There is a newer version of this record available.

Dataset Open Access

ClaimBuster: A Benchmark Dataset of Check-worthy Factual Claims

Fatma Arslan; Naeemul Hassan; Chengkai Li; Mark Tremayne


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="653" ind1=" " ind2=" ">
    <subfield code="a">factual claim</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">check-worthy claim</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">check-worthiness</subfield>
  </datafield>
  <controlfield tag="005">20200702030127.0</controlfield>
  <datafield tag="500" ind1=" " ind2=" ">
    <subfield code="a">The work is partially supported by NSF grants IIS-1408928, IIP-1565699, IIS-1719054, OIA-1937143, a Knight Prototype Fund from the Knight Foundation, and subawards from Duke University as part of a grant to the Duke Tech &amp;amp; Check Cooperative from the Knight Foundation and Facebook. Any opinions, findings, and conclusions or recommendations expressed in this publication are those of the authors and do not necessarily reflect the views of the funding agencies.</subfield>
  </datafield>
  <controlfield tag="001">3609356</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Maryland</subfield>
    <subfield code="a">Naeemul Hassan</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Texas at Arlington</subfield>
    <subfield code="0">(orcid)0000-0002-1724-8278</subfield>
    <subfield code="a">Chengkai Li</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Texas at Arlington</subfield>
    <subfield code="a">Mark Tremayne</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">5316340</subfield>
    <subfield code="z">md5:686ac1dd5123d9ca0d229ee9760d4962</subfield>
    <subfield code="u">https://zenodo.org/record/3609356/files/all_sentences.csv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">3856042</subfield>
    <subfield code="z">md5:af9649bc3cc93edbc804893720a50bde</subfield>
    <subfield code="u">https://zenodo.org/record/3609356/files/crowdsourced.csv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">167741</subfield>
    <subfield code="z">md5:1577f6d45bf33eabe9cf760f0fb66da3</subfield>
    <subfield code="u">https://zenodo.org/record/3609356/files/groundtruth.csv</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2020-01-15</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="o">oai:zenodo.org:3609356</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">University of Texas at Arlington</subfield>
    <subfield code="a">Fatma Arslan</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">ClaimBuster: A Benchmark Dataset of Check-worthy Factual Claims</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 ClaimBuster dataset consists of&amp;nbsp;statements extracted from all U.S. general election presidential debates (1960-2016) along with human-annotated check-worthiness labels.&amp;nbsp;It&amp;nbsp;contains 23,533 sentences where each sentence is categorized into one of the three categories: non-factual statement, unimportant factual statement, and check-worthy factual statement.&amp;nbsp;&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.3609355</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3609356</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
2,381
1,470
views
downloads
All versions This version
Views 2,3811,006
Downloads 1,4701,321
Data volume 6.1 GB5.4 GB
Unique views 2,039911
Unique downloads 915803

Share

Cite as