Dataset Open Access

Paderborn Genre Analysis Corpus 2012 (PaGA-12)

Baumann, Michael; Lettmann, Theodor; Stein, Benno


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/6cd98ae5-143f-44d0-9ded-48a1bcbc7646/corpus-paga-12.zip"
      }, 
      "checksum": "md5:c9652cb695e35698fe0459a2bc6b6aa3", 
      "bucket": "6cd98ae5-143f-44d0-9ded-48a1bcbc7646", 
      "key": "corpus-paga-12.zip", 
      "type": "zip", 
      "size": 20673121
    }
  ], 
  "owners": [
    65747
  ], 
  "doi": "10.5281/zenodo.3250070", 
  "stats": {
    "version_unique_downloads": 16.0, 
    "unique_views": 166.0, 
    "views": 184.0, 
    "version_views": 185.0, 
    "unique_downloads": 16.0, 
    "version_unique_views": 167.0, 
    "volume": 413462420.0, 
    "version_downloads": 20.0, 
    "downloads": 20.0, 
    "version_volume": 413462420.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3250070", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3250069", 
    "bucket": "https://zenodo.org/api/files/6cd98ae5-143f-44d0-9ded-48a1bcbc7646", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3250069.svg", 
    "html": "https://zenodo.org/record/3250070", 
    "latest_html": "https://zenodo.org/record/3250070", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3250070.svg", 
    "latest": "https://zenodo.org/api/records/3250070"
  }, 
  "conceptdoi": "10.5281/zenodo.3250069", 
  "created": "2019-06-19T12:27:24.926223+00:00", 
  "updated": "2020-01-21T07:23:05.042302+00:00", 
  "conceptrecid": "3250069", 
  "revision": 8, 
  "id": 3250070, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3250070", 
    "description": "<p>The Paderborn Genre Analysis 2012 corpus (PaGA-12) contains 1,639 HTML documents of 26 genres. All documents were collected from 2009-10-18 to 2009-11-20, and each document is manually assigned to exactly one genre. For each genre, the corpus provides at least 50 documents.</p>\n\n<p>All HTML documents contain German text only, and framesets are removed. The corpus is delivered in form of a MySQL database dump; the database structure is detailed in a README file delivered with the corpus.</p>", 
    "language": "deu", 
    "title": "Paderborn Genre Analysis Corpus 2012 (PaGA-12)", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3250069"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3250070"
          }
        }
      ]
    }, 
    "communities": [
      {
        "id": "webis"
      }
    ], 
    "keywords": [
      "documents", 
      "genre", 
      "german"
    ], 
    "publication_date": "2012-01-01", 
    "creators": [
      {
        "affiliation": "Universit\u00e4t Paderborn", 
        "name": "Baumann, Michael"
      }, 
      {
        "affiliation": "Bauhaus-Universit\u00e4t Weimar", 
        "name": "Lettmann, Theodor"
      }, 
      {
        "orcid": "0000-0001-9033-2217", 
        "affiliation": "Bauhaus-Universit\u00e4t Weimar", 
        "name": "Stein, Benno"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3250069", 
        "relation": "isVersionOf"
      }
    ]
  }
}
185
20
views
downloads
All versions This version
Views 185184
Downloads 2020
Data volume 413.5 MB413.5 MB
Unique views 167166
Unique downloads 1616

Share

Cite as