{
  "fetched_at": "2026-10-19T21:37:46Z",
  "source_url": "https://www.kaggle.com/competitions/advnlp-constructive-comments-classification/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.</li>\n<li>Now click on submit button.</li>\n\n<h3>NOTE: </h3>\n<p> Upload your Assessment Notebook with FileName as  <b>YourName_Submission</b> (In case using multiple files, upload a zip file) </p>\n\nGoogle Form for Submission: https://forms.gle/heTJ7CJMSE2QiNtV8\n(Only upload final submission for evaluation)\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
    }
  ]
}