{
  "fetched_at": "2026-10-24T10:02:14Z",
  "source_url": "https://www.kaggle.com/competitions/cs725-assignment-2/data",
  "pages": [
    {
      "name": "rules",
      "content": "<h1>Mentioned in Overview Tab</h1>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<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>page_likes</strong> - number of likes the facebook page has (shows user support for a wall posts)</li>\n<li><strong>page_checkin</strong> -number of people visited the place (only applicable to places, institutions, hotels, etc. pages )</li>\n<li><strong>daily_crowd</strong> - count of users that are engaged with the page ( who frequently comment, share posts of page)</li>\n<li><strong>page_category</strong> - defines the category of source of document ( eg: brand, company, artist, etc.)</li>\n<li><strong>F1-F8</strong> - These features are aggregated by page, by calculating min, max, average, median and standard deviation of essential features.</li>\n<li><strong>c1</strong> - The total number of comments before selected base date/time</li>\n<li><strong>c2</strong> - The number of comments in last 24 hours, relative to base date/time.</li>\n<li><strong>c3</strong> - The number of comments in last 48 to last 24 hours relative to base date/time.</li>\n<li><strong>c4</strong> - The number of comments in the first 24 hours after the publication of post but before base date/time.</li>\n<li><strong>c5</strong> - The difference between c2 and c3.</li>\n<li><strong>base_time </strong>- Selected time in order to simulate the scenario. ( decimal encoding 0-71)</li>\n<li><strong>post_length</strong> - Character count in the</li>\n<li><strong>share_count</strong> - This features counts the no of shares of the post, that how many peoples had shared this post on to their timeline.</li>\n<li><strong>promotion</strong> - To reach more people with posts in News Feed, individual promote their post and this features tells that whether the post is promoted(1) or not(0).</li>\n<li><strong>h_target</strong> - Hours after base_time when target variable is recorded</li>\n<li><strong>post_day</strong> - day of week when post was posted</li>\n<li><strong>basetime_day</strong> - day of week corresponding to base_time (when data was collected)</li>\n<li><strong>target</strong> - volume of comments received after h_target hours of base_time <ul><li>1: High volume of comments</li> <li>2: Medium volume of comments</li><li>3: Low volume of comments</li></ul></li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>Assignment link: https://www.cse.iitb.ac.in/~pjyothi/cs725/assgmt2/</p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is <a href=\"https://www.kaggle.com/wiki/MeanFScore\"> Mean F1-Score</a>. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:</p>\n<p>\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]</p>\n<p>The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.</p>\n<h2>Submission Format</h2>\n<p><strong>For every instance in the dataset</strong>, submission files should contain two columns: Id and predicted_class. predicted_class should denote the predicted category of volume of comments i.e. 1, 2 or 3.</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>Id,predicted_class<br />1,1<br /><span style=\"font-size: 14px; line-height: 1.4em;\">8,2<br />9,3<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">10,2<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">etc.</span></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}