<?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-04927904</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="2026-05-20T10:08:08+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Can natural language processing or large language models replace human operators for pre-processing word and sentence-based free comments sensory evaluation data?</title>
            <author role="crp">
              <persName>
                <forename type="first">Michel</forename>
                <surname>Visalli</surname>
              </persName>
              <email type="md5">e124944211e8b22da1aec8a6ebf5d3b2</email>
              <email type="domain">inrae.fr</email>
              <idno type="idhal" notation="string">michel-visalli</idno>
              <idno type="idhal" notation="numeric">748692</idno>
              <idno type="halauthorid" notation="string">50279-748692</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7286-396X</idno>
              <affiliation ref="#struct-1229375"/>
              <affiliation ref="#struct-1175514"/>
              <affiliation ref="#struct-1229376"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ronan</forename>
                <surname>Symoneaux</surname>
              </persName>
              <email type="md5">95c1b56dbb71ffc9004b5ee06cdc3057</email>
              <email type="domain">groupe-esa.com</email>
              <idno type="idhal" notation="string">ronan-symoneaux</idno>
              <idno type="idhal" notation="numeric">1560027</idno>
              <idno type="halauthorid" notation="string">293825-1560027</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-6792-8629</idno>
              <affiliation ref="#struct-1031200"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Cécile</forename>
                <surname>Mursic</surname>
              </persName>
              <idno type="halauthorid">3302312-0</idno>
              <affiliation ref="#struct-1221520"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Margaux</forename>
                <surname>Touret</surname>
              </persName>
              <idno type="halauthorid">3358017-0</idno>
              <affiliation ref="#struct-1221520"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Flore</forename>
                <surname>Lourtioux</surname>
              </persName>
              <idno type="halauthorid">1874967-0</idno>
              <affiliation ref="#struct-1031200"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Kipédène</forename>
                <surname>Coulibaly</surname>
              </persName>
              <email type="md5">f282d0b44ad90740392bcce8b943245d</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">kipedene-coulibaly</idno>
              <idno type="idhal" notation="numeric">1407098</idno>
              <idno type="halauthorid" notation="string">3212856-1407098</idno>
              <idno type="ORCID">https://orcid.org/0009-0006-4889-0067</idno>
              <affiliation ref="#struct-1229375"/>
              <affiliation ref="#struct-1229376"/>
              <affiliation ref="#struct-1175514"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Benjamin</forename>
                <surname>Mahieu</surname>
              </persName>
              <email type="md5">767de5b70c6d48a4ef96b0ccc4c3127b</email>
              <email type="domain">oniris-nantes.fr</email>
              <idno type="idhal" notation="string">benjamin-mahieu</idno>
              <idno type="idhal" notation="numeric">1484987</idno>
              <idno type="halauthorid" notation="string">1865245-1484987</idno>
              <idno type="IDREF">https://www.idref.fr/238474151</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0057-1615</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/FJQ-0090-2022</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/FJQ-0090-2022</idno>
              <affiliation ref="#struct-302936"/>
              <affiliation ref="#struct-1066619"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Michel</forename>
                <surname>Visalli</surname>
              </persName>
              <email type="md5">e124944211e8b22da1aec8a6ebf5d3b2</email>
              <email type="domain">inrae.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-02-04 07:41:44</date>
              <date type="whenModified">2026-05-05 13:36:02</date>
              <date type="whenReleased">2025-02-04 07:41:44</date>
              <date type="whenProduced">2025-06</date>
              <fs>
                <f name="inra_etatDocument_local" notation="numeric">
                  <numeric>0</numeric>
                </f>
                <f name="inra_etatDocument_local" notation="string" n="0">
                  <string>inra_etatDocument_local_0</string>
                </f>
                <f name="inra_publicVise_local" notation="string" n="SC">
                  <string>inra_publicVise_local_SC</string>
                </f>
              </fs>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1044758">
                <persName>
                  <forename>Michel</forename>
                  <surname>Visalli</surname>
                </persName>
                <email type="md5">e124944211e8b22da1aec8a6ebf5d3b2</email>
                <email type="domain">inrae.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04927904</idno>
            <idno type="halUri">https://hal.science/hal-04927904</idno>
            <idno type="halBibtex">visalli:hal-04927904</idno>
            <idno type="halRefHtml">&lt;i&gt;Food Quality and Preference&lt;/i&gt;, 2025, 127, pp.105456. &lt;a target="_blank" href="https://dx.doi.org/10.1016/j.foodqual.2025.105456"&gt;&amp;#x27E8;10.1016/j.foodqual.2025.105456&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Food Quality and Preference, 2025, 127, pp.105456. &amp;#x27E8;10.1016/j.foodqual.2025.105456&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-BOURGOGNE">Université Bourgogne Europe</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="CSGA" corresp="UNIV-BOURGOGNE">Centre des Sciences du Goût et de l'Alimentation</idno>
            <idno type="stamp" n="UNAM">l'unam - université nantes angers le mans</idno>
            <idno type="stamp" n="AGREENIUM">Archive ouverte en agrobiosciences</idno>
            <idno type="stamp" n="INRAE">Institut National de Recherche en Agriculture, Alimentation et Environnement</idno>
            <idno type="stamp" n="ALIMH">Département Alimentation Humaine</idno>
            <idno type="stamp" n="RESEAU-EAU">Réseau "Systèmes Agricoles et Eau"</idno>
            <idno type="stamp" n="INSTITUT-AGRO">Institut Agro</idno>
            <idno type="stamp" n="ONIRIS">École nationale vétérinaire, agroalimentaire et de l'alimentation de Nantes-Atlantique (Oniris)</idno>
            <idno type="stamp" n="STATSC" corresp="ONIRIS">Statistique Sensométrie et Chimiométrie</idno>
            <idno type="stamp" n="GROUPE-ESA">École Supérieure des Agricultures (ESA)</idno>
            <idno type="stamp" n="GRAPPE-ESA">UMR GRAPPE Groupe de Recherche en Agroalimentaire sur les Produits et les Procédés</idno>
            <idno type="stamp" n="CALIS">Consommateur-ALIment-Santé</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Can natural language processing or large language models replace human operators for pre-processing word and sentence-based free comments sensory evaluation data?</title>
                <author role="crp">
                  <persName>
                    <forename type="first">Michel</forename>
                    <surname>Visalli</surname>
                  </persName>
                  <email type="md5">e124944211e8b22da1aec8a6ebf5d3b2</email>
                  <email type="domain">inrae.fr</email>
                  <idno type="idhal" notation="string">michel-visalli</idno>
                  <idno type="idhal" notation="numeric">748692</idno>
                  <idno type="halauthorid" notation="string">50279-748692</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7286-396X</idno>
                  <affiliation ref="#struct-1229375"/>
                  <affiliation ref="#struct-1175514"/>
                  <affiliation ref="#struct-1229376"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ronan</forename>
                    <surname>Symoneaux</surname>
                  </persName>
                  <email type="md5">95c1b56dbb71ffc9004b5ee06cdc3057</email>
                  <email type="domain">groupe-esa.com</email>
                  <idno type="idhal" notation="string">ronan-symoneaux</idno>
                  <idno type="idhal" notation="numeric">1560027</idno>
                  <idno type="halauthorid" notation="string">293825-1560027</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-6792-8629</idno>
                  <affiliation ref="#struct-1031200"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Cécile</forename>
                    <surname>Mursic</surname>
                  </persName>
                  <idno type="halauthorid">3302312-0</idno>
                  <affiliation ref="#struct-1221520"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Margaux</forename>
                    <surname>Touret</surname>
                  </persName>
                  <idno type="halauthorid">3358017-0</idno>
                  <affiliation ref="#struct-1221520"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Flore</forename>
                    <surname>Lourtioux</surname>
                  </persName>
                  <idno type="halauthorid">1874967-0</idno>
                  <affiliation ref="#struct-1031200"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Kipédène</forename>
                    <surname>Coulibaly</surname>
                  </persName>
                  <email type="md5">f282d0b44ad90740392bcce8b943245d</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">kipedene-coulibaly</idno>
                  <idno type="idhal" notation="numeric">1407098</idno>
                  <idno type="halauthorid" notation="string">3212856-1407098</idno>
                  <idno type="ORCID">https://orcid.org/0009-0006-4889-0067</idno>
                  <affiliation ref="#struct-1229375"/>
                  <affiliation ref="#struct-1229376"/>
                  <affiliation ref="#struct-1175514"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Benjamin</forename>
                    <surname>Mahieu</surname>
                  </persName>
                  <email type="md5">767de5b70c6d48a4ef96b0ccc4c3127b</email>
                  <email type="domain">oniris-nantes.fr</email>
                  <idno type="idhal" notation="string">benjamin-mahieu</idno>
                  <idno type="idhal" notation="numeric">1484987</idno>
                  <idno type="halauthorid" notation="string">1865245-1484987</idno>
                  <idno type="IDREF">https://www.idref.fr/238474151</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0057-1615</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/FJQ-0090-2022</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/FJQ-0090-2022</idno>
                  <affiliation ref="#struct-302936"/>
                  <affiliation ref="#struct-1066619"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">13408</idno>
                <idno type="issn">0950-3293</idno>
                <title level="j">Food Quality and Preference</title>
                <imprint>
                  <publisher>Elsevier</publisher>
                  <biblScope unit="volume">127</biblScope>
                  <biblScope unit="pp">105456</biblScope>
                  <date type="datePub">2025-06</date>
                  <date type="dateEpub">2025-02-01</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1016/j.foodqual.2025.105456</idno>
              <idno type="wos">001423561600001</idno>
              <ref target="https://doi.org/10.1016/j.foodqual.2025.105456" type="seeAlso"/>
              <ref type="publisher">https://www.sciencedirect.com/science/article/pii/S095032932500031X</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Open ended questions</term>
                <term xml:lang="en">ChatGPT</term>
                <term xml:lang="en">Textual data</term>
                <term xml:lang="en">Consumer test</term>
                <term xml:lang="en">Method comparison</term>
                <term xml:lang="en">Drivers of liking</term>
              </keywords>
              <classCode scheme="halDomain" n="sdv.ida">Life Sciences [q-bio]/Food engineering</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>The free comment (FC) method enables the collection of insights on products based on consumers' natural language. The primary drawback is the need for extensive data pre-processing. This study compared the results of three data pre-processing techniques applied to FC data related to the perception of six madeleines by two panels of 100 consumers: manual pre-processing by four human experts, automated pre-processing by an expert system, and automated pre-processing by the large language model ChatGPT. Two modes of data collection were used: responses only with words or short expressions (“FC words”), or responses based on complete sentences (“FC sentences”). Various indicators (number of words extracted, number of concepts retained, pre-processing time, level of repeatability/discrimination/stability of findings) were computed and compared between data collection modes and pre-processing techniques. It was shown that the automated systems performed correctly with FC words; however, they were less effective at extracting relevant words from FC sentences. The findings from statistical analyses following automated pre-processing were less repeatable and discriminative compared to those from the most proficient human operators. It was also demonstrated that, beyond the overall differences between products, the pre-processing of FC data can be a major source of non-reproducibility in findings, depending on the operators and the level of detail they consider when extracting information. Finally, the advantages and disadvantages of each pre-processing technique were summarized, along with several recommendations for pre-processing and analysing FC data at the appropriate level of granularity to draw robust conclusions.</p>
            </abstract>
            <particDesc>
              <org type="ir" xml:id="fr-esr-fdr-ir-102">
                <orgName type="acronym">CALIS</orgName>
              </org>
              <org type="ir" xml:id="fr-inrae-infra-sci-ir-10">
                <orgName>Platform for Profiling Properties of Food and Biobased Products</orgName>
                <orgName type="acronym">PROBE</orgName>
              </org>
            </particDesc>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1229375" status="VALID">
          <idno type="IdRef">159748593</idno>
          <idno type="ISNI">0000000403872525</idno>
          <idno type="RNSR">201019359D</idno>
          <idno type="ROR">https://ror.org/05s1rff82</idno>
          <orgName>Centre des Sciences du Goût et de l'Alimentation [Dijon]</orgName>
          <orgName type="acronym">CSGA</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>Université Bourgogne Europe - Bât. CSG - 9E Bd Jeanne d'Arc - 21000 Dijon</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://csga.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR6265" active="#struct-441569" type="direct"/>
            <relation name="UMR1324" active="#struct-577435" type="direct"/>
            <relation name="UMR6265" active="#struct-1096329" type="direct"/>
            <relation active="#struct-1042499" type="indirect"/>
            <relation active="#struct-1220685" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1175514" status="VALID">
          <orgName>INRAE, PROBE Research Infrastructure</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-1229376" status="VALID">
          <orgName>Plateforme Chemosens [Dijon]</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>Site Université de BourgogneBât. Centre des Sciences du Goût9E boulevard Jeanne d'Arc21000 Dijon</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.chemosens.inra.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1229375" type="direct"/>
            <relation name="UMR6265" active="#struct-441569" type="indirect"/>
            <relation name="UMR1324" active="#struct-577435" type="indirect"/>
            <relation name="UMR6265" active="#struct-1096329" type="indirect"/>
            <relation active="#struct-1042499" type="indirect"/>
            <relation active="#struct-1220685" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1031200" status="VALID">
          <orgName>Groupe de Recherche en Agroalimentaire sur les Produits et les Procédés</orgName>
          <orgName type="acronym">GRAPPE</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>55, rue Rabelais - BP 30748 49007 ANGERS Cedex 01</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-363639" type="direct"/>
            <relation name="UMR1422" active="#struct-577435" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1221520" status="INCOMING">
          <orgName>Techni'Sens, La Rochelle</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-302936" status="VALID">
          <idno type="ROR">https://ror.org/05q0ncs32</idno>
          <orgName>École nationale vétérinaire, agroalimentaire et de l'alimentation Nantes-Atlantique</orgName>
          <orgName type="acronym">Oniris VetAgroBio</orgName>
          <desc>
            <address>
              <addrLine>101 route de Gachet - 44300 Nantes</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.oniris-nantes.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-1066619" status="VALID">
          <idno type="RNSR">200621270Y</idno>
          <orgName>Statistique, Sensométrie et Chimiométrie</orgName>
          <orgName type="acronym">StatSC</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>INRAE Site de la Géraudièrerue de la Géraudière BP 7162744316 NANTES CEDEX 3</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.oniris-nantes.fr/recherche-1/statsc</ref>
          </desc>
          <listRelation>
            <relation active="#struct-302936" type="direct"/>
            <relation name="USC1381" active="#struct-577435" type="direct"/>
          </listRelation>
        </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-577435" status="VALID">
          <idno type="ROR">https://ror.org/003vg9w96</idno>
          <orgName>Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement</orgName>
          <orgName type="acronym">INRAE</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1096329" status="VALID">
          <idno type="IdRef">261024671</idno>
          <idno type="ROR">https://ror.org/03zek0r74</idno>
          <idno type="Wikidata">Q8077943</idno>
          <orgName>Institut Agro Dijon</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <addrLine>26 Boulevard du Dr Petitjean - BP 87999 - 21079 Dijon cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://institut-agro-dijon.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1042499" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-1042499" status="VALID">
          <idno type="IdRef">260373249</idno>
          <idno type="ROR">https://ror.org/01dkyve95</idno>
          <orgName>Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement</orgName>
          <orgName type="acronym">Institut Agro</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.institut-agro.fr</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-1220685" status="VALID">
          <idno type="IdRef">28258160X</idno>
          <idno type="ROR">https://ror.org/00g700j37</idno>
          <orgName>Université Bourgogne Europe</orgName>
          <orgName type="acronym">UBE</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>Maison de l'université -Esplanade Erasme -BP 27877 - 21078 DIJON Cedex France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ube.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-363639" status="VALID">
          <idno type="ROR">https://ror.org/02vb4k656</idno>
          <orgName>Ecole Supérieure des Agricultures</orgName>
          <orgName type="acronym">ESA</orgName>
          <desc>
            <address>
              <addrLine>Enseignement supérieur et recherche en agriculture, alimentation, territoires et marchés55 Rue Rabelais, 49007 Angers – 02 41 23 55 55</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.groupe-esa.com/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>