Dataset Open Access

Structured citations in the English Wikipedia

Delpeuch, Antonin


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <datafield tag="999" ind1="C" ind2="5">
    <subfield code="x">http://dx.doi.org/10.6084/m9.figshare.1299540</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">wikipedia</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">citation</subfield>
  </datafield>
  <controlfield tag="005">20200124192447.0</controlfield>
  <controlfield tag="001">55004</controlfield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">77</subfield>
    <subfield code="z">md5:246649761c021c43acef99422dd14221</subfield>
    <subfield code="u">https://zenodo.org/record/55004/files/header.tsv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">898</subfield>
    <subfield code="z">md5:96424f135cf1148b963d543e2ddfdc28</subfield>
    <subfield code="u">https://zenodo.org/record/55004/files/parse_citations_in_dump.py</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">695610680</subfield>
    <subfield code="z">md5:5c67630bf1cd20d157d497a48832a5c0</subfield>
    <subfield code="u">https://zenodo.org/record/55004/files/enwiki_2016-06-01_CS1_citations.tsv.bz2</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2016-06-06</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="o">oai:zenodo.org:55004</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="a">Delpeuch, Antonin</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Structured citations in the English Wikipedia</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">http://creativecommons.org/licenses/by-sa/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution Share Alike 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&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;</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.55004</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
452
44
views
downloads
All versions This version
Views 452452
Downloads 4444
Data volume 14.6 GB14.6 GB
Unique views 433433
Unique downloads 2929

Share

Cite as