Dataset Open Access

Structured citations in the English Wikipedia

Delpeuch, Antonin


DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:cnt="http://www.w3.org/2011/content#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.55004">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Dataset"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.55004</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.55004"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Delpeuch, Antonin</foaf:name>
        <foaf:givenName>Antonin</foaf:givenName>
        <foaf:familyName>Delpeuch</foaf:familyName>
      </rdf:Description>
    </dct:creator>
    <dct:title>Structured citations in the English Wikipedia</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2016</dct:issued>
    <dcat:keyword>wikipedia</dcat:keyword>
    <dcat:keyword>citation</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2016-06-06</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/55004"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/55004</skos:notation>
      </adms:Identifier>
    </adms:identifier>
    <dct:description>&lt;p&gt;This dataset contains the metadata of citations in the English Wikipedia that editors have input as citation templates (which use the Citation Style 1). It has been obtained from an XML dump of Wikipedia (2016-05-01), and was parsed with the wikiciteparser library. This library runs the Lua code used in Wikipedia to format such citations and generate structured metadata (such as COinS) from them.&lt;/p&gt; &lt;p&gt;https://github.com/dissemin/wikiciteparser&lt;/p&gt; &lt;p&gt;Sample:&lt;/p&gt; &lt;blockquote&gt; &lt;p&gt;716551092&amp;nbsp;&amp;nbsp; &amp;nbsp;12&amp;nbsp;&amp;nbsp; &amp;nbsp;2016-04-22T10:19:33Z&amp;nbsp;&amp;nbsp; &amp;nbsp;Anarchism&amp;nbsp;&amp;nbsp; &amp;nbsp;cite journal &amp;nbsp;&amp;nbsp; &amp;nbsp;{&amp;quot;PublisherName&amp;quot;: &amp;quot;International Group of San Francisco&amp;quot;, &amp;quot;Title&amp;quot;: &amp;quot;Towards Anarchism&amp;quot;, &amp;quot;URL&amp;quot;: &amp;quot;http://www.marxists.org/archive/malatesta/1930s/xx/toanarchy.htm&amp;quot;, &amp;quot;Authors&amp;quot;: [{&amp;quot;link&amp;quot;: &amp;quot;Errico Malatesta&amp;quot;, &amp;quot;last&amp;quot;: &amp;quot;Malatesta&amp;quot;, &amp;quot;first&amp;quot;: &amp;quot;Errico&amp;quot;}], &amp;quot;ID_list&amp;quot;: {&amp;quot;OCLC&amp;quot;: &amp;quot;3930443&amp;quot;}, &amp;quot;Periodical&amp;quot;: &amp;quot;MAN!&amp;quot;, &amp;quot;PublicationPlace&amp;quot;: &amp;quot;Los Angeles&amp;quot;}&lt;br /&gt; 716551092&amp;nbsp;&amp;nbsp; &amp;nbsp;12&amp;nbsp;&amp;nbsp; &amp;nbsp;2016-04-22T10:19:33Z&amp;nbsp;&amp;nbsp; &amp;nbsp;Anarchism&amp;nbsp;&amp;nbsp; &amp;nbsp;cite journal &amp;nbsp;&amp;nbsp; &amp;nbsp;{&amp;quot;Date&amp;quot;: &amp;quot;2007-05-14&amp;quot;, &amp;quot;URL&amp;quot;: &amp;quot;http://www.theglobeandmail.com/servlet/story/RTGAM.20070514.wxlanarchist14/BNStory/lifeWork/home/&amp;quot;, &amp;quot;Title&amp;quot;: &amp;quot;Working for The Man&amp;quot;, &amp;quot;Periodical&amp;quot;: &amp;quot;The Globe and Mail&amp;quot;, &amp;quot;Authors&amp;quot;: [{&amp;quot;last&amp;quot;: &amp;quot;Agrell&amp;quot;, &amp;quot;first&amp;quot;: &amp;quot;Siri&amp;quot;}]}&lt;br /&gt; 716551092&amp;nbsp;&amp;nbsp; &amp;nbsp;12&amp;nbsp;&amp;nbsp; &amp;nbsp;2016-04-22T10:19:33Z&amp;nbsp;&amp;nbsp; &amp;nbsp;Anarchism&amp;nbsp;&amp;nbsp; &amp;nbsp;cite web &amp;nbsp;&amp;nbsp; &amp;nbsp;{&amp;quot;Date&amp;quot;: &amp;quot;2006&amp;quot;, &amp;quot;URL&amp;quot;: &amp;quot;http://www.britannica.com/eb/article-9117285&amp;quot;, &amp;quot;PublisherName&amp;quot;: &amp;quot;Encyclop\u00e6dia Britannica Premium Service&amp;quot;, &amp;quot;Periodical&amp;quot;: &amp;quot;Encyclop\u00e6dia Britannica&amp;quot;, &amp;quot;Title&amp;quot;: &amp;quot;Anarchism&amp;quot;}&lt;br /&gt; 716551092&amp;nbsp;&amp;nbsp; &amp;nbsp;12&amp;nbsp;&amp;nbsp; &amp;nbsp;2016-04-22T10:19:33Z&amp;nbsp;&amp;nbsp; &amp;nbsp;Anarchism&amp;nbsp;&amp;nbsp; &amp;nbsp;cite journal &amp;nbsp;&amp;nbsp; &amp;nbsp;{&amp;quot;Date&amp;quot;: &amp;quot;2005&amp;quot;, &amp;quot;Pages&amp;quot;: &amp;quot;14&amp;quot;, &amp;quot;Periodical&amp;quot;: &amp;quot;The Shorter Routledge Encyclopedia of Philosophy&amp;quot;, &amp;quot;Title&amp;quot;: &amp;quot;Anarchism&amp;quot;}&lt;/p&gt; &lt;/blockquote&gt; &lt;p&gt;Credit: these citations have been input by Wikipedia editors (this dataset is therefore distributed under a CC-BY-SA license).&lt;/p&gt; &lt;p&gt;Acknowledgments: this extraction process was carried on one of OpenJournal&amp;#39;s servers.&lt;/p&gt; &lt;p&gt;See also: citation identifiers extracted from Wikipedia (so, not looking at specific templates, but using regular expressions): http://dx.doi.org/10.6084/m9.figshare.1299540&lt;/p&gt;</dct:description>
    <dct:description xml:lang="">{"references": ["http://dx.doi.org/10.6084/m9.figshare.1299540"]}</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dcat:distribution>
      <dcat:Distribution>
        <dct:license rdf:resource="http://creativecommons.org/licenses/by-sa/4.0/legalcode"/>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.55004"/>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
481
49
views
downloads
All versions This version
Views 481481
Downloads 4949
Data volume 16.0 GB16.0 GB
Unique views 460460
Unique downloads 3232

Share

Cite as