December 7, 2022 Dataset Open Access

Hiba Arnaout; Simon Razniewski; Jeff Z. Pan

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.7537200">
    <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.7537200</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.7537200"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Hiba Arnaout</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Max Planck Institute for Informatics</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>Simon Razniewski</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Max Planck Institute for Informatics</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>Jeff Z. Pan</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>The University of Edinburgh</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Wiki-based Communities of Interest: Demographics and Outliers</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">2022</dct:issued>
    <dcat:keyword>wikipedia</dcat:keyword>
    <dcat:keyword>wikimedia</dcat:keyword>
    <dcat:keyword>wikidata</dcat:keyword>
    <dcat:keyword>demography</dcat:keyword>
    <dcat:keyword>trivia</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2022-12-07</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/7537200"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/7537200</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.7410436"/>
    <dct:description>&lt;p&gt;These datasets contains&amp;nbsp;statements about demographics and outliers&amp;nbsp;of Wiki-based Communities of Interest.&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;strong&gt;Group-centric dataset (sample):&lt;/strong&gt;&lt;/p&gt; &lt;pre&gt;&lt;code class="language-json"&gt;{ "title": "winners of Priestley Medal", "recorded_members": 83, "topics": ["STEM.Chemistry"], "demographics": [ "occupation-chemist", "gender-male", "citizen-U.S." ], "outliers": [ { "reason": "NOT(chemist) unlike 82 recorded members", "members": [ "Francis Garvan (lawyer, art collector)" ] }, { "reason": "NOT(male) unlike 80 recorded members", "members": [ "Mary L. Good (female)", "Darleane Hoffman (female)", "Jacqueline Barton (female)" ] } ] }&lt;/code&gt;&lt;/pre&gt; &lt;p&gt;&lt;strong&gt;Subject-centric dataset (sample):&lt;/strong&gt;&lt;/p&gt; &lt;pre&gt;&lt;code class="language-json"&gt;{ "subject": "Serena Williams", "statements": [ { "statement": "NOT(sport-basketball) but (tennis) unlike 4 recorded winners of Best Female Athlete ESPY Award.", "score": 0.36 }, { "statement": "NOT(occupation-politician) but (tennis player, businessperson, autobiographer) unlike 20 recorded winners of Michigan Women's Hall of Fame.", "score": 0.17 } ] }&lt;/code&gt;&lt;/pre&gt; &lt;p&gt;&lt;strong&gt;This data can be also browsed at:&amp;nbsp;&lt;a href="https://wikiknowledge.onrender.com/demographics/"&gt;https://wikiknowledge.onrender.com/demographics/&lt;/a&gt;&lt;/strong&gt;&lt;/p&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dcat:distribution>
      <dcat:Distribution>
        <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.7537200"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.7537200"/>
        <dcat:byteSize>63717789</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/7537200/files/group_centric.jsonl"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.7537200"/>
        <dcat:byteSize>172036359</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/7537200/files/subject_centric.jsonl"/>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>