<?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-04631257</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="2026-05-24T15:32:37+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Distinguishing Sellers Reported as Scammers on Online Illicit Markets Using Their Language Traces</title>
            <author role="aut">
              <persName>
                <forename type="first">Clara</forename>
                <surname>Degeneve</surname>
              </persName>
              <idno type="idhal" notation="numeric">1396863</idno>
              <idno type="halauthorid" notation="string">2591890-1396863</idno>
              <idno type="ORCID">https://orcid.org/0009-0002-1751-3657</idno>
              <affiliation ref="#struct-97916"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Julien</forename>
                <surname>Longhi</surname>
              </persName>
              <email type="md5">7bfa47ab4ab97a6717c8b59dbb668671</email>
              <email type="domain">u-cergy.fr</email>
              <idno type="idhal" notation="string">julien-longhi</idno>
              <idno type="idhal" notation="numeric">7150</idno>
              <idno type="halauthorid" notation="string">12740-7150</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4134-9888</idno>
              <idno type="IDREF">https://www.idref.fr/121884074</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=KKt7T4kAAAAJ</idno>
              <idno type="VIAF">https://viaf.org/viaf/59411639</idno>
              <idno type="ISNI">http://isni.org/isni/0000000041699461</idno>
              <affiliation ref="#struct-1003543"/>
              <affiliation ref="#struct-1003493"/>
              <affiliation ref="#struct-1003413"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Quentin</forename>
                <surname>Rossy</surname>
              </persName>
              <idno type="idhal" notation="numeric">1396864</idno>
              <idno type="halauthorid" notation="string">2591891-1396864</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-6906-4422</idno>
              <affiliation ref="#struct-97916"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Julien</forename>
                <surname>Longhi</surname>
              </persName>
              <email type="md5">c9e8a0c891d8210579054d347ae16bd9</email>
              <email type="domain">cyu.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-07-02 14:35:00</date>
              <date type="whenModified">2025-03-21 09:56:02</date>
              <date type="whenReleased">2024-07-03 13:59:56</date>
              <date type="whenProduced">2024-06-28</date>
              <date type="whenEndEmbargoed">2024-07-02</date>
              <ref type="file" target="https://hal.science/hal-04631257v1/document">
                <date notBefore="2024-07-02"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-04631257v1/file/languages-09-00235.pdf" id="file-4632262-4021090">
                <date notBefore="2024-07-02"/>
              </ref>
              <ref type="externalLink" target="https://doi.org/10.3390/languages9070235"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="115837">
                <persName>
                  <forename>Julien</forename>
                  <surname>Longhi</surname>
                </persName>
                <email type="md5">c9e8a0c891d8210579054d347ae16bd9</email>
                <email type="domain">cyu.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04631257</idno>
            <idno type="halUri">https://hal.science/hal-04631257</idno>
            <idno type="halBibtex">degeneve:hal-04631257</idno>
            <idno type="halRefHtml">&lt;i&gt;Languages&lt;/i&gt;, 2024, 9 (7), pp.235. &lt;a target="_blank" href="https://dx.doi.org/10.3390/languages9070235"&gt;&amp;#x27E8;10.3390/languages9070235&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Languages, 2024, 9 (7), pp.235. &amp;#x27E8;10.3390/languages9070235&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4632262-4021090"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-CERGY">Université de Cergy Pontoise</idno>
            <idno type="stamp" n="CY-TECH-SM" corresp="UNIV-CERGY">CY TECH : Sciences de la modélisation</idno>
            <idno type="stamp" n="AGORA-CY" corresp="UNIV-CERGY">Laboratoire AGORA</idno>
            <idno type="stamp" n="CY-ART-HUMANITES" corresp="UNIV-CERGY">CY : Art &amp; Humanités</idno>
            <idno type="stamp" n="IDHN" corresp="UNIV-CERGY">Institut des humanités numériques</idno>
            <idno type="stamp" n="CY-MAISON-SHS" corresp="UNIV-CERGY">CY : MAISON-SHS</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">Distinguishing Sellers Reported as Scammers on Online Illicit Markets Using Their Language Traces</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Clara</forename>
                    <surname>Degeneve</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1396863</idno>
                  <idno type="halauthorid" notation="string">2591890-1396863</idno>
                  <idno type="ORCID">https://orcid.org/0009-0002-1751-3657</idno>
                  <affiliation ref="#struct-97916"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Julien</forename>
                    <surname>Longhi</surname>
                  </persName>
                  <email type="md5">7bfa47ab4ab97a6717c8b59dbb668671</email>
                  <email type="domain">u-cergy.fr</email>
                  <idno type="idhal" notation="string">julien-longhi</idno>
                  <idno type="idhal" notation="numeric">7150</idno>
                  <idno type="halauthorid" notation="string">12740-7150</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4134-9888</idno>
                  <idno type="IDREF">https://www.idref.fr/121884074</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=KKt7T4kAAAAJ</idno>
                  <idno type="VIAF">https://viaf.org/viaf/59411639</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000041699461</idno>
                  <affiliation ref="#struct-1003543"/>
                  <affiliation ref="#struct-1003493"/>
                  <affiliation ref="#struct-1003413"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Quentin</forename>
                    <surname>Rossy</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1396864</idno>
                  <idno type="halauthorid" notation="string">2591891-1396864</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-6906-4422</idno>
                  <affiliation ref="#struct-97916"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">152869</idno>
                <idno type="eissn">2226-471X</idno>
                <title level="j">Languages</title>
                <imprint>
                  <publisher> MDPI</publisher>
                  <biblScope unit="volume">9</biblScope>
                  <biblScope unit="issue">7</biblScope>
                  <biblScope unit="pp">235</biblScope>
                  <date type="datePub">2024-06-28</date>
                </imprint>
              </monogr>
              <idno type="doi">10.3390/languages9070235</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">cryptomarket; fraud; scammer; language trace; forensic linguistic</term>
              </keywords>
              <classCode scheme="halDomain" n="scco.ling">Cognitive science/Linguistics</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>Fraud exists on both legitimate e-commerce platforms and illicit dark web marketplaces, impacting both environments. Detecting fraudulent vendors proves challenging, despite clients’ reporting scams to platform administrators and specialised forums. This study introduces a method to differentiate sellers reported as scammers from others by analysing linguistic patterns in their textual traces collected from three distinct cryptomarkets (White House Market, DarkMarket, and Empire Market). It distinguished between potential scammers and reputable sellers based on claims made by Dread forum users. Vendor profiles and product descriptions were then subjected to textometric analysis for raw text and N-gram analysis for pre-processed text. Textual statistics showed no significant differences between profile descriptions and ads, which suggests the need to combine language traces with transactional traces. Textometric indicators, however, were useful in identifying unique ads in which potential scammers used longer, detailed descriptions, including purchase rules and refund policies, to build trust. These indicators aided in choosing relevant documents for qualitative analysis. A pronounced, albeit modest, emphasis on language related to ‘Quality and Price’, ‘Problem Resolution, Communicationand Trust’, and ‘Shipping’ was observed. This supports the hypothesis that scammers may more frequently provide details about transactions and delivery issues. Selective scamming and exit scams may explain the results. Consequently, an analysis of the temporal trajectory of vendors that sheds light on the developmental patterns of their profiles up until their recognition as scammers can be envisaged.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-97916" status="VALID">
          <idno type="IdRef">027525031</idno>
          <idno type="ROR">https://ror.org/019whta54</idno>
          <orgName>Université de Lausanne = University of Lausanne</orgName>
          <orgName type="acronym">UNIL</orgName>
          <date type="start">1537-01-01</date>
          <desc>
            <address>
              <addrLine>CH-1015 Lausanne</addrLine>
              <country key="CH"/>
            </address>
            <ref type="url">http://www.hec.unil.ch/</ref>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-1003543" status="VALID">
          <idno type="IdRef">230880789</idno>
          <idno type="RNSR">201822858X</idno>
          <idno type="ROR">https://ror.org/03eqwt088</idno>
          <orgName>Institut des Humanités numériques</orgName>
          <orgName type="acronym">IDHN</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>8 Boulevard de l'Oise 95000 CERGY</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.u-cergy.fr/fr/laboratoires/idhn.html</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1003474" type="direct"/>
            <relation active="#struct-265277" type="indirect"/>
            <relation name="UMR8051" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1003413" type="indirect"/>
            <relation name="EA 7518" active="#struct-1003481" type="direct"/>
            <relation name="EA 7518" active="#struct-1003413" type="indirect"/>
            <relation name="EA 4112" active="#struct-1003483" type="direct"/>
            <relation name="EA4113" active="#struct-1003413" type="indirect"/>
            <relation name="EA 7392" active="#struct-1003493" type="direct"/>
            <relation name="EA7392" active="#struct-1003413" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1003493" status="VALID">
          <idno type="IdRef">03432187X</idno>
          <idno type="RNSR">201421657J</idno>
          <idno type="ROR">https://ror.org/05mzs1s34</idno>
          <orgName>Laboratoire AGORA</orgName>
          <orgName type="acronym">AGORA - EA 7392</orgName>
          <date type="start">2019-10-29</date>
          <desc>
            <address>
              <addrLine>Université de Cergy-Pontoise - Chênes I - 33 Boulevard du port 95011 Cergy</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cyu.fr/laboratoire-de-recherche-civilisation-identites-culturelles-textes-et-francophonies</ref>
          </desc>
          <listRelation>
            <relation name="EA7392" active="#struct-1003413" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1003413" status="VALID">
          <idno type="IdRef">241871808</idno>
          <idno type="ROR">https://ror.org/043htjv09</idno>
          <orgName>CY Cergy Paris Université</orgName>
          <orgName type="acronym">CY</orgName>
          <date type="start">2019-10-29</date>
          <desc>
            <address>
              <addrLine>33 boulevard du port, 95015 Cergy-Pontoise Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cyu.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-1003474" status="VALID">
          <idno type="IdRef">129737623</idno>
          <idno type="RNSR">200212719W</idno>
          <idno type="ROR">https://ror.org/0592ata02</idno>
          <orgName>Equipes Traitement de l'Information et Systèmes</orgName>
          <orgName type="acronym">ETIS - UMR 8051</orgName>
          <date type="start">2019-10-29</date>
          <desc>
            <address>
              <addrLine>6, avenue du Ponceau. F 95014 CERGY-PONTOISE CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.etis-lab.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-265277" type="direct"/>
            <relation name="UMR8051" active="#struct-441569" type="direct"/>
            <relation active="#struct-1003413" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-265277" status="VALID">
          <idno type="ROR">https://ror.org/03qeacd72</idno>
          <orgName>Ecole Nationale Supérieure de l'Electronique et de ses Applications</orgName>
          <orgName type="acronym">ENSEA</orgName>
          <desc>
            <address>
              <addrLine>6 avenue du Ponceau - CS 20 707 Cergy - 95014 Cergy-Pontoise Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ensea.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="laboratory" xml:id="struct-1003481" status="VALID">
          <idno type="IdRef">232461791</idno>
          <idno type="RNSR">201822859Y</idno>
          <idno type="ROR">https://ror.org/059zr1469</idno>
          <orgName>Lexiques, Textes, Discours, Dictionnaire - Centre Jean Pruvost</orgName>
          <orgName type="acronym">LT2D</orgName>
          <date type="start">2019-10-29</date>
          <desc>
            <address>
              <addrLine>CY LT2DCY Cergy Paris UniversitéSite Chênes 233, boulevard du Port95011 Cergy-Pontoise Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://lt2d.cyu.fr/</ref>
          </desc>
          <listRelation>
            <relation name="EA 7518" active="#struct-1003413" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1003483" status="VALID">
          <idno type="IdRef">157566641</idno>
          <idno type="RNSR">200615357W</idno>
          <orgName>Laboratoire Mobilités, Réseaux, Territoires, Environnements</orgName>
          <orgName type="acronym">MRTE - EA 4112</orgName>
          <date type="start">2019-10-29</date>
          <date type="end">2022-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Cergy-Pontoise U.F.R. Lettres et Sciences humaines 33 boulevard du Port 95011 Cergy-Pontoise Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.u-cergy.fr/fr/recherche-et-valorisation/laboratoires/mrte.html</ref>
          </desc>
          <listRelation>
            <relation name="EA4113" active="#struct-1003413" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>