Dataset Open Access

Hacker News Curated Comments Dataset

Christopher Moody


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/b0799b59-9385-4758-860e-018c2cb90286/hacker_news_comments.csv"
      }, 
      "checksum": "md5:1900b83d663a9cf2f34fd9d42fdb3846", 
      "bucket": "b0799b59-9385-4758-860e-018c2cb90286", 
      "key": "hacker_news_comments.csv", 
      "type": "csv", 
      "size": 780573044
    }
  ], 
  "owners": [
    20376
  ], 
  "doi": "10.5281/zenodo.45901", 
  "stats": {
    "version_unique_downloads": 52354.0, 
    "unique_views": 27045.0, 
    "views": 29776.0, 
    "version_views": 29784.0, 
    "unique_downloads": 52328.0, 
    "version_unique_views": 27053.0, 
    "volume": 56838987344948.0, 
    "version_downloads": 72849.0, 
    "downloads": 72817.0, 
    "version_volume": 56863965682356.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.45901", 
    "latest_html": "https://zenodo.org/record/45901", 
    "bucket": "https://zenodo.org/api/files/b0799b59-9385-4758-860e-018c2cb90286", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.45901.svg", 
    "html": "https://zenodo.org/record/45901", 
    "latest": "https://zenodo.org/api/records/45901"
  }, 
  "created": "2016-02-12T14:01:04+00:00", 
  "updated": "2020-01-24T19:25:45.970988+00:00", 
  "conceptrecid": "629926", 
  "revision": 11, 
  "id": 45901, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.45901", 
    "description": "<p>A curated dataset from&nbsp;fh-bigquery:hackernews.stories</p>\n\n<p>Only HN stories with more than 10 comments are included, and only comments from users with more than 10 comments are included.</p>", 
    "license": {
      "id": "CC0-1.0"
    }, 
    "title": "Hacker News Curated Comments Dataset", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "629926"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "45901"
          }
        }
      ]
    }, 
    "keywords": [
      "hacker news, topic models, text, nlp"
    ], 
    "publication_date": "2016-02-10", 
    "creators": [
      {
        "affiliation": "Stitch Fix", 
        "name": "Christopher Moody"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }
  }
}
29,784
72,849
views
downloads
All versions This version
Views 29,78429,776
Downloads 72,84972,817
Data volume 56.9 TB56.8 TB
Unique views 27,05327,045
Unique downloads 52,35452,328

Share

Cite as