<codeBook xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xsi:schemaLocation="ddi:codebook:2_5 http://www.ddialliance.org/Specification/DDI-Codebook/2.5/XMLSchema/codebook.xsd" xmlns="ddi:codebook:2_5">
  <docDscr>
    <citation>
      <titlStmt>
        <titl xml:lang="sv">Developing a rule-based method for identifying researchers on Twitter: The case of vaccine discussions</titl>
        <parTitl xml:lang="en">Developing a rule-based method for identifying researchers on Twitter: The case of vaccine discussions</parTitl>
        <IDNo agency="SND">snd1117-1-1.0</IDNo>
        <IDNo agency="hb.se">FO2017/23</IDNo>
        <IDNo agency="DOI">https://doi.org/10.5878/akmc-va16</IDNo>
      </titlStmt>
      <prodStmt>
        <producer xml:lang="en" abbr="SND">Swedish National Data Service</producer>
        <producer xml:lang="sv" abbr="SND">Svensk nationell datatjänst</producer>
      </prodStmt>
      <holdings URI="https://doi.org/10.5878/akmc-va16">Landing page</holdings>
    </citation>
  </docDscr>
  <stdyDscr>
    <citation>
      <titlStmt>
        <titl xml:lang="sv">Developing a rule-based method for identifying researchers on Twitter: The case of vaccine discussions</titl>
        <parTitl xml:lang="en">Developing a rule-based method for identifying researchers on Twitter: The case of vaccine discussions</parTitl>
        <IDNo agency="SND">snd1117-1-1.0</IDNo>
        <IDNo agency="hb.se">FO2017/23</IDNo>
        <IDNo agency="DOI">https://doi.org/10.5878/akmc-va16</IDNo>
      </titlStmt>
      <rspStmt />
      <prodStmt>
        <grantNo xml:lang="en" agency="Horizon 2020">770531</grantNo>
        <grantNo xml:lang="sv" agency="Horizon 2020">770531</grantNo>
      </prodStmt>
      <distStmt>
        <distrbtr xml:lang="en" abbr="SND" URI="https://snd.se">Swedish National Data Service</distrbtr>
        <distrbtr xml:lang="sv" abbr="SND" URI="https://snd.se">Svensk nationell datatjänst</distrbtr>
        <distDate xml:lang="en" date="2019-08-23" />
      </distStmt>
      <verStmt>
        <version elementVersion="1.0" elementVersionDate="2019-08-23" />
      </verStmt>
      <holdings URI="https://doi.org/10.5878/akmc-va16">Landing page</holdings>
    </citation>
    <stdyInfo>
      <subject>
        <keyword xml:lang="en" vocab="GEMET" vocabURI="http://www.eionet.europa.eu/gemet/concept/1447">classification</keyword>
        <keyword xml:lang="sv" vocab="GEMET" vocabURI="http://www.eionet.europa.eu/gemet/concept/1447">klassifikation</keyword>
        <topcClas xml:lang="en" vocab="CESSDA Topic Classification" vocabURI="https://vocabularies.cessda.eu/vocabulary/TopicClassification?code=MediaCommunicationAndLanguage.InformationSociety">Information society</topcClas>
        <topcClas xml:lang="sv" vocab="CESSDA Topic Classification" vocabURI="https://vocabularies.cessda.eu/vocabulary/TopicClassification?code=MediaCommunicationAndLanguage.InformationSociety">Informationssamhället</topcClas>
        <topcClas xml:lang="en" vocab="CESSDA Topic Classification" vocabURI="https://vocabularies.cessda.eu/vocabulary/TopicClassification?code=MediaCommunicationAndLanguage.LanguageAndLinguistics">Language and linguistics</topcClas>
        <topcClas xml:lang="sv" vocab="CESSDA Topic Classification" vocabURI="https://vocabularies.cessda.eu/vocabulary/TopicClassification?code=MediaCommunicationAndLanguage.LanguageAndLinguistics">Språk och lingvistik</topcClas>
        <topcClas xml:lang="en" vocab="CESSDA Topic Classification" vocabURI="https://vocabularies.cessda.eu/vocabulary/TopicClassification?code=Education.HigherAndFurtherEducation">Higher and further education</topcClas>
        <topcClas xml:lang="sv" vocab="CESSDA Topic Classification" vocabURI="https://vocabularies.cessda.eu/vocabulary/TopicClassification?code=Education.HigherAndFurtherEducation">Gymnasial och högre utbildning</topcClas>
      </subject>
      <abstract xml:lang="en" contentType="abstract">This study seeks to develop a method for identifying the occurrences and proportions of researchers, media and other professionals active in Twitter discussions. As a case example, an anonymised dataset from Twitter vaccine discussions is used. The study proposes a method of using keywords as strings within lists to identify classes from user biographies. This provides a way to apply multiple classification principles to a set of Twitter biographies using semantic rules through the Python programming language. The script used for the study is here deposited.

Method development for Twitter biography classification concerning occurrences of academics, academically related groups and individuals, media, other groups and members of the general public. Written in the Python programming language.</abstract>
      <abstract xml:lang="sv" contentType="abstract">Denna studie söker utveckla en metod för att identifiera förekomster och proportioner av forskare, media- och andra professionella aktiva i Twitterdiskussioner. Som ett fallexempel används ett anonymiserat dataset från vaccindiskussioner på Twitter. Studien föreslår en metod som använder nyckelord som strängar inom listor för att identifiera klasser ifrån användarbiografier. Detta möjliggör en applicering av multipla klassifikationsprinciper till en mängd Twitterbiografier genom att använda semantiska regler genom programmeringsspråket Python. Det skript som använts för att genomföra studien är här deponerat.

Metodutveckling för klassning av Twitterbiografier rörande förekomster av akademiker, grupper och individer relaterade till akademi, media, andra grupper samt allmänhet. Skriven i programmeringsspråket Python.</abstract>
      <sumDscr>
        <anlyUnit xml:lang="en" unit="Group">Group<concept vocab="DDI Analysis Unit" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/AnalysisUnit/2.1.3?languageVersion=en-2.1.3">Group</concept></anlyUnit>
        <anlyUnit xml:lang="sv" unit="Grupp">Grupp<concept vocab="DDI Analysis Unit" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/AnalysisUnit/2.1.3?languageVersion=sv-2.1.3">Grupp</concept></anlyUnit>
        <anlyUnit xml:lang="en" unit="Individual">Individual<concept vocab="DDI Analysis Unit" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/AnalysisUnit/2.1.3?languageVersion=en-2.1.3">Individual</concept></anlyUnit>
        <anlyUnit xml:lang="sv" unit="Individ">Individ<concept vocab="DDI Analysis Unit" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/AnalysisUnit/2.1.3?languageVersion=sv-2.1.3">Individ</concept></anlyUnit>
        <anlyUnit xml:lang="en" unit="Organization/Institution">Organization/Institution<concept vocab="DDI Analysis Unit" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/AnalysisUnit/2.1.3?languageVersion=en-2.1.3">Organization/Institution</concept></anlyUnit>
        <anlyUnit xml:lang="sv" unit="Organisation/institution">Organisation/institution<concept vocab="DDI Analysis Unit" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/AnalysisUnit/2.1.3?languageVersion=sv-2.1.3">Organisation/institution</concept></anlyUnit>
        <anlyUnit xml:lang="en" unit="Other">Other<concept vocab="DDI Analysis Unit" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/AnalysisUnit/2.1.3?languageVersion=en-2.1.3">Other</concept></anlyUnit>
        <anlyUnit xml:lang="sv" unit="Övrigt">Övrigt<concept vocab="DDI Analysis Unit" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/AnalysisUnit/2.1.3?languageVersion=sv-2.1.3">Övrigt</concept></anlyUnit>
        <universe xml:lang="en">Twitter users</universe>
        <universe xml:lang="sv">Twitteranvändare</universe>
        <dataKind xml:lang="en">Software</dataKind>
      </sumDscr>
    </stdyInfo>
    <method>
      <dataColl>
        <timeMeth xml:lang="en">Other<concept vocab="DDI Time Method" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/TimeMethod/1.2.3?languageVersion=en-1.2.3">Other</concept></timeMeth>
        <timeMeth xml:lang="sv">Övrigt<concept vocab="DDI Time Method" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/TimeMethod/1.2.3?languageVersion=sv-1.2.3">Övrigt</concept></timeMeth>
        <sampProc xml:lang="en">Other<concept vocab="DDI Sampling Procedure" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/SamplingProcedure/2.0.1?languageVersion=en-2.0.1">Other</concept></sampProc>
        <sampProc xml:lang="sv">Övrigt<concept vocab="DDI Sampling Procedure" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/SamplingProcedure/2.0.1?languageVersion=sv-2.0.1">Övrigt</concept></sampProc>
      </dataColl>
    </method>
    <dataAccs>
      <useStmt>
        <restrctn xml:lang="en">Access to data through SND. Data are freely accessible.</restrctn>
        <restrctn xml:lang="sv">Åtkomst till data via SND. Data är fritt tillgängliga.</restrctn>
        <conditions elementVersion="info:eu-repo-Access-Terms vocabulary">openAccess</conditions>
      </useStmt>
    </dataAccs>
    <othrStdyMat>
      <relPubl>
        <citation>
          <titlStmt>
            <titl xml:lang="sv">Ekström, B. (2019). Developing a rule-based method for identifying researchers on Twitter: The case of vaccine discussions. Poster abstract accepted to ISSI, 17th International Society of Scientometrics and Informetrics Conference, Rome, 2-5 September.</titl>
            <parTitl xml:lang="en">Ekström, B. (2019). Developing a rule-based method for identifying researchers on Twitter: The case of vaccine discussions. Poster abstract accepted to ISSI, 17th International Society of Scientometrics and Informetrics Conference, Rome, 2-5 September.</parTitl>
          </titlStmt>
          <distStmt>
            <distDate date="2019">2019</distDate>
          </distStmt>
        </citation>
      </relPubl>
    </othrStdyMat>
  </stdyDscr>
</codeBook>