December 9, 2020 Dataset Open Access

Saier, Tarek; Färber, Michael

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.4313164">
    <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.4313164</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.4313164"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0001-5028-0109">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0001-5028-0109</dct:identifier>
        <foaf:name>Saier, Tarek</foaf:name>
        <foaf:givenName>Tarek</foaf:givenName>
        <foaf:familyName>Saier</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Freiburg</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0001-5458-8645">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0001-5458-8645</dct:identifier>
        <foaf:name>Färber, Michael</foaf:name>
        <foaf:givenName>Michael</foaf:givenName>
        <foaf:familyName>Färber</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Freiburg</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>unarXive: A Large Scholarly Data Set with Publications' Full-Text, Annotated In-Text Citations, and Links to Metadata</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">2020</dct:issued>
    <dcat:keyword>scholarly data</dcat:keyword>
    <dcat:keyword>citations</dcat:keyword>
    <dcat:keyword>papers</dcat:keyword>
    <dcat:keyword>arXiv.org</dcat:keyword>
    <dcat:keyword>digital libraries</dcat:keyword>
    <dcat:keyword>dataset</dcat:keyword>
    <dcat:keyword>scientometrics</dcat:keyword>
    <dcat:keyword>full-text</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2020-12-09</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/4313164"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/4313164</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <foaf:page rdf:resource="https://link.springer.com/article/10.1007%2Fs11192-020-03382-z"/>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.2553522"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/bibliometrics"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/natural-language-processing"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/scholarly-data"/>
    <dct:description>&lt;p&gt;In recent years, scholarly data sets have been used for various purposes, such as paper recommendation, citation recommendation, citation context analysis, and citation context-based document summarization. The evaluation of approaches to such tasks and their applicability in real-world scenarios heavily depend on the used data set. However, existing scholarly data sets are limited in several regards.&lt;/p&gt; &lt;p&gt;Here, we propose a new &lt;strong&gt;data set based on all publications from all scientific disciplines available on arXiv.org&lt;/strong&gt;. Apart from providing the &lt;strong&gt;papers&amp;#39; plain text&lt;/strong&gt;, &lt;strong&gt;in-text citations were annotated&lt;/strong&gt; via global identifiers. Furthermore, citing and cited publications were linked to the &lt;strong&gt;Microsoft Academic Graph&lt;/strong&gt;, providing access to rich metadata. Our data set consists of &lt;strong&gt;over one million documents and 29.2 million citation contexts&lt;/strong&gt;. The data set, which is made freely available for research purposes, not only can enhance the future evaluation of research paper-based and citation context-based approaches but also serve as a basis for new ways to analyze in-text citations.&lt;/p&gt; &lt;p&gt;This &lt;strong&gt;updated version&lt;/strong&gt; (v3) of our data set is based on all arXiv publications until 2020-07-31 and on the Microsoft Academic Graph as of 2020-08-18. As additional contribution, we included a table with the publication date and the scientific discipline for each paper for easier filtering.&lt;/p&gt; &lt;p&gt;See &lt;a href="https://github.com/IllDepence/unarXive"&gt;https://github.com/IllDepence/unarXive&lt;/a&gt; for the &lt;strong&gt;source code&lt;/strong&gt; which has been used for creating the data set.&lt;/p&gt; &lt;p&gt;&lt;strong&gt;Usage examples&lt;/strong&gt; for our data set are provided at &lt;a href="https://github.com/IllDepence/unarXive#usage-examples"&gt;https://github.com/IllDepence/unarXive#usage-examples&lt;/a&gt;.&lt;/p&gt; &lt;p&gt;For &lt;strong&gt;citing&lt;/strong&gt; our data set and for further information we can refer to our journal article&lt;/p&gt; &lt;p&gt;&lt;em&gt;Tarek Saier, Michael F&amp;auml;rber: &amp;quot;&lt;a href="https://www.aifb.kit.edu/images/f/f9/UnarXive_Scientometrics2020.pdf"&gt;unarXive: A Large Scholarly Data Set with Publications&amp;rsquo; Full-Text, Annotated In-Text Citations, and Links to Metadata&lt;/a&gt;&amp;quot;, Scientometrics, 2020, &lt;a href="http://dx.doi.org/10.1007/s11192-020-03382-z"&gt;http://dx.doi.org/10.1007/s11192-020-03382-z&lt;/a&gt;.&lt;/em&gt;&lt;/p&gt; &lt;p&gt;&amp;nbsp;&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>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4313164"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4313164"/>
        <dcat:byteSize>19120394657</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/4313164/files/unarXive-2020.tar.bz2"/>
        <dcat:mediaType>application/x-tar</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>