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/15a29496-4dd6-4f3b-8601-25b4504724b8/ClaimBuster_Datasets.zip"
      }, 
      "checksum": "md5:06ca00d0705e0a7fe9fb9a23a539ca97", 
      "bucket": "15a29496-4dd6-4f3b-8601-25b4504724b8", 
      "key": "ClaimBuster_Datasets.zip", 
      "type": "zip", 
      "size": 4715650
    }
  ], 
  "owners": [
    88167
  ], 
  "doi": "10.5281/zenodo.3836810", 
  "stats": {
    "version_unique_downloads": 404.0, 
    "unique_views": 374.0, 
    "views": 421.0, 
    "version_views": 946.0, 
    "unique_downloads": 39.0, 
    "version_unique_views": 790.0, 
    "volume": 202772950.0, 
    "version_downloads": 649.0, 
    "downloads": 43.0, 
    "version_volume": 2759646257.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3836810", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3609355", 
    "bucket": "https://zenodo.org/api/files/15a29496-4dd6-4f3b-8601-25b4504724b8", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3609355.svg", 
    "html": "https://zenodo.org/record/3836810", 
    "latest_html": "https://zenodo.org/record/3836810", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3836810.svg", 
    "latest": "https://zenodo.org/api/records/3836810"
  }, 
  "conceptdoi": "10.5281/zenodo.3609355", 
  "created": "2020-05-20T23:14:29.296633+00:00", 
  "updated": "2020-07-02T03:01:28.933203+00:00", 
  "conceptrecid": "3609355", 
  "revision": 3, 
  "id": 3836810, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3836810", 
    "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 where each sentence is categorized into one of the three categories: non-factual statement, unimportant factual statement, and check-worthy factual statement.</p>\n\n<p>If you use this dataset, please cite the following paper:</p>\n\n<p>@inproceedings{arslan2020claimbuster,<br>\n&nbsp; &nbsp; title={{A Benchmark Dataset of Check-worthy Factual Claims}},<br>\n&nbsp; &nbsp; author={Arslan, Fatma and Hassan, Naeemul and Li, Chengkai and Tremayne, Mark },<br>\n&nbsp; &nbsp; booktitle={14th International AAAI Conference on Web and Social Media},<br>\n&nbsp; &nbsp; year={2020},<br>\n&nbsp; &nbsp; organization={AAAI}<br>\n}</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": 1, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3609355"
          }, 
          "is_last": true, 
          "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"
      }
    ]
  }
}
946
649
views
downloads
All versions This version
Views 946421
Downloads 64943
Data volume 2.8 GB202.8 MB
Unique views 790374
Unique downloads 40439

Share

Cite as