{
  "fetched_at": "2026-10-19T10:14:53Z",
  "source_url": "https://www.kaggle.com/competitions/congressionaltweetcompetitionspring2022/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n*   **congressional_tweet_training_data.csv** - the training set\n*   **congressional_tweet_test_data.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this competition, you will be working with a **Congressional Twitter Dataset**. The dataset is a collection of tweets posted by Congressional politicians on Twitter [excluding tweets with no hashtags.].\n\nThe training dataset includes tweets posted, and a few features associated with tweets including the partisanship information of the politician who posted the tweet. The test dataset has the same features excluding the partisanship id [for convenience, the party classification has been set to 'D' in the test dataset].\n\nYour task will be to correctly predict the partisanship of the politician who posted the tweet(s) by analyzing tweet-specific information.\n\nDescriptive information about the features included in the dataset:\n\n***Id*** : id number associated with the tweet\n***favorite _ count*** : number of times the tweet was favorited\n***full _ text*** : full text of the tweet\n***hashtags*** : list of hashtags included in the tweet\n***retweet _ count*** : number of times the tweet has been retweeted \n***year*** : year of the tweet\n***party*** : partisanship of the owner of the tweet [D = 'Democrat', R = 'Republican']",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "You will be evaluated based on the '***accuracy***' of your prediction. For the definition of accuracy, please check: https://developers.google.com/machine-learning/crash-course/classification/accuracy",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}