UPDATE: Zenodo migration postponed to Oct 13 from 06:00-08:00 UTC. Read the announcement.

Dataset Open Access

l-sized Training and Evaluation Data for Publication "Using Supervised Learning to Classify Metadata of Research Data by Field of Study"

Tobias Weber


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/820f79bd-d87d-4515-924c-b7ea34e069d9/l_data_vectorized.tar.gz"
      }, 
      "checksum": "md5:2d0dacc2e0902b6ca69e1b997fb6da51", 
      "bucket": "820f79bd-d87d-4515-924c-b7ea34e069d9", 
      "key": "l_data_vectorized.tar.gz", 
      "type": "gz", 
      "size": 2005185530
    }
  ], 
  "owners": [
    64749
  ], 
  "doi": "10.5281/zenodo.3490460", 
  "stats": {
    "version_unique_downloads": 18.0, 
    "unique_views": 73.0, 
    "views": 79.0, 
    "version_views": 79.0, 
    "unique_downloads": 18.0, 
    "version_unique_views": 73.0, 
    "volume": 50129638250.0, 
    "version_downloads": 25.0, 
    "downloads": 25.0, 
    "version_volume": 50129638250.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3490460", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3490459", 
    "bucket": "https://zenodo.org/api/files/820f79bd-d87d-4515-924c-b7ea34e069d9", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3490459.svg", 
    "html": "https://zenodo.org/record/3490460", 
    "latest_html": "https://zenodo.org/record/3490460", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3490460.svg", 
    "latest": "https://zenodo.org/api/records/3490460"
  }, 
  "conceptdoi": "10.5281/zenodo.3490459", 
  "created": "2019-10-15T10:56:59.768047+00:00", 
  "updated": "2020-04-20T00:34:08.351904+00:00", 
  "conceptrecid": "3490459", 
  "revision": 5, 
  "id": 3490460, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3490460", 
    "description": "<p>Automated classification of metadata of research data by their discipline(s) of research can be used in scientometric research, by repository service providers, and in the context of research data aggregation services. Openly available metadata of the DataCite index for research data were used to compile a large training and evaluation set comprised of 609,524 records. This is the cleaned and vectorized version with a feature selection of large size.</p>", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "l-sized Training and Evaluation  Data for Publication \"Using Supervised Learning to Classify Metadata of Research Data by Field of Study\"", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3490459"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3490460"
          }
        }
      ]
    }, 
    "subjects": [
      {
        "term": "004 Data processing & computer science", 
        "scheme": "url", 
        "identifier": "https://dewey.info/"
      }, 
      {
        "term": "020 Library & information sciences", 
        "scheme": "url", 
        "identifier": "https://dewey.info/"
      }
    ], 
    "keywords": [
      "research data", 
      "disciplines of research", 
      "supervised machine learning", 
      "multi-label classification", 
      "text processing", 
      "data science"
    ], 
    "publication_date": "2019-10-15", 
    "creators": [
      {
        "orcid": "0000-0003-1815-7041", 
        "affiliation": "Leibniz Supercomputing Centre", 
        "name": "Tobias Weber"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3490329", 
        "relation": "compiles", 
        "resource_type": "dataset"
      }, 
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3490459", 
        "relation": "isVersionOf"
      }
    ]
  }
}
79
25
views
downloads
All versions This version
Views 7979
Downloads 2525
Data volume 50.1 GB50.1 GB
Unique views 7373
Unique downloads 1818

Share

Cite as