<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">Arabisk e-bokskorpus</titl>
        <parTitl xml:lang="en">The Arabic E-Book Corpus</parTitl>
        <IDNo agency="SND">doi-10-23695-xwz6-jv19-0</IDNo>
        <IDNo agency="DOI">https://doi.org/10.23695/XWZ6-JV19</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/10.23695/XWZ6-JV19">Landing page</holdings>
    </citation>
  </docDscr>
  <stdyDscr>
    <citation>
      <titlStmt>
        <titl xml:lang="sv">Arabisk e-bokskorpus</titl>
        <parTitl xml:lang="en">The Arabic E-Book Corpus</parTitl>
        <IDNo agency="SND">doi-10-23695-xwz6-jv19-0</IDNo>
        <IDNo agency="DOI">https://doi.org/10.23695/XWZ6-JV19</IDNo>
      </titlStmt>
      <rspStmt>
        <AuthEnty xml:lang="en" affiliation="">Språkbanken Text</AuthEnty>
      </rspStmt>
      <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="2025-09-12" />
      </distStmt>
      <verStmt>
        <version elementVersion="0" elementVersionDate="2025-09-12" />
      </verStmt>
      <holdings URI="https://doi.org/10.23695/XWZ6-JV19">Landing page</holdings>
    </citation>
    <stdyInfo>
      <subject />
      <abstract xml:lang="en" contentType="abstract">The Arabic E-Book Corpus is a freely available collection of 1,745 books (81.5 million words) published in by the Hindawi foundation between 2008 and 2024. The books are of various genres, including non-fiction, novels, children's literature, poetry, and plays. The corpus is provided in two versions: html and unformatted plain text. The latter version will be appropriate for most purposes.
For additional detail, see Hallberg, A. (2025). An 81-million-word multi-genre corpus of Arabic books. Data in Brief, 60, 111456.
The corpus is also available for download in HTML format or unformatted plain text.</abstract>
      <abstract xml:lang="sv" contentType="abstract">Arabisk e-bokskorpus är en fritt tillgänglig samling av 1 745 böcker på arabiska, publicerade av Hindawi Foundation mellan 2008 och 2024. Böckerna är av olika genrer, bland annat, facktext, romaner, barnlitteratur, poesi och pjäser.
För ytterligare detaljer, se Hallberg, A. (2025). An 81-million-word multi-genre corpus of Arabic books. Data in Brief, 60, 111456.
Korpusen finns även tillgänglig för nedladdning i HTML-format och icke-formaterad ren text.</abstract>
      <sumDscr />
    </stdyInfo>
    <method>
      <dataColl />
    </method>
    <dataAccs>
      <useStmt>
        <restrctn xml:lang="en">Access to data through an external actor. </restrctn>
        <restrctn xml:lang="sv">Åtkomst till data via extern aktör. </restrctn>
      </useStmt>
    </dataAccs>
    <othrStdyMat />
  </stdyDscr>
</codeBook>