{
  "fetched_at": "2026-10-20T08:21:28Z",
  "source_url": "https://www.kaggle.com/competitions/activitytweeting/data",
  "pages": [
    {
      "name": "rules",
      "content": "One account per participant\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\nNo private sharing outside teams\nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all classmates through Canvas.\n\nIndividual participants\nThis is an individual competition. You are not allowed to \"team up\" with others. While you can work together in study groups, all submissions should be individual.\n\nSubmission Limits\nYou may submit a maximum of 10 entries per day.\n\nCompetition Timeline\nStart Date: 02/24/2020 4:00 PM EST\n\nEnd Date: 03/12/2020 11:59 PM EST\n\nYour runs will be scored in two phases. When the competition is active, your runs will be scored on 50% of the test instances and you will be placed in the leaderboard based on this score. At the end of the competition, your runs will be scored on the entire test dataset for the final ranking. Your grade for this assignment will be partly based on the best F1 score you obtain and your ranking in the competition.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\nThe canvas folder for this assignment has three files:\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>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n<h2>Data fields</h2>\n<ul>\n<li><strong>TweetID</strong> - a project-specific id assigned to the tweets</li>\n<li><strong>Label</strong> - 0 or 1, indicating the supervision class label</li>\n<li><strong>TimeOfDay</strong> - a number from 0-23 to show the hour of day when the tweet was tweeted (adjusted for time zones).</li>\n<li>etc...</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>In this assignment, you will develop a text classifier to classify tweets into two classes:\n<ul>\n<li> Class '1': If the tweet mentions the tweeter doing a moderate to high physical activity or how they feel about the mentioned activity</li>\n<li> Class '0': If the tweet does not refer to the tweeter doing a moderate to high physical activity</li>\n</ul>\nFor this task, all tweets will contain at least one word / term that refers to a moderate to high physical activity. However, the tweet may use the activity term in non-activity context (e.g. \"star wars marathon\") or in the context of someone else actually doing the activity or (e.g. the tweeter is watching a basketball game). In such cases, the label should be '0'. \n\n<h2> Dataset </h2>\nOn Canvas, you are provided with a training file of 4000 tweets, and a test file with 1000 tweets. You are expected to train a classifier on train data, and predict labels for each tweet in the test file. The training and test datasets are imbalanced, i.e. the proportion of tweets in the positive and negative classes are not equal in both training and test datasets. You should follow best practices, such as splitting the train file into train and validation sets, to evaluate out-of-sample performance.\n\n<h2>Acknowledgements</h2>\n<p>The dataset is derived from a current research project on identifying sedentary and physical activity mentions in tweets.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is F1-Score. The F1 score is the harmonic mean of 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 score weights recall and precision equally, and a good classification 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\n<h2>Output format</h2>\nEach line in the output file should contain two fields, separated by a comma as below:\n<pre>TweetID,Label</pre>\nwhere TweetID is the id of the tweet from the test file and Label is either 0 or 1. Please refer to the sample_output.txt file for an example. \n\n<p>Note: The file should contain the column names file above. Please follow the format in the sample_output.txt file provided.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}