There is a newer version of this record available.

Dataset Restricted Access

SemEval 2019 Task 4 - Hyperpartisan News Detection

Johannes Kiesel; Martin Potthast; Maria Mestre; Rishabh Shukla; Benno Stein; David Corney; Emmanuel Vincent; Payam Adineh


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: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.1400316">
    <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.1400316</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.1400316"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-1617-6508">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-1617-6508</dct:identifier>
        <foaf:name>Johannes Kiesel</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Bauhaus-Universität Weimar</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Martin Potthast</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Leipzig University</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Maria Mestre</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Factmata Ltd.</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Rishabh Shukla</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Factmata Ltd.</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Benno Stein</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Bauhaus-Universität Weimar</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>David Corney</foaf:name>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Emmanuel Vincent</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Factmata Ltd.</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Payam Adineh</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Bauhaus-Universität Weimar</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>SemEval 2019 Task 4 - Hyperpartisan News Detection</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">2018</dct:issued>
    <dcat:keyword>Hyperpartisan news</dcat:keyword>
    <dcat:keyword>SemEval</dcat:keyword>
    <dcat:keyword>SemEval 2019</dcat:keyword>
    <dcat:keyword>SemEval 2019 Task 4</dcat:keyword>
    <dcat:keyword>Biased news</dcat:keyword>
    <dcat:keyword>News bias</dcat:keyword>
    <dcat:keyword>Hyperpartisan</dcat:keyword>
    <dcat:keyword>Hyperpartisanship</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2018-07-11</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/1400316"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/1400316</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isReferencedBy rdf:resource="https://pan.webis.de/semeval19/semeval19-web/"/>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.1310145"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/pan"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/webis"/>
    <owl:versionInfo>Trial</owl:versionInfo>
    <dct:description>&lt;p&gt;Second trial dataset for the SemEval 2019 Task 4: Hyperpartisan News Detection.&lt;/p&gt; &lt;p&gt;The dataset contains ~1 million articles. It is split in training and validation, where &lt;strong&gt;no&lt;/strong&gt; publisher that occurs in the training set also occurs in the validation set. Due to imbalance in our raw data, the training dataset of this version contains more articles that are hyperpartisan (533334: 26667 left and 26667 right) than not (26667). The validation set is balanced as the test set will be: 50% hyperpartisan (33333 left and 33333 right) and 50% not (66666). All articles are labeled by the overall bias of the publisher as provided by BuzzFeed journalists or MediaBiasFactCheck.com.&lt;/p&gt; &lt;p&gt;The trial data is not fully cleaned. Due to some encoding error, some characters are replaced by question marks. However, all files are already fully compatible with the XML schema files. Unlike the first trial version of this dataset, the &amp;lt;q&amp;gt; tag is used instead of &amp;lt;quote&amp;gt; (to be compatible with HTML).&lt;/p&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/RESTRICTED"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/restrictedAccess">
        <rdfs:label>Restricted Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.1400316"/>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
16,930
7,714
views
downloads
All versions This version
Views 16,930553
Downloads 7,714323
Data volume 2.2 TB181.2 GB
Unique views 14,178498
Unique downloads 1,945108

Share

Cite as