June 26, 2019 Dataset Open Access

Baltes, Sebastian; Dumani, Lorik

JSON-LD (schema.org) Export

{
  "description": "<p>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 <em>SOTorrent</em>, an open dataset based on the official SO data dump. <em>SOTorrent </em>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 <em>SOTorrent </em>to investigate and understand the evolution of SO posts and their relation to other platforms such as GitHub.</p>\n\n<p><strong>If you use this dataset in your work, please cite our <a href=\"http://empirical-software.engineering/publications#msr18-sotorrent\">MSR 2018 paper</a> (<a href=\"https://dblp.uni-trier.de/rec/bibtex/conf/msr/BaltesDT008\">BibTex</a>) or our <a href=\"http://empirical-software.engineering/publications#msr19-sotorrent\">MSR 2019 mining challenge proposal</a>.</strong></p>", 
  "license": "https://creativecommons.org/licenses/by-sa/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "University of Trier", 
      "@id": "https://orcid.org/0000-0002-2442-7522", 
      "@type": "Person", 
      "name": "Baltes, Sebastian"
    }, 
    {
      "affiliation": "University of Trier", 
      "@id": "https://orcid.org/0000-0001-9567-1699", 
      "@type": "Person", 
      "name": "Dumani, Lorik"
    }
  ], 
  "url": "https://zenodo.org/record/3255045", 
  "datePublished": "2019-06-26", 
  "version": "2019-06-21", 
  "keywords": [
    "stack overflow", 
    "code snippets", 
    "software evolution", 
    "github"
  ], 
  "@context": "https://schema.org/", 
  "distribution": [
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/1_create_database.sql", 
      "encodingFormat": "sql", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/2_create_sotorrent_user.sql", 
      "encodingFormat": "sql", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/3_load_so_from_xml.sql", 
      "encodingFormat": "sql", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/4_create_indices.sql", 
      "encodingFormat": "sql", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/5_create_sotorrent_tables.sql", 
      "encodingFormat": "sql", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/6_load_sotorrent.sql", 
      "encodingFormat": "sql", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/7_load_gh_references.sql", 
      "encodingFormat": "sql", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/8_create_sotorrent_indices.sql", 
      "encodingFormat": "sql", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/Badges.xml.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/Comments.xml.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/CommentUrl.csv.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/GHMatches.csv.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/LICENSE.md", 
      "encodingFormat": "md", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/PostBlockDiff.csv.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/PostBlockVersion.csv.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/PostHistory.xml.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/PostLinks.xml.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/PostReferenceGH.csv.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/Posts.xml.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/PostVersion.csv.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/PostVersionUrl.csv.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/README.md", 
      "encodingFormat": "md", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/Tags.xml.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/TitleVersion.csv.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/Users.xml.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/b8d6049f-3103-41be-8c01-833c0a3b0b3a/Votes.xml.7z", 
      "encodingFormat": "7z", 
      "@type": "DataDownload"
    }
  ], 
  "identifier": "https://doi.org/10.5281/zenodo.3255045", 
  "@id": "https://doi.org/10.5281/zenodo.3255045", 
  "@type": "Dataset", 
  "name": "SOTorrent Dataset"
}