac.il/math</ref>
          </desc>
          <listRelation>
            <relation active="#struct-173023" type="direct"/>
            <relation active="#struct-63133" type="indirect"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-63133" status="VALID">
          <idno type="ROR">https://ror.org/04mhzgx49</idno>
          <orgName>Tel Aviv University</orgName>
          <orgName type="acronym">TAU</orgName>
          <desc>
            <address>
              <addrLine>Tel Aviv 699780</addrLine>
              <country key="IL"/>
            </address>
            <ref type="url">https://english.tau.ac.il/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-2544" status="OLD">
          <idno type="RNSR">199812948M</idno>
          <orgName>Laboratoire de Recherche en Informatique</orgName>
          <orgName type="acronym">LRI</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>LRI - Bâtiments 650-660 Université Paris-Sud 91405 Orsay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lri.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-92966" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation name="UMR8623" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-92966" status="OLD">
          <idno type="ROR">https://ror.org/028rypz17</idno>
          <orgName>Université Paris-Sud - Paris 11</orgName>
          <orgName type="acronym">UP11</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment 300 - 91405 Orsay cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-psud.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.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="institution" xml:id="struct-173023" status="VALID">
          <orgName>Raymond and Beverly Sackler Faculty of Exact Sciences [Tel Aviv]</orgName>
          <orgName type="acronym">TAU</orgName>
          <desc>
            <address>
              <addrLine>Tel Aviv University - Tel Aviv 69978 Israel</addrLine>
              <country key="IL"/>
            </address>
            <ref type="url">https://en-exact-sciences.tau.ac.il/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-63133" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="europeanProject" xml:id="projeurop-114634" status="VALID">
          <idno type="number">291071</idno>
          <idno type="program">ERC-2011-ADG_20110209</idno>
          <idno type="call">ERC-2011-ADG_20110209</idno>
          <orgName>MODAS</orgName>
          <desc>Mob Data Sourcing</desc>
          <date type="start">2012-01-04</date>
          <date type="end">2018-03-31</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>