February 1, 2019 Dataset Open Access

Saier, Tarek; Färber, Michael

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.2609187</identifier>
  <creators>
    <creator>
      <creatorName>Saier, Tarek</creatorName>
      <givenName>Tarek</givenName>
      <familyName>Saier</familyName>
      <affiliation>University of Freiburg</affiliation>
    </creator>
    <creator>
      <creatorName>Färber, Michael</creatorName>
      <givenName>Michael</givenName>
      <familyName>Färber</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-5458-8645</nameIdentifier>
      <affiliation>University of Freiburg</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Bibliometric-Enhanced arXiv: A Data Set for Paper-Based and Citation-Based Tasks</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2019</publicationYear>
  <subjects>
    <subject>scholarly data</subject>
    <subject>citations</subject>
    <subject>papers</subject>
    <subject>arXiv.org</subject>
    <subject>digital libraries</subject>
    <subject>dataset</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2019-02-01</date>
  </dates>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/2609187</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsDocumentedBy">http://ceur-ws.org/Vol-2345/paper2.pdf</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.2553522</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/bibliometrics</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/natural-language-processing</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/scholarly-data</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;We propose a new data set based on &lt;strong&gt;all publications from all scientific fields 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&lt;/strong&gt; were annotated via global identifiers. As far as possible, cited publications were linked to the &lt;strong&gt;Microsoft Academic Graph&lt;/strong&gt;. Our data set consists of &lt;strong&gt;over one million documents&lt;/strong&gt; and &lt;strong&gt;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 researchpaper-based and citation context-based approaches but also serve as a basis for novel ideas to analyze papers.&lt;/p&gt;

&lt;p&gt;More information can be found in our paper &lt;a href="http://ceur-ws.org/Vol-2345/paper2.pdf"&gt;Bibliometric-Enhanced arXiv: A Data Set for Paper-Based and Citation-Based Tasks&lt;/a&gt;.&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 source code which has been used for creating the data set.&lt;/p&gt;</description>
  </descriptions>
</resource>