There is a newer version of this record available.

Dataset Open Access

SOTorrent Dataset

Baltes, Sebastian; Dumani, Lorik


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:cnt="http://www.w3.org/2011/content#" 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.2273117">
    <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.2273117</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.2273117"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-2442-7522">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Baltes, Sebastian</foaf:name>
        <foaf:givenName>Sebastian</foaf:givenName>
        <foaf:familyName>Baltes</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Trier</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0001-9567-1699">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Dumani, Lorik</foaf:name>
        <foaf:givenName>Lorik</foaf:givenName>
        <foaf:familyName>Dumani</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Trier</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>SOTorrent Dataset</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>stack overflow</dcat:keyword>
    <dcat:keyword>code snippets</dcat:keyword>
    <dcat:keyword>software evolution</dcat:keyword>
    <dcat:keyword>github</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2018-12-14</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/2273117"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/2273117</skos:notation>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.1135262"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/empirical-software-engineering"/>
    <owl:versionInfo>2018-12-09</owl:versionInfo>
    <dct:description>&lt;p&gt;Stack Overflow (SO) is the most popular question-and-answer website for software developers, providing a large amount of code snippets and free-form text on a wide variety of topics. Like other software artifacts, questions and answers on SO evolve over time, for example when bugs in code snippets are fixed, code is updated to work with a more recent library version, or text surrounding a code snippet is edited for clarity. To be able to analyze how content on SO evolves, we built &lt;em&gt;SOTorrent&lt;/em&gt;, an open dataset based on the official SO data dump. &lt;em&gt;SOTorrent &lt;/em&gt;provides access to the version history of SO content at the level of whole posts and individual text or code blocks. It connects SO posts to other platforms by aggregating URLs from text blocks and comments, and by collecting references from GitHub files to SO posts. Our vision is that researchers will use &lt;em&gt;SOTorrent &lt;/em&gt;to investigate and understand the evolution of SO posts and their relation to other platforms such as GitHub.&lt;/p&gt; &lt;p&gt;&lt;strong&gt;If you use this dataset in your work, please cite our &lt;a href="http://empirical-software.engineering/publications#msr18-sotorrent"&gt;MSR 2018 paper&lt;/a&gt; (&lt;a href="https://dblp.uni-trier.de/rec/bibtex/conf/msr/BaltesDT008"&gt;BibTex&lt;/a&gt;) or our &lt;a href="http://empirical-software.engineering/publications#msr19-sotorrent"&gt;MSR 2019 mining challenge proposal&lt;/a&gt;.&lt;/strong&gt;&lt;/p&gt;</dct:description>
    <dct:description xml:lang="">The dataset is based on the official Stack Overflow data dump released 2018-12-02 (https://archive.org/details/stackexchange) and the Google BigQuery GitHub data set queried 2018-12-09 (https://cloud.google.com/bigquery/public-data/github). Please read the license files (LICENSE.md) before using the dataset.</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:rights>
          <dct:RightsStatement rdf:about="https://creativecommons.org/licenses/by-sa/4.0/legalcode">
            <rdfs:label>Creative Commons Attribution Share Alike 4.0 International</rdfs:label>
          </dct:RightsStatement>
        </dct:rights>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.2273117"/>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
5,324
23,923
views
downloads
All versions This version
Views 5,3241,014
Downloads 23,9232,996
Data volume 179.8 TB25.1 TB
Unique views 4,121866
Unique downloads 4,005676

Share

Cite as