Dataset Open Access

A ground-truth dataset to identify bots in GitHub

Mehdi Golzadeh; Alexandre Decan; Damien Legay; Tom Mens


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">Ground-truth; Bot, Human, GitHub accounts, Repository</subfield>
  </datafield>
  <controlfield tag="005">20201007002634.0</controlfield>
  <controlfield tag="001">4000388</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Software engineering lab, University of Mons</subfield>
    <subfield code="a">Alexandre Decan</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Software engineering lab, University of Mons</subfield>
    <subfield code="a">Damien Legay</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Software engineering lab, University of Mons</subfield>
    <subfield code="a">Tom Mens</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">81129</subfield>
    <subfield code="z">md5:b2f970611a844bbd9e915836d87d693c</subfield>
    <subfield code="u">https://zenodo.org/record/4000388/files/groundtruthbots.csv.gz</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2020-08-25</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="p">user-empirical-software-engineering</subfield>
    <subfield code="p">user-msr</subfield>
    <subfield code="o">oai:zenodo.org:4000388</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Software engineering lab, University of Mons</subfield>
    <subfield code="0">(orcid)0000-0003-1041-439X</subfield>
    <subfield code="a">Mehdi Golzadeh</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">A ground-truth dataset to identify bots in GitHub</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-empirical-software-engineering</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-msr</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;This dataset is a ground truth dataset we used to identify bots. Each account in this dataset is rated by at least 3 raters with high interrater agreement.&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.4000387</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.4000388</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
268
78
views
downloads
All versions This version
Views 268268
Downloads 7878
Data volume 6.3 MB6.3 MB
Unique views 254254
Unique downloads 7171

Share

Cite as