{
  "fetched_at": "2026-10-19T19:05:40Z",
  "source_url": "https://www.kaggle.com/competitions/classifying-20-newsgroups/data",
  "pages": [
    {
      "name": "rules",
      "content": "<h3>Team size</h3>\n<p>You should participate individually in this competition.</p>\n\t<!-- Begin Base Rules -->\n    <h3>One account per participant</h3>\n    <p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\n    <h3>No private sharing outside teams</h3>\n    <p>\n        Privately sharing code or data outside of teams is not permitted.\n        It's okay to share code if made available to all participants on the forums.\n    </p>\n    <h3>Team Mergers</h3>\n    <p>Team mergers are not allowed in this competition.</p>\n    <h3>Submission Limits</h3>\n    <p>You may submit a maximum of 5 entries per day.</p>\n    <p>You may select up to 2 final submissions for judging.</p>\n    <h3>Competition Timeline</h3>\n    <p>Start Date: <strong>3/12/2018</strong></p>\n    <p>End Date: <strong>4/14/2018 12:00 AM UTC</strong></p>\n\t<!-- End Base Rules -->\n<h3>Final submission</h3>\n<p>\nThe public leaderboard only shows the results of evaluation on 50% of the test set. At the end of the competition you should select two of your best submissions, which will then be evaluated on the other 50% of the test set unseen during the competition.\n</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p>Participants should train their models using the <strong>train.csv</strong> file, and submit the predicted labels for the messages from <strong>test.csv</strong>. The submission file should have the same format as the <strong>sample_submission.csv</strong> (i.e. 2 columns - id and predicted label for the message with respective id). Submissions should contain predicted labels for each message in the test set.</p>\n\n<p>The dataset contains over 18000 messages with assigned topic labels, and is split into train and test parts. The training dataset contains around 11300 labelled messages and the test dataset contains 7500 messages without label (the task is to predict these labels). Below is the full list of labells and corresponding topics:</p>\n\n<p> 0 - alt.atheism </p>\n<p> 1 - comp.graphics </p>\n<p> 2 - comp.os.ms-windows.misc </p>\n<p> 3 - comp.sys.ibm.pc.hardware </p>\n<p> 4 - comp.sys.mac.hardware </p>\n<p> 5 - comp.windows.x </p>\n<p> 6 - misc.forsale </p>\n<p> 7 - rec.autos </p>\n<p> 8 - rec.motorcycles </p>\n<p> 9 - rec.sport.baseball </p>\n<p> 10 - rec.sport.hockey </p>\n<p> 11 - sci.crypt </p>\n<p> 12 - sci.electronics </p>\n<p> 13 - sci.med </p>\n<p> 14 - sci.space </p>\n<p> 15 - soc.religion.christian </p>\n<p> 16 - talk.politics.guns </p>\n<p> 17 - talk.politics.mideast </p>\n<p> 18 - talk.politics.misc </p>\n<p> 19 - talk.religion.misc </p>\n</p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - the training set</li>\n<li><strong>test.csv</strong> - the test set</li>\n<li><strong>sample_submission.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n<h2>Data fields</h2>\n<ul>\n<li><strong>id</strong> - unique id to a given message</li>\n<li><strong>message</strong> - the text of a message</li>\n<li><strong>topic</strong> - the label of a message's topic</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>This competition's main goal is to apply the machine learning algorithms you have learned in a text classification task. The task is to classify text messages from the 20 newsgroups dataset by their topic.\n</p>\nThe dataset contains around 18000 messages from 20 different newsgroups (more details in the Data section).\n\n### Acknowledgements\n\nThe data source:  http://qwone.com/~jason/20Newsgroups/",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The leaderboard is formed based on the classification accuracy score.</p>\n\n<h2>Submission Format</h2>\n<p><strong>For every message in the test dataset</strong>, submission files should contain two columns: id and topic.</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>id,topic<br />0,1<br /><span style=\"font-size: 14px; line-height: 1.4em;\">2,8<br />3,0<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\"><span style=\"font-size: 14px; line-height: 1.4em;\">etc.</span></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}