<?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-03205149</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="2026-05-15T06:44:39+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Sentiment analysis and machine learning in finance: a comparison of methods and models on one million messages</title>
            <author role="aut">
              <persName>
                <forename type="first">Thomas</forename>
                <surname>Renault</surname>
              </persName>
              <email type="md5">a9515c2628d77efa4ea524682756aceb</email>
              <email type="domain">univ-paris1.fr</email>
              <idno type="idhal" notation="string">thomas-renault</idno>
              <idno type="idhal" notation="numeric">1093377</idno>
              <idno type="halauthorid" notation="string">1503616-1093377</idno>
              <idno type="IDREF">https://www.idref.fr/233314903</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4838-4755</idno>
              <idno type="GOOGLE SCHOLAR">uACrv00AAAAJ</idno>
              <affiliation ref="#struct-15080"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Thomas</forename>
                <surname>Renault</surname>
              </persName>
              <email type="md5">a9515c2628d77efa4ea524682756aceb</email>
              <email type="domain">univ-paris1.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-04-22 09:59:12</date>
              <date type="whenModified">2024-03-01 10:57:43</date>
              <date type="whenReleased">2021-04-22 09:59:12</date>
              <date type="whenProduced">2020-09</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="499458">
                <persName>
                  <forename>Thomas</forename>
                  <surname>Renault</surname>
                </persName>
                <email type="md5">a9515c2628d77efa4ea524682756aceb</email>
                <email type="domain">univ-paris1.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03205149</idno>
            <idno type="halUri">https://hal.science/hal-03205149</idno>
            <idno type="halBibtex">renault:hal-03205149</idno>
            <idno type="halRefHtml">&lt;i&gt;Digital Finance&lt;/i&gt;, 2020, 2 (1-2), pp.1-13. &lt;a target="_blank" href="https://dx.doi.org/10.1007/s42521-019-00014-x"&gt;&amp;#x27E8;10.1007/s42521-019-00014-x&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Digital Finance, 2020, 2 (1-2), pp.1-13. &amp;#x27E8;10.1007/s42521-019-00014-x&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SHS">Sciences de l'Homme et de la Société</idno>
            <idno type="stamp" n="UNIV-PARIS1">Université Panthéon-Sorbonne - Paris I</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="CES" corresp="SHS">Centre d'Economie de la Sorbonne</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">Sentiment analysis and machine learning in finance: a comparison of methods and models on one million messages</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Thomas</forename>
                    <surname>Renault</surname>
                  </persName>
                  <email type="md5">a9515c2628d77efa4ea524682756aceb</email>
                  <email type="domain">univ-paris1.fr</email>
                  <idno type="idhal" notation="string">thomas-renault</idno>
                  <idno type="idhal" notation="numeric">1093377</idno>
                  <idno type="halauthorid" notation="string">1503616-1093377</idno>
                  <idno type="IDREF">https://www.idref.fr/233314903</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4838-4755</idno>
                  <idno type="GOOGLE SCHOLAR">uACrv00AAAAJ</idno>
                  <affiliation ref="#struct-15080"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">138004</idno>
                <idno type="issn">2524-6984</idno>
                <idno type="eissn">2524-6186</idno>
                <title level="j">Digital Finance</title>
                <imprint>
                  <publisher>Springer</publisher>
                  <biblScope unit="volume">2</biblScope>
                  <biblScope unit="issue">1-2</biblScope>
                  <biblScope unit="pp">1-13</biblScope>
                  <date type="datePub">2020-09</date>
                  <date type="dateEpub">2019-09-08</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/s42521-019-00014-x</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Social media</term>
                <term xml:lang="en">StockTwits</term>
                <term xml:lang="en">Sentiment analysis</term>
                <term xml:lang="en">Machine learning</term>
                <term xml:lang="en">Asset pricing</term>
              </keywords>
              <classCode scheme="jel" n="G.G1.G10">G - Financial Economics/G.G1 - General Financial Markets/G.G1.G10 - General</classCode>
              <classCode scheme="jel" n="G.G1.G12">G - Financial Economics/G.G1 - General Financial Markets/G.G1.G12 - Asset Pricing • Trading Volume • Bond Interest Rates</classCode>
              <classCode scheme="jel" n="G.G1.G14">G - Financial Economics/G.G1 - General Financial Markets/G.G1.G14 - Information and Market Efficiency • Event Studies • Insider Trading</classCode>
              <classCode scheme="halDomain" n="qfin">Quantitative Finance [q-fin]</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>We use a large dataset of one million messages sent on the microblogging platform StockTwits to evaluate the performance of a wide range of preprocessing methods and machine learning algorithms for sentiment analysis in finance. We find that adding bigrams and emojis significantly improve sentiment classification performance. However, more complex and time-consuming machine learning methods, such as random forests or neural networks, do not improve the accuracy of the classification. We also provide empirical evidence that the preprocessing method and the size of the dataset have a strong impact on the correlation between investor sentiment and stock returns. While investor sentiment and stock returns are highly correlated, we do not find that investor sentiment derived from messages sent on social media helps in predicting large capitalization stocks return at a daily frequency.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-15080" status="VALID">
          <idno type="IdRef">116552077</idno>
          <idno type="RNSR">200612823S</idno>
          <idno type="ROR">https://ror.org/006shqv80</idno>
          <orgName>Centre d'économie de la Sorbonne</orgName>
          <orgName type="acronym">CES</orgName>
          <date type="start">2006-01-01</date>
          <desc>
            <address>
              <addrLine>Maison des Sciences Économiques - 106-112 Boulevard de l'Hôpital - 75647 Paris Cedex 13</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://centredeconomiesorbonne.cnrs.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR8174" active="#struct-7550" type="direct"/>
            <relation name="UMR8174" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-7550" status="VALID">
          <idno type="IdRef">027361802</idno>
          <idno type="ISNI">000000012173743X</idno>
          <idno type="ROR">https://ror.org/002t25c44</idno>
          <orgName>Université Paris 1 Panthéon-Sorbonne</orgName>
          <orgName type="acronym">UP1</orgName>
          <desc>
            <address>
              <addrLine>12 place du Panthéon, 75231 Paris Cedex 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.pantheonsorbonne.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>