UPDATE: Zenodo migration postponed to Oct 13 from 06:00-08:00 UTC. Read the announcement.

Dataset Open Access

Wikidata Vandalism Corpus 2015 (WDVC-15)

Heindorf, Stefan; Potthast, Martin; Stein, Benno; Engels, Gregor


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">Stefan Heindorf, Martin Potthast, Benno Stein, and Gregor Engels. Towards Vandalism Detection in Knowledge Bases: Corpus Construction and Analysis. In Ricardo Baeza-Yates, Mounia Lalmas, Alistair Moffat, and Berthier Ribeiro-Neto, editors, 38th International ACM Conference on Research and Development in Information Retrieval (SIGIR 2015), pages 831-834, August 2015. ACM. ISBN 978-1-4503-3621-5</subfield>
  </datafield>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">wikidata</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">wikipedia</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">vandalism</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">detector</subfield>
  </datafield>
  <controlfield tag="005">20200616074203.0</controlfield>
  <controlfield tag="001">3250651</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="g">SIGIR 2015</subfield>
    <subfield code="a">38th International ACM Conference on Research and Development in Information Retrieval</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Bauhaus-Universität Weimar</subfield>
    <subfield code="0">(orcid)0000-0003-2451-0665</subfield>
    <subfield code="a">Potthast, Martin</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Bauhaus-Universität Weimar</subfield>
    <subfield code="0">(orcid)0000-0001-9033-2217</subfield>
    <subfield code="a">Stein, Benno</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Universität Paderborn</subfield>
    <subfield code="a">Engels, Gregor</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">4815698116</subfield>
    <subfield code="z">md5:34a68c8bb6023911d71539beeae001fa</subfield>
    <subfield code="u">https://zenodo.org/record/3250651/files/wikidata-vandalism-corpus-2015.tar.bz2</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2015-08-13</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="p">user-webis</subfield>
    <subfield code="o">oai:zenodo.org:3250651</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Universität Paderborn</subfield>
    <subfield code="0">(orcid)0000-0002-4525-6865</subfield>
    <subfield code="a">Heindorf, Stefan</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Wikidata Vandalism Corpus 2015 (WDVC-15)</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-webis</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 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;The Wikidata vandalism corpus 2015 (WDVC-15) is a corpus for the evaluation of automatic vandalism detectors for Wikidata. For research purposes the corpus can be used free of charge.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3250650</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3250651</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
609
55
views
downloads
All versions This version
Views 609609
Downloads 5555
Data volume 264.9 GB264.9 GB
Unique views 532532
Unique downloads 4444

Share

Cite as