<?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-02871345</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="2026-05-14T16:48:09+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A Topic-Based Hidden Markov Model for Real-Time Spam Tweets Filtering</title>
            <author role="aut">
              <persName>
                <forename type="first">Mahdi</forename>
                <surname>Washha</surname>
              </persName>
              <idno type="halauthorid">1378803-0</idno>
              <affiliation ref="#struct-402019"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Aziz</forename>
                <surname>Qaroush</surname>
              </persName>
              <idno type="halauthorid">1378804-0</idno>
              <affiliation ref="#struct-577336"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Manel</forename>
                <surname>Mezghani</surname>
              </persName>
              <email type="md5">52ce76c9e9e1f0a9b47128c7ceef83e4</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="numeric">1165320</idno>
              <idno type="halauthorid" notation="string">909964-1165320</idno>
              <idno type="IDREF">https://www.idref.fr/195589572</idno>
              <affiliation ref="#struct-402019"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Florence</forename>
                <surname>Sèdes</surname>
              </persName>
              <email type="md5">0ffea35bf585ac4c3c1cbd4817e6449b</email>
              <email type="domain">irit.fr</email>
              <idno type="idhal" notation="string">florence-sedes</idno>
              <idno type="idhal" notation="numeric">735498</idno>
              <idno type="halauthorid" notation="string">38932-735498</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-9273-302X</idno>
              <idno type="IDREF">https://www.idref.fr/033232679</idno>
              <orgName ref="#struct-217752"/>
              <affiliation ref="#struct-402019"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Open Archive Toulouse Archive Ouverte</forename>
                <surname>(OATAO)</surname>
              </persName>
              <email type="md5">ac3f71840d50da799c1bb19c7b808bac</email>
              <email type="domain">listes-diff.inp-toulouse.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-06-17 11:20:15</date>
              <date type="whenModified">2025-10-22 18:04:08</date>
              <date type="whenReleased">2020-06-22 10:50:46</date>
              <date type="whenProduced">2017-09-06</date>
              <date type="whenEndEmbargoed">2020-06-17</date>
              <ref type="file" target="https://hal.science/hal-02871345v1/document">
                <date notBefore="2020-06-17"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-02871345v1/file/washha_22076.pdf" id="file-2871345-2524921">
                <date notBefore="2020-06-17"/>
              </ref>
              <ref type="externalLink" target="https://doi.org/10.1016/j.procs.2017.08.075"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="146910">
                <persName>
                  <forename>Open Archive Toulouse Archive Ouverte</forename>
                  <surname>(OATAO)</surname>
                </persName>
                <email type="md5">ac3f71840d50da799c1bb19c7b808bac</email>
                <email type="domain">listes-diff.inp-toulouse.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02871345</idno>
            <idno type="halUri">https://hal.science/hal-02871345</idno>
            <idno type="halBibtex">washha:hal-02871345</idno>
            <idno type="halRefHtml">&lt;i&gt;21st International Conference on Knowledge-Based and Intelligent Information &amp; Engineering Systems (KES 2017)&lt;/i&gt;, Sep 2017, Marseille, France. pp.833-843, &lt;a target="_blank" href="https://dx.doi.org/10.1016/j.procs.2017.08.075"&gt;&amp;#x27E8;10.1016/j.procs.2017.08.075&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">21st International Conference on Knowledge-Based and Intelligent Information &amp; Engineering Systems (KES 2017), Sep 2017, Marseille, France. pp.833-843, &amp;#x27E8;10.1016/j.procs.2017.08.075&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2871345-2524921"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-TLSE2">Université Toulouse 2</idno>
            <idno type="stamp" n="UNIV-TLSE3">Université de Toulouse</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UT1-CAPITOLE">Université Toulouse 1 Capitole</idno>
            <idno type="stamp" n="IRIT">IRIT - Institut de Recherche en Informatique de Toulouse</idno>
            <idno type="stamp" n="IRIT-SIG" corresp="IRIT">Systèmes d’Informations Généralisées</idno>
            <idno type="stamp" n="IRIT-GD" corresp="IRIT">Gestion des Données</idno>
            <idno type="stamp" n="IRIT-UT3">IRIT - Université Toulouse III Paul Sabatier</idno>
            <idno type="stamp" n="TOULOUSE-INP">Toulouse - INP</idno>
            <idno type="stamp" n="UNIV-UT3">Université Toulouse 3</idno>
            <idno type="stamp" n="UT3-INP">Université de Toulouse / Toulouse INP</idno>
            <idno type="stamp" n="UT3-TOULOUSEINP">Université de Toulouse / Toulouse INP</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">A Topic-Based Hidden Markov Model for Real-Time Spam Tweets Filtering</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Mahdi</forename>
                    <surname>Washha</surname>
                  </persName>
                  <idno type="halauthorid">1378803-0</idno>
                  <affiliation ref="#struct-402019"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Aziz</forename>
                    <surname>Qaroush</surname>
                  </persName>
                  <idno type="halauthorid">1378804-0</idno>
                  <affiliation ref="#struct-577336"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Manel</forename>
                    <surname>Mezghani</surname>
                  </persName>
                  <email type="md5">52ce76c9e9e1f0a9b47128c7ceef83e4</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="numeric">1165320</idno>
                  <idno type="halauthorid" notation="string">909964-1165320</idno>
                  <idno type="IDREF">https://www.idref.fr/195589572</idno>
                  <affiliation ref="#struct-402019"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Florence</forename>
                    <surname>Sèdes</surname>
                  </persName>
                  <email type="md5">0ffea35bf585ac4c3c1cbd4817e6449b</email>
                  <email type="domain">irit.fr</email>
                  <idno type="idhal" notation="string">florence-sedes</idno>
                  <idno type="idhal" notation="numeric">735498</idno>
                  <idno type="halauthorid" notation="string">38932-735498</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-9273-302X</idno>
                  <idno type="IDREF">https://www.idref.fr/033232679</idno>
                  <orgName ref="#struct-217752"/>
                  <affiliation ref="#struct-402019"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Proceedings of the 21st International Conference on Knowledge-Based and Intelligent Information &amp; Engineering Systems (KES 2017)</title>
                <meeting>
                  <title>21st International Conference on Knowledge-Based and Intelligent Information &amp; Engineering Systems (KES 2017)</title>
                  <date type="start">2017-09-06</date>
                  <date type="end">2017-09-08</date>
                  <settlement>Marseille</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">833-843</biblScope>
                  <date type="datePub">2017</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1016/j.procs.2017.08.075</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Twitter</term>
                <term xml:lang="en">Real-Time</term>
                <term xml:lang="en">Social Spam</term>
                <term xml:lang="en">Hidden Markov Model</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-si">Computer Science [cs]/Social and Information Networks [cs.SI]</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>Online social networks (OSNs) have become an important source of information for a tremendous range of applications and researches such as search engines, and summarization systems. However, the high usability and accessibility of OSNs have exposed many information quality (IQ) problems which consequently decrease the performance of the OSNs dependent applications. Social spammers are a particular kind of ill-intentioned users who degrade the quality of OSNs information through misusing all possible services provided by OSNs. Social spammers spread many intensive posts/tweets to lure legitimate users to malicious or commercial sites containing malware downloads, phishing, and drug sales. Given the fact that Twitter is not immune towards the social spam problem, different researchers have designed various detection methods which inspect individual tweets or accounts for the existence of spam contents. However, although of the high detection rates of the account-based spam detection methods, these methods are not suitable for filtering tweets in the real-time detection because of the need for information from Twitter’s servers. At tweet spam detection level, many light features have been proposed for real-time filtering; however, the existing classification models separately classify a tweet without considering the state of previous handled tweets associated with a topic. Also, these models periodically require retraining using a ground-truth data to make them up-to-date. Hence, in this paper, we formalize a Hidden Markov Model (HMM) as a time-dependent model for real-time topical spam tweets filtering. More precisely, our method only leverages the available and accessible meta-data in the tweet object to detect spam tweets exiting in a stream of tweets related to a topic (e.g., #Trump), with considering the state of previously handled tweets associated to the same topic. Compared to the classical time-independent classification methods such as Random Forest, the experimental evaluation demonstrates the efficiency of increasing the quality of topics in terms of precision, recall, and F-measure performance metrics.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-402019" status="OLD">
          <orgName>Systèmes d’Informations Généralisées</orgName>
          <orgName type="acronym">IRIT-SIG</orgName>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>IRIT118 Route de Narbonne31062 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.irit.fr/departement/gestion-des-donnees/equipe-sig/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-34499" type="direct"/>
            <relation active="#struct-81148" type="indirect"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="indirect"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation active="#struct-217752" type="indirect"/>
            <relation name="UMR5505 / URA1399" active="#struct-441569" type="indirect"/>
            <relation active="#struct-448187" type="indirect"/>
            <relation active="#struct-1149079" type="indirect"/>
            <relation name="FED4171" active="#struct-217752" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-577336" status="INCOMING">
          <orgName>Birzeit University</orgName>
          <desc>
            <address>
              <addrLine>Ramallah</addrLine>
              <country key="PS"/>
            </address>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-34499" status="OLD">
          <idno type="IdRef">030947448</idno>
          <idno type="ISNI">0000000121927225</idno>
          <idno type="RNSR">199511949P</idno>
          <idno type="ROR">https://ror.org/01rx4qw44</idno>
          <orgName>Institut de recherche en informatique de Toulouse</orgName>
          <orgName type="acronym">IRIT</orgName>
          <date type="start">1990-01-01</date>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>118 Route de Narbonne, F-31062 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.irit.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-81148" type="direct"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation active="#struct-217752" type="direct"/>
            <relation name="UMR5505 / URA1399" active="#struct-441569" type="direct"/>
            <relation active="#struct-448187" type="direct"/>
            <relation active="#struct-1149079" type="direct"/>
            <relation name="FED4171" active="#struct-217752" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-81148" status="VALID">
          <idno type="IdRef">026404354</idno>
          <idno type="ISNI">0000000121902837</idno>
          <idno type="ROR">https://ror.org/0443n9e75</idno>
          <orgName>Université Toulouse Capitole</orgName>
          <orgName type="acronym">UT Capitole</orgName>
          <date type="start">1970-01-01</date>
          <desc>
            <address>
              <addrLine>2 rue du Doyen-Gabriel-Marty - 31042 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ut-capitole.fr/</ref>
          </desc>
          <listRelation>
            <relation name="443875" active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-443875" status="VALID">
          <idno type="ROR">https://ror.org/017tgbk05</idno>
          <orgName>Communauté d'universités et établissements de Toulouse</orgName>
          <orgName type="acronym">Comue de Toulouse</orgName>
          <desc>
            <address>
              <addrLine>41 Allée Jules Guesde, 31000 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-toulouse.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-116256" status="VALID">
          <idno type="IdRef">026403994</idno>
          <idno type="ROR">https://ror.org/04ezk3x31</idno>
          <orgName>Université Toulouse - Jean Jaurès</orgName>
          <orgName type="acronym">UT2J</orgName>
          <date type="start">1971-01-01</date>
          <desc>
            <address>
              <addrLine>5 allées Antonio Machado - 31058 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tlse2.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-217752" status="OLD">
          <idno type="IdRef">026404672</idno>
          <idno type="ISNI">0000000121617331</idno>
          <idno type="ROR">https://ror.org/02v6kpv12</idno>
          <idno type="Wikidata">Q1273188</idno>
          <orgName>Université Toulouse III - Paul Sabatier</orgName>
          <orgName type="acronym">UT3</orgName>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>118 route de Narbonne - 31062 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tlse3.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" 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-448187" status="VALID">
          <idno type="IdRef">026388820</idno>
          <idno type="ISNI">0000000121766169</idno>
          <idno type="ROR">https://ror.org/033p9g875</idno>
          <orgName>Institut National Polytechnique (Toulouse)</orgName>
          <orgName type="acronym">Toulouse INP</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.inp-toulouse.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-1149079" status="OLD">
          <orgName>Toulouse Mind &amp; Brain Institut</orgName>
          <orgName type="acronym">TMBI</orgName>
          <date type="start">2021-01-01</date>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>CHU Purpan, Pavillon Baudot, 31059 Toulouse cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.tmbi.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation name="FED4171" active="#struct-217752" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>