Dataset Open Access

Tracking Knowledge Propagation Across Wikipedia Languages

Valentim, Rodolfo; Comarela, Giovanni; Park, Souneil; Saez-Trumper, Diego


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.4433137">
    <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.4433137</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.4433137"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-7702-2991">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-7702-2991</dct:identifier>
        <foaf:name>Valentim, Rodolfo</foaf:name>
        <foaf:givenName>Rodolfo</foaf:givenName>
        <foaf:familyName>Valentim</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Politecnico di Torino</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0001-7612-9650">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0001-7612-9650</dct:identifier>
        <foaf:name>Comarela, Giovanni</foaf:name>
        <foaf:givenName>Giovanni</foaf:givenName>
        <foaf:familyName>Comarela</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Federal University of Espírito Santo</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>Park, Souneil</foaf:name>
        <foaf:givenName>Souneil</foaf:givenName>
        <foaf:familyName>Park</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Telefonica Research</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-7679-5423">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-7679-5423</dct:identifier>
        <foaf:name>Saez-Trumper, Diego</foaf:name>
        <foaf:givenName>Diego</foaf:givenName>
        <foaf:familyName>Saez-Trumper</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Wikimedia Foundation</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Tracking Knowledge Propagation Across Wikipedia Languages</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">2021</dct:issued>
    <dcat:keyword>knowledge propagation</dcat:keyword>
    <dcat:keyword>Wikipedia</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2021-03-15</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/4433137"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/4433137</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.4433136"/>
    <dct:description>&lt;p&gt;We present a dataset of &lt;em&gt;inter-language knowledge propagation&lt;/em&gt; in Wikipedia. Covering the entire 309 language editions and 33M articles, the dataset aims to track the full propagation history of Wikipedia concepts, and allow follow up research on building predictive models of them. For this purpose, we align all the Wikipedia articles in a language-agnostic manner according to the concept they cover, which results in 13M propagation instances. To the best of our knowledge, this dataset is the first to explore the full inter-language propagation at a large scale. Together with the dataset, a holistic overview of the propagation and key insights about the underlying structural factors are provided to aid future research. For example, we find that although long cascades are unusual, the propagation tends to continue further once it reaches more than four language editions. We also find that the size of language editions are associated with the speed of propagation. We believe the dataset not only contributes to the prior literature on Wikipedia growth but also enables new use cases such as edit recommendation for addressing knowledge gaps, detection of disinformation, and cultural relationship analysis.&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.4433137"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4433137">https://doi.org/10.5281/zenodo.4433137</dcat:accessURL>
        <dcat:byteSize>321896511</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/4433137/files/dataset.csv.zip">https://zenodo.org/record/4433137/files/dataset.csv.zip</dcat:downloadURL>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4433137">https://doi.org/10.5281/zenodo.4433137</dcat:accessURL>
        <dcat:byteSize>351865094</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/4433137/files/dataset.jsonl.zip">https://zenodo.org/record/4433137/files/dataset.jsonl.zip</dcat:downloadURL>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
496
171
views
downloads
All versions This version
Views 496496
Downloads 171171
Data volume 57.2 GB57.2 GB
Unique views 415415
Unique downloads 116116

Share

Cite as