{
  "fetched_at": "2026-10-19T21:37:41Z",
  "source_url": "https://www.kaggle.com/competitions/advanced-nlp-l1-hackthon-1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "**What files do I need?**\n\nYou'll need train.csv which contains the input data to train ml model, Use test.csv data for predictions, you can refer to sample_submission.csv to understand the output format\n\n**What is the data format?**\n\ntrain.csv : Contains id, text, target\n \n(id: unique Id for the text, text: the comments text, target: Indicator whether given comment text is Constructive or not)\n\n**What am I predicting?**\n\nYou will be predicting the target for the given corpus of comments text in test.csv. Make sure you submit your predictions with correct label names referenced in the description.\n\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h1>Advance NLP - Hackathon 1</h1>\n\nClassification of text comments as Constructive vs Non-Constructive.\n\nThe main intention of this hackathon is to assess the understanding of concepts discussed so far in this course. Here the problem statement is a simple text classification on whether the provided comment is constructive or not. \nThese comments are grabbed from online competing platforms where a user will have multiple emotions and articulating approaches in describing the same feeling. Now our task is to classify all those comments into two specific classes.\n<li> Constructive - 1</li>\n<li>Non-Constructive - 0</li>\n\n<h2>Steps to Follow : </h2>\n\n<li>Read train.csv file which contains two columns id and comment text. Then build a classification model on top of this dataset .</li>\n<li>Using the model create class labels for each record in test.csv and save it as in the form of provided sample submission file. In the 1st hackthon, you are allowed to use only ML based models. </li>\n<li>Now click on submit button.</li>\n\n\nMore Details about dataset: https://www.kaggle.com/mtaboada/c3-constructive-comments-corpus\n\n\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "**1. Evaluation Metric**\n\nThe evaluation metric for this competition is Mean F1-Score. 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:\n\n\n$$F1 =2\\frac{p.r}{p+r}$$  \n\nwhere  $$p=\\frac{tp}{tp+fp}$$,  $$r=\\frac{tp}{tp+fn}$$ \n\n**2. Submission Format**\nFor every text in the test set, submission files should contain two columns: id and target.\n\nThe submission file should contain the column headers: id, predicted\n\nExample:\nid, \ttarget\nsource\\_30306595\\_50, 0 \nsource\\_28078752\\_39, 1\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}