<?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-04862262</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="2026-05-18T12:10:40+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Political-RAG: using generative AI to extract political information from media content</title>
            <author role="aut">
              <persName>
                <forename type="first">Muhammad</forename>
                <surname>Arslan</surname>
              </persName>
              <idno type="idhal" notation="numeric">1413799</idno>
              <idno type="halauthorid" notation="string">38487-1413799</idno>
              <idno type="ORCID">https://orcid.org/0009-0000-5481-0568</idno>
              <affiliation ref="#struct-496957"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Saba</forename>
                <surname>Munawar</surname>
              </persName>
              <idno type="halauthorid">3354406-0</idno>
              <affiliation ref="#struct-422832"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Christophe</forename>
                <surname>Cruz</surname>
              </persName>
              <email type="md5">9b281d38f222ff188707ce927fc046ff</email>
              <email type="domain">u-bourgogne.fr</email>
              <idno type="idhal" notation="string">christophe-cruz</idno>
              <idno type="idhal" notation="numeric">6759</idno>
              <idno type="halauthorid" notation="string">13085-6759</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-5611-9479</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=_0cF3rMAAAAJ&amp;hl=fr&amp;oi=ao</idno>
              <idno type="IDREF">https://www.idref.fr/083343563</idno>
              <affiliation ref="#struct-496957"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Christophe</forename>
                <surname>Cruz</surname>
              </persName>
              <email type="md5">c6468777a241ab20e3f3ef8c4e65b3dc</email>
              <email type="domain">ube.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-01-02 23:57:37</date>
              <date type="whenModified">2025-08-12 18:11:16</date>
              <date type="whenReleased">2025-01-08 13:46:01</date>
              <date type="whenProduced">2024-10-23</date>
              <date type="whenEndEmbargoed">2025-01-02</date>
              <ref type="file" target="https://hal.science/hal-04862262v1/document">
                <date notBefore="2025-01-02"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-04862262v1/file/226.pdf" id="file-4862262-4228643">
                <date notBefore="2025-01-02"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="163587">
                <persName>
                  <forename>Christophe</forename>
                  <surname>Cruz</surname>
                </persName>
                <email type="md5">c6468777a241ab20e3f3ef8c4e65b3dc</email>
                <email type="domain">ube.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04862262</idno>
            <idno type="halUri">https://hal.science/hal-04862262</idno>
            <idno type="halBibtex">arslan:hal-04862262</idno>
            <idno type="halRefHtml">&lt;i&gt;Journal of Information Technology and Politics&lt;/i&gt;, 2024, pp.1 - 16. &lt;a target="_blank" href="https://dx.doi.org/10.1080/19331681.2024.2417263"&gt;&amp;#x27E8;10.1080/19331681.2024.2417263&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Journal of Information Technology and Politics, 2024, pp.1 - 16. &amp;#x27E8;10.1080/19331681.2024.2417263&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4862262-4228643"/></licence>
            </availability>
          </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="UNIV-BM">Université de Technologie de Belfort-Montbeliard</idno>
            <idno type="stamp" n="ICB" corresp="UNIV-BOURGOGNE">Laboratoire Interdisciplinaire Carnot de Bourgogne</idno>
            <idno type="stamp" n="UNIV-BM-THESE">Université de Technologie de Belfort-Montbeliard</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">Political-RAG: using generative AI to extract political information from media content</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Muhammad</forename>
                    <surname>Arslan</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1413799</idno>
                  <idno type="halauthorid" notation="string">38487-1413799</idno>
                  <idno type="ORCID">https://orcid.org/0009-0000-5481-0568</idno>
                  <affiliation ref="#struct-496957"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Saba</forename>
                    <surname>Munawar</surname>
                  </persName>
                  <idno type="halauthorid">3354406-0</idno>
                  <affiliation ref="#struct-422832"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Christophe</forename>
                    <surname>Cruz</surname>
                  </persName>
                  <email type="md5">9b281d38f222ff188707ce927fc046ff</email>
                  <email type="domain">u-bourgogne.fr</email>
                  <idno type="idhal" notation="string">christophe-cruz</idno>
                  <idno type="idhal" notation="numeric">6759</idno>
                  <idno type="halauthorid" notation="string">13085-6759</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-5611-9479</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=_0cF3rMAAAAJ&amp;hl=fr&amp;oi=ao</idno>
                  <idno type="IDREF">https://www.idref.fr/083343563</idno>
                  <affiliation ref="#struct-496957"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">88123</idno>
                <idno type="issn">1933-1681</idno>
                <idno type="eissn">1933-169X</idno>
                <title level="j">Journal of Information Technology and Politics</title>
                <imprint>
                  <publisher>Taylor &amp; Francis</publisher>
                  <biblScope unit="pp">1 - 16</biblScope>
                  <date type="datePub">2024-10-23</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1080/19331681.2024.2417263</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Retrieval-Augmented Generation (RAG)</term>
                <term xml:lang="en">Political events extraction</term>
                <term xml:lang="en">Large Language Models (LLMs)</term>
                <term xml:lang="en">Information Extraction (IE)</term>
                <term xml:lang="en">Natural Language Processing</term>
                <term xml:lang="en">Natural Language Processing Information Extraction (IE) Large Language Models (LLMs) Retrieval-Augmented Generation (RAG) Political events extraction</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</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>In the digital era, media content is crucial for political analysis, providing valuable insights through news articles, social media posts, speeches, and reports. Natural Language Processing (NLP) has transformed Political Information Extraction (IE), automating tasks such as event extraction and sentiment analysis. Traditional NLP methods, while effective, are often task-specific and require specialized expertise. In contrast, Large Language Models (LLMs) powered by Generative Artificial Intelligence (GenAI) offer a more integrated solution. However, domain-specific challenges persist, which led to the development of the Retrieval-Augmented Generation (RAG) framework. RAG enhances LLMs by incorporating external data retrieval, addressing issues related to data availability. To demonstrate RAG's capabilities, we introduce the Political-RAG system, designed to extract political event information from media content, including Twitter data and news articles. Initially developed for event extraction, the Political-RAG system lays the foundation for developing various complex Political IE tasks. These include detecting hate speech, analyzing conflicts, assessing political bias, and evaluating social trends, sentiment, and opinions.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-496957" status="OLD">
          <idno type="IdRef">161048978</idno>
          <idno type="ISNI">0000000099292445</idno>
          <idno type="RNSR">201220440V</idno>
          <idno type="ROR">https://ror.org/02b6c1039</idno>
          <orgName>Laboratoire Interdisciplinaire Carnot de Bourgogne</orgName>
          <orgName type="acronym">ICB</orgName>
          <date type="start">2017-01-01</date>
          <date type="end">2024-12-31</date>
          <desc>
            <address>
              <addrLine>Université de Bourgogne - 9 avenue Alain Savary - BP 47870 - 21078 Dijon Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://icb.u-bourgogne.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300261" type="direct"/>
            <relation active="#struct-300270" type="direct"/>
            <relation active="#struct-426438" type="direct"/>
            <relation name="UMR6303" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-422832" status="VALID">
          <idno type="ROR">https://ror.org/003eyb898</idno>
          <orgName>National University of Computer and Emerging Sciences [Islamabad]</orgName>
          <orgName type="acronym">NUCES</orgName>
          <date type="start">2000-01-01</date>
          <desc>
            <address>
              <addrLine>A.K. Brohi Road, H-11/4Islamabad</addrLine>
              <country key="PK"/>
            </address>
            <ref type="url">http://www.nu.edu.pk/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300261" status="VALID">
          <orgName>Université de Technologie de Belfort-Montbeliard</orgName>
          <orgName type="acronym">UTBM</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300270" status="OLD">
          <idno type="IdRef">02819005X</idno>
          <idno type="ISNI">0000000122989313</idno>
          <idno type="ROR">https://ror.org/03k1bsr36</idno>
          <orgName>Université de Bourgogne</orgName>
          <orgName type="acronym">UB</orgName>
          <date type="end">2024-12-31</date>
          <desc>
            <address>
              <addrLine>Maison de l'université - Esplanade Érasme - BP 27877 - 21078 Dijon cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-bourgogne.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-426438" status="VALID">
          <idno type="IdRef">200716271</idno>
          <idno type="ISNI">0000 0004 4910 6615</idno>
          <idno type="ROR">https://ror.org/02dn7x778</idno>
          <orgName>Université Bourgogne Franche-Comté [COMUE]</orgName>
          <orgName type="acronym">UBFC</orgName>
          <date type="start">2015-04-01</date>
          <date type="end">2024-12-31</date>
          <desc>
            <address>
              <addrLine>32, avenue de l’observatoire25000 BESANCON</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ubfc.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>
      </listOrg>
    </back>
  </text>
</TEI>