<?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-02424279</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="2026-05-11T15:16:21+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Data quality in ETL process: A preliminary study</title>
            <author role="aut">
              <persName>
                <forename type="first">Manel</forename>
                <surname>Souibgui</surname>
              </persName>
              <email type="md5">58412e20b880f7ef008d983aea225778</email>
              <email type="domain">fst.utm.tn</email>
              <idno type="idhal" notation="string">manel-souibgui</idno>
              <idno type="idhal" notation="numeric">742781</idno>
              <idno type="halauthorid" notation="string">51991-742781</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-9252-9750</idno>
              <idno type="IDREF">https://www.idref.fr/266982794</idno>
              <affiliation ref="#struct-253759"/>
              <affiliation ref="#struct-16574"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Faten</forename>
                <surname>Atigui</surname>
              </persName>
              <email type="md5">69128ba965515a7f93ffaf4f664fc82a</email>
              <email type="domain">cnam.fr</email>
              <idno type="idhal" notation="string">faten-atigui</idno>
              <idno type="idhal" notation="numeric">182255</idno>
              <idno type="halauthorid" notation="string">25296-182255</idno>
              <idno type="IDREF">https://www.idref.fr/175044333</idno>
              <idno type="ORCID">https://orcid.org/0009-0000-1100-5489</idno>
              <affiliation ref="#struct-16574"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Saloua</forename>
                <surname>Zammali</surname>
              </persName>
              <idno type="halauthorid">722014-0</idno>
              <affiliation ref="#struct-253759"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Samira</forename>
                <surname>Si-Said Cherfi</surname>
              </persName>
              <email type="md5">b42fffd76515c57a510f5d0d3b1afb18</email>
              <email type="domain">cnam.fr</email>
              <idno type="idhal" notation="string">samira-si-said-cherfi</idno>
              <idno type="idhal" notation="numeric">181035</idno>
              <idno type="halauthorid" notation="string">24779-181035</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-5989-5529</idno>
              <idno type="IDREF">https://www.idref.fr/120166798</idno>
              <affiliation ref="#struct-392824"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sadok Ben</forename>
                <surname>Yahia</surname>
              </persName>
              <idno type="halauthorid">857034-0</idno>
              <affiliation ref="#struct-253759"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Samira</forename>
                <surname>Si-Said Cherfi</surname>
              </persName>
              <email type="md5">b42fffd76515c57a510f5d0d3b1afb18</email>
              <email type="domain">cnam.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-01-09 10:38:47</date>
              <date type="whenModified">2025-07-09 15:06:18</date>
              <date type="whenReleased">2020-01-15 10:59:17</date>
              <date type="whenProduced">2019-09-04</date>
              <date type="whenEndEmbargoed">2020-01-09</date>
              <ref type="file" target="https://hal.science/hal-02424279v1/document">
                <date notBefore="2020-01-09"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-02424279v1/file/1-s2.0-S1877050919314097-main.pdf" id="file-2433488-2320037">
                <date notBefore="2020-01-09"/>
              </ref>
              <ref type="externalLink" target="https://doi.org/10.1016/j.procs.2019.09.223"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="175492">
                <persName>
                  <forename>Samira</forename>
                  <surname>Si-Said Cherfi</surname>
                </persName>
                <email type="md5">b42fffd76515c57a510f5d0d3b1afb18</email>
                <email type="domain">cnam.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02424279</idno>
            <idno type="halUri">https://hal.science/hal-02424279</idno>
            <idno type="halBibtex">souibgui:hal-02424279</idno>
            <idno type="halRefHtml">&lt;i&gt;23rd International Conference on Knowledge-Based and Intelligent Information and Engineering Systems&lt;/i&gt;, Sep 2019, Budapest, Hungary. pp.676-687, &lt;a target="_blank" href="https://dx.doi.org/10.1016/j.procs.2019.09.223"&gt;&amp;#x27E8;10.1016/j.procs.2019.09.223&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">23rd International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, Sep 2019, Budapest, Hungary. pp.676-687, &amp;#x27E8;10.1016/j.procs.2019.09.223&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by-nc-nd/4.0/">CC BY-NC-ND 4.0 - Attribution - Non-commercial use - No Derivative Works<ref corresp="#file-2433488-2320037"/></licence>
            </availability>
          </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="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">Data quality in ETL process: A preliminary study</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Manel</forename>
                    <surname>Souibgui</surname>
                  </persName>
                  <email type="md5">58412e20b880f7ef008d983aea225778</email>
                  <email type="domain">fst.utm.tn</email>
                  <idno type="idhal" notation="string">manel-souibgui</idno>
                  <idno type="idhal" notation="numeric">742781</idno>
                  <idno type="halauthorid" notation="string">51991-742781</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-9252-9750</idno>
                  <idno type="IDREF">https://www.idref.fr/266982794</idno>
                  <affiliation ref="#struct-253759"/>
                  <affiliation ref="#struct-16574"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Faten</forename>
                    <surname>Atigui</surname>
                  </persName>
                  <email type="md5">69128ba965515a7f93ffaf4f664fc82a</email>
                  <email type="domain">cnam.fr</email>
                  <idno type="idhal" notation="string">faten-atigui</idno>
                  <idno type="idhal" notation="numeric">182255</idno>
                  <idno type="halauthorid" notation="string">25296-182255</idno>
                  <idno type="IDREF">https://www.idref.fr/175044333</idno>
                  <idno type="ORCID">https://orcid.org/0009-0000-1100-5489</idno>
                  <affiliation ref="#struct-16574"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Saloua</forename>
                    <surname>Zammali</surname>
                  </persName>
                  <idno type="halauthorid">722014-0</idno>
                  <affiliation ref="#struct-253759"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Samira</forename>
                    <surname>Si-Said Cherfi</surname>
                  </persName>
                  <email type="md5">b42fffd76515c57a510f5d0d3b1afb18</email>
                  <email type="domain">cnam.fr</email>
                  <idno type="idhal" notation="string">samira-si-said-cherfi</idno>
                  <idno type="idhal" notation="numeric">181035</idno>
                  <idno type="halauthorid" notation="string">24779-181035</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-5989-5529</idno>
                  <idno type="IDREF">https://www.idref.fr/120166798</idno>
                  <affiliation ref="#struct-392824"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sadok Ben</forename>
                    <surname>Yahia</surname>
                  </persName>
                  <idno type="halauthorid">857034-0</idno>
                  <affiliation ref="#struct-253759"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Procedia Computer Science</title>
                <meeting>
                  <title>23rd International Conference on Knowledge-Based and Intelligent Information and Engineering Systems</title>
                  <date type="start">2019-09-04</date>
                  <date type="end">2019-09-06</date>
                  <settlement>Budapest</settlement>
                  <country key="HU">Hungary</country>
                </meeting>
                <imprint>
                  <publisher>Elsevier</publisher>
                  <biblScope unit="volume">159</biblScope>
                  <biblScope unit="pp">676-687</biblScope>
                  <date type="datePub">2019-09-04</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1016/j.procs.2019.09.223</idno>
              <ref type="publisher">http://kes2019.kesinternational.org</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Business Intelligence &amp; Analytics</term>
                <term xml:lang="en">ETL quality</term>
                <term xml:lang="en">Data and process quality</term>
                <term xml:lang="en">Talend Data Integration</term>
                <term xml:lang="en">Talend Data Quality</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-oh">Computer Science [cs]/Other [cs.OH]</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 accuracy and relevance of Business Intelligence &amp; Analytics (BI&amp;A) rely on the ability to bring high data quality to the data warehouse from both internal and external sources using the ETL process. The latter is complex and time-consuming as it manages data with heterogeneous content and diverse quality problems. Ensuring data quality requires tracking quality defects along the ETL process. In this paper, we present the main ETL quality characteristics. We provide an overview of the existing ETL process data quality approaches. We also present a comparative study of some commercial ETL tools to show how much these tools consider data quality dimensions. To illustrate our study, we carry out experiments using an ETL dedicated solution (Talend Data Integration) and a data quality dedicated solution (Talend Data Quality). Based on our study, we identify and discuss quality challenges to be addressed in our future research.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-253759" status="VALID">
          <orgName>Laboratoire d'Informatique, Programmation, Algorithmique et Heuristique</orgName>
          <orgName type="acronym">LIPAH</orgName>
          <desc>
            <address>
              <addrLine>Faculté des Sciences de Tunis - Université de Tunis El Manar2092 Manar II - Tunis</addrLine>
              <country key="TN"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-481790" type="direct"/>
            <relation active="#struct-207896" type="indirect"/>
          </listRelation>
        </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="researchteam" xml:id="struct-392824" status="VALID">
          <orgName>CEDRIC. Ingénierie des Systèmes d'Information et de Décision</orgName>
          <orgName type="acronym">CEDRIC - ISID</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-16574" type="direct"/>
            <relation name="EA4629" active="#struct-179741" type="indirect"/>
            <relation name="EA4629" active="#struct-300351" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-481790" status="VALID">
          <idno type="IdRef">147476275</idno>
          <orgName>Faculté des Sciences Mathématiques, Physiques et Naturelles de Tunis</orgName>
          <orgName type="acronym">FST</orgName>
          <date type="start">1960-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Tunis El Manar - Campus Universitaire El-Manar, 2092 El Manar Tunis</addrLine>
              <country key="TN"/>
            </address>
            <ref type="url">http://www.fst.rnu.tn/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-207896" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-207896" status="VALID">
          <idno type="IdRef">112859585</idno>
          <idno type="ISNI">0000000122959819</idno>
          <idno type="ROR">https://ror.org/029cgt552</idno>
          <idno type="Wikidata">Q3551684</idno>
          <orgName>Tunis El Manar University [University of Tunis El Manar] [Tunisia] = Université de Tunis El Manar [Tunisie] = جامعة تونس المنار (ar)</orgName>
          <orgName type="acronym">UTM</orgName>
          <date type="start">1987-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Universitaire Farhat Hached B.P. n° 94 - ROMMANA 1068 Tunis</addrLine>
              <country key="TN"/>
            </address>
            <ref type="url">http://www.utm.rnu.tn/</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>