<ddi:DDIInstance xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="ddi:instance:3_3 http://ddialliance.org/Specification/DDI-Lifecycle/3.3/XMLSchema/instance.xsd" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:ddi="ddi:instance:3_3" xmlns:r="ddi:reusable:3_3" xmlns:s="ddi:studyunit:3_3" xmlns:d="ddi:datacollection:3_3" xmlns:a="ddi:archive:3_3" xmlns:c="ddi:conceptualcomponent:3_3" xmlns:cm="ddi:comparative:3_3" xmlns:g="ddi:group:3_3" xmlns:l="ddi:logicalproduct:3_3" xmlns:p="ddi:physicaldataproduct:3_3" xmlns:pi="ddi:physicalinstance:3_3" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xhtml="http://www.w3.org/1999/xhtml" xmlns:xml="http://www.w3.org/XML/1998/namespace" isMaintainable="true" scopeOfUniqueness="Agency">
  <r:URN>urn:ddi:se.researchdata:2023-254:1</r:URN>
  <r:Agency>SND</r:Agency>
  <r:ID>2023-254</r:ID>
  <r:Version>1</r:Version>
  <g:ResourcePackage>
    <r:URN>urn:ddi:se.researchdata:2023-254.ResourcePackage:2.0</r:URN>
    <r:OtherMaterialScheme>
      <r:URN>urn:ddi:se.researchdata:2023-254.OtherMaterialScheme:2.0</r:URN>
    </r:OtherMaterialScheme>
    <a:OrganizationScheme>
      <r:URN>urn:ddi:se.researchdata:2023-254.OrganizationScheme-0:2.0</r:URN>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:2023-254.Individual-0:2.0</r:URN>
        <r:UserAttributePair>
          <r:AttributeKey>affiliation</r:AttributeKey>
          <r:AttributeValue>Department of Medical Sciences, Uppsala University</r:AttributeValue>
        </r:UserAttributePair>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FirstGiven>Gabriel</a:FirstGiven>
            <a:LastFamily>Westman</a:LastFamily>
            <a:FullName>
              <r:String>Gabriel Westman</r:String>
            </a:FullName>
          </a:IndividualName>
          <a:ResearcherID>
            <a:TypeOfID>ORCID</a:TypeOfID>
            <a:ResearcherIdentification>0000-0001-9402-772X</a:ResearcherIdentification>
          </a:ResearcherID>
        </a:IndividualIdentification>
      </a:Individual>
    </a:OrganizationScheme>
  </g:ResourcePackage>
  <s:StudyUnit>
    <r:URN>urn:ddi:se.researchdata:2023-254.StudyUnit:2.0</r:URN>
    <r:UserID typeOfUserID="datasetIdentifier">2023-254</r:UserID>
    <r:Citation>
      <r:Title>
        <r:String xml:lang="sv">Web-scraped EMA guidelines and European Public Assessment Reports</r:String>
        <r:String xml:lang="en">Web-scraped EMA guidelines and European Public Assessment Reports</r:String>
      </r:Title>
      <r:Creator>
        <r:CreatorReference>
          <r:URN>urn:ddi:se.researchdata:2023-254.Individual-0:2.0</r:URN>
          <r:TypeOfObject>Individual</r:TypeOfObject>
        </r:CreatorReference>
      </r:Creator>
      <r:Publisher>
        <r:PublisherName>
          <r:String xml:lang="sv">Uppsala universitet</r:String>
          <r:String xml:lang="en">Uppsala University</r:String>
        </r:PublisherName>
      </r:Publisher>
      <r:Publisher>
        <r:PublisherName>
          <r:String xml:lang="sv">Uppsala universitet</r:String>
          <r:String xml:lang="en">Uppsala University</r:String>
        </r:PublisherName>
      </r:Publisher>
      <r:PublicationDate>
        <r:SimpleDate>2023-11-27</r:SimpleDate>
      </r:PublicationDate>
      <r:InternationalIdentifier>
        <r:IdentifierContent>10.57804/wa37-j878</r:IdentifierContent>
        <r:ManagingAgency controlledVocabularyAgencyName="DOI">DOI</r:ManagingAgency>
      </r:InternationalIdentifier>
    </r:Citation>
    <r:Abstract>
      <r:Content xml:lang="sv">Detta datapaket innehåller data och python-kod som ligger till grund för publikationen "A full-document analysis of the semantic relation between European Public Assessment Reports and EMA guidelines using a BERT language model" (Bergman et al, PLOS ONE 2023).

Databasen innehåller metadata och fulltext från 669 st EMA Scientific guidelines och 1024 EMA European Public Assessment Reports.</r:Content>
      <r:Content xml:lang="en">This submission consists of the data and python code that supports the original research article "A full-document analysis of the semantic relation between European Public Assessment Reports and EMA guidelines using a BERT language model" (Bergman et al, PLOS ONE 2023).

The database contains metadata and fulltext from 669 EMA Scientific guidelines and 1024 EMA European Public Assessment Reports.</r:Content>
    </r:Abstract>
    <r:Coverage>
      <r:TopicalCoverage>
        <r:URN>urn:ddi:se.researchdata:2023-254.TopicalCoverage:2.0</r:URN>
        <r:Subject xml:lang="en" controlledVocabularyID="301" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Basic Medicine</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="301" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Medicinska och farmaceutiska grundvetenskaper</r:Subject>
        <r:Keyword xml:lang="en" controlledVocabularyID="urn:ddi:int.cessda.elsst:482e42ce-7ce5-4a31-b7dd-632d6fdc7df8:4" controlledVocabularyName="ELSST">DRUG THERAPY</r:Keyword>
        <r:Keyword xml:lang="sv" controlledVocabularyID="urn:ddi:int.cessda.elsst:482e42ce-7ce5-4a31-b7dd-632d6fdc7df8:4" controlledVocabularyName="ELSST">LÄKEMEDELSTERAPI</r:Keyword>
        <r:Keyword xml:lang="en" controlledVocabularyID="p6069" controlledVocabularyName="YSO">computational linguistics</r:Keyword>
        <r:Keyword xml:lang="sv" controlledVocabularyID="p6069" controlledVocabularyName="YSO">datalingvistik</r:Keyword>
      </r:TopicalCoverage>
      <r:SpatialCoverage />
      <r:TemporalCoverage>
        <r:URN>urn:ddi:se.researchdata:2023-254.TemporalCoverage:2.0</r:URN>
        <r:ReferenceDate>
          <r:StartDate>2008-01-01</r:StartDate>
          <r:EndDate>2022-12-31</r:EndDate>
        </r:ReferenceDate>
      </r:TemporalCoverage>
    </r:Coverage>
    <r:AnalysisUnit controlledVocabularyID="AnalysisUnit" controlledVocabularyAgencyName="DDI Alliance">MediaUnit.Text<r:ControlledVocabularyURN>http://rdf-vocabulary.ddialliance.org/cv/AnalysisUnit/2.1.3/45ab7c1</r:ControlledVocabularyURN></r:AnalysisUnit>
    <r:AnalysisUnitsCovered>
      <r:String xml:lang="en">Media unit: Text</r:String>
      <r:String xml:lang="sv">Mediaenhet: Text</r:String>
    </r:AnalysisUnitsCovered>
    <a:Archive>
      <r:URN>urn:ddi:se.researchdata:2023-254.Archive:2.0</r:URN>
      <a:ArchiveSpecific>
        <a:Item>
          <a:Access>
            <r:URN>urn:ddi:se.researchdata:2023-254.Archive-ArchiveSpecificType-AccessType:2.0</r:URN>
            <a:TypeOfAccess controlledVocabularyName="info:eu-repo-Access-Terms vocabulary">openAccess</a:TypeOfAccess>
          </a:Access>
          <a:DataFileQuantity>6</a:DataFileQuantity>
        </a:Item>
      </a:ArchiveSpecific>
    </a:Archive>
  </s:StudyUnit>
</ddi:DDIInstance>