Conference paper Open Access

The Pushshift Telegram Dataset

Baumgartner, Jason; Zannettou, Savvas; Squire, Megan; Blackburn, Jeremy


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/62959645-07c6-437c-98ed-206f7e4cae37/accounts.ndjson.zst"
      }, 
      "checksum": "md5:a68ec75718218796caba58b8a06f871b", 
      "bucket": "62959645-07c6-437c-98ed-206f7e4cae37", 
      "key": "accounts.ndjson.zst", 
      "type": "zst", 
      "size": 125161770
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/62959645-07c6-437c-98ed-206f7e4cae37/channels.ndjson.zst"
      }, 
      "checksum": "md5:80e678333976597384dcda0054677b67", 
      "bucket": "62959645-07c6-437c-98ed-206f7e4cae37", 
      "key": "channels.ndjson.zst", 
      "type": "zst", 
      "size": 7325115
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/62959645-07c6-437c-98ed-206f7e4cae37/messages.ndjson.zst"
      }, 
      "checksum": "md5:ed90ff295afebccd47262280aecf33f2", 
      "bucket": "62959645-07c6-437c-98ed-206f7e4cae37", 
      "key": "messages.ndjson.zst", 
      "type": "zst", 
      "size": 51942168171
    }
  ], 
  "owners": [
    87836
  ], 
  "doi": "10.5281/zenodo.3607497", 
  "stats": {
    "version_unique_downloads": 1243.0, 
    "unique_views": 1671.0, 
    "views": 1888.0, 
    "version_views": 1888.0, 
    "unique_downloads": 1243.0, 
    "version_unique_views": 1671.0, 
    "volume": 143606853010479.0, 
    "version_downloads": 3366.0, 
    "downloads": 3366.0, 
    "version_volume": 143606853010479.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3607497", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3607496", 
    "bucket": "https://zenodo.org/api/files/62959645-07c6-437c-98ed-206f7e4cae37", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3607496.svg", 
    "html": "https://zenodo.org/record/3607497", 
    "latest_html": "https://zenodo.org/record/3607497", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3607497.svg", 
    "latest": "https://zenodo.org/api/records/3607497"
  }, 
  "conceptdoi": "10.5281/zenodo.3607496", 
  "created": "2020-01-15T21:14:16.904100+00:00", 
  "updated": "2020-01-20T17:11:36.244181+00:00", 
  "conceptrecid": "3607496", 
  "revision": 2, 
  "id": 3607497, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3607497", 
    "description": "<p>The Pushshift Telegram Dataset</p>\n\n<p>The dataset consists of three files:</p>\n\n<p><em>Accounts.ndjson:&nbsp;</em>Provides data for 2.2M Telegram users that were active in the channels we crawled.</p>\n\n<p><em>Channels.ndjson:&nbsp;</em>Provides data for 28K Telegram channels that we crawled.</p>\n\n<p><em>Messages.ndjson: </em>Provides data for 317M Telegram messages that were posted by 2.2M Telegram users in 28K Telegram channels.</p>\n\n<p>Each file is a newline delimited json (ndjson) file that includes a json object with the data for each account/channel/message. The format of each object is according to the Telethon API (<a href=\"https://docs.telethon.dev/en/latest/\">https://docs.telethon.dev/en/latest/</a>), which is a Python interface for Telegram&#39;s API.</p>", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "The Pushshift Telegram Dataset", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3607496"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3607497"
          }
        }
      ]
    }, 
    "keywords": [
      "Telegram", 
      "pushshift"
    ], 
    "publication_date": "2020-01-14", 
    "creators": [
      {
        "affiliation": "Pushshift.io", 
        "name": "Baumgartner, Jason"
      }, 
      {
        "affiliation": "Max Planck Institute", 
        "name": "Zannettou, Savvas"
      }, 
      {
        "affiliation": "Elon University", 
        "name": "Squire, Megan"
      }, 
      {
        "affiliation": "Binghamton University", 
        "name": "Blackburn, Jeremy"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "subtype": "conferencepaper", 
      "type": "publication", 
      "title": "Conference paper"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3607496", 
        "relation": "isVersionOf"
      }
    ]
  }
}
1,888
3,366
views
downloads
All versions This version
Views 1,8881,888
Downloads 3,3663,366
Data volume 143.6 TB143.6 TB
Unique views 1,6711,671
Unique downloads 1,2431,243

Share

Cite as