There is a newer version of this record available.

Dataset Open Access

ClaimBuster: A Benchmark Dataset of Check-worthy Factual Claims

Fatma Arslan; Naeemul Hassan; Chengkai Li; Mark Tremayne


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/0eae643c-e79f-4f2d-986d-e70b3cff6223/all_sentences.csv"
      }, 
      "checksum": "md5:686ac1dd5123d9ca0d229ee9760d4962", 
      "bucket": "0eae643c-e79f-4f2d-986d-e70b3cff6223", 
      "key": "all_sentences.csv", 
      "type": "csv", 
      "size": 5316340
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0eae643c-e79f-4f2d-986d-e70b3cff6223/crowdsourced.csv"
      }, 
      "checksum": "md5:af9649bc3cc93edbc804893720a50bde", 
      "bucket": "0eae643c-e79f-4f2d-986d-e70b3cff6223", 
      "key": "crowdsourced.csv", 
      "type": "csv", 
      "size": 3856042
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0eae643c-e79f-4f2d-986d-e70b3cff6223/groundtruth.csv"
      }, 
      "checksum": "md5:1577f6d45bf33eabe9cf760f0fb66da3", 
      "bucket": "0eae643c-e79f-4f2d-986d-e70b3cff6223", 
      "key": "groundtruth.csv", 
      "type": "csv", 
      "size": 167741
    }
  ], 
  "owners": [
    88167
  ], 
  "doi": "10.5281/zenodo.3609356", 
  "stats": {
    "version_unique_downloads": 915.0, 
    "unique_views": 911.0, 
    "views": 1006.0, 
    "version_views": 2381.0, 
    "unique_downloads": 803.0, 
    "version_unique_views": 2039.0, 
    "volume": 5392940920.0, 
    "version_downloads": 1470.0, 
    "downloads": 1321.0, 
    "version_volume": 6081252378.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3609356", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3609355", 
    "bucket": "https://zenodo.org/api/files/0eae643c-e79f-4f2d-986d-e70b3cff6223", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3609355.svg", 
    "html": "https://zenodo.org/record/3609356", 
    "latest_html": "https://zenodo.org/record/3836810", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3609356.svg", 
    "latest": "https://zenodo.org/api/records/3836810"
  }, 
  "conceptdoi": "10.5281/zenodo.3609355", 
  "created": "2020-01-16T04:23:03.218833+00:00", 
  "updated": "2020-07-02T03:01:27.575095+00:00", 
  "conceptrecid": "3609355", 
  "revision": 7, 
  "id": 3609356, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3609356", 
    "description": "<p>The ClaimBuster dataset consists of&nbsp;statements extracted from all U.S. general election presidential debates (1960-2016) along with human-annotated check-worthiness labels.&nbsp;It&nbsp;contains 23,533 sentences where each sentence is categorized into one of the three categories: non-factual statement, unimportant factual statement, and check-worthy factual statement.&nbsp;</p>", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "ClaimBuster: A Benchmark Dataset of Check-worthy Factual Claims", 
    "notes": "The work is partially supported by NSF grants IIS-1408928, IIP-1565699, IIS-1719054, OIA-1937143, a Knight Prototype Fund from the Knight Foundation, and subawards from Duke University as part of a grant to the Duke Tech &amp; Check Cooperative from the Knight Foundation and Facebook. Any opinions, findings, and conclusions or recommendations expressed in this publication are those of the authors and do not necessarily reflect the views of the funding agencies.", 
    "relations": {
      "version": [
        {
          "count": 2, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3609355"
          }, 
          "is_last": false, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3836810"
          }
        }
      ]
    }, 
    "keywords": [
      "factual claim", 
      "check-worthy claim", 
      "check-worthiness"
    ], 
    "publication_date": "2020-01-15", 
    "creators": [
      {
        "affiliation": "University of Texas at Arlington", 
        "name": "Fatma Arslan"
      }, 
      {
        "affiliation": "University of Maryland", 
        "name": "Naeemul Hassan"
      }, 
      {
        "orcid": "0000-0002-1724-8278", 
        "affiliation": "University of Texas at Arlington", 
        "name": "Chengkai Li"
      }, 
      {
        "affiliation": "University of Texas at Arlington", 
        "name": "Mark Tremayne"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3609355", 
        "relation": "isVersionOf"
      }
    ]
  }
}
2,381
1,470
views
downloads
All versions This version
Views 2,3811,006
Downloads 1,4701,321
Data volume 6.1 GB5.4 GB
Unique views 2,039911
Unique downloads 915803

Share

Cite as