{
  "fetched_at": "2026-10-20T04:44:11Z",
  "source_url": "https://www.kaggle.com/competitions/advance-nlp-hackathon-2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>In recent decades we have noticed a considerable increase in reports or confession posts of abuse victims on twitter. Most of the time victims do not report it to their guardians or the concerned authorities. Teenagers and minorities are the most affected group of abuse. Part of these victims tweets about their incident to let go of pain and suffering or as a cry for help. Identifying such reports are challenging because of the unavailability of annotated training data, and a high degree of data sparsity. To address this we are hosting this competition, So all the best for all of you.!</p>\n\n\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - the training set</li>\n<li><strong>test.csv</strong> -  test data file</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>tweet_id</strong> - tweet id unique for each record</li>\n<li><strong>tweet</strong> - tweet text</li>\n<li><strong>label</strong> - class label and classes are as follows - { 1 : Report, 2 : Empathy, 3 : General}</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "\n<h2>Advance NLP Hackathon - 2 </h2>\n\n<p>Classification of tweets text into three segments/classes\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 tweet is a general tweet or is for stating empathy or do we need to report tweet as it is a abusive tweet.\nThese tweets are scraped from Twitter. Now our task is to classify all those tweets into specific classes.\n</p><li>Report - 1</li>\n\n<li>Empathy - 2</li>\n\n<li>General - 3</li>\n<p></p>\n\n<h2> Steps to follow : </h2>\n\n<ul>\n<li>Read train.csv file which contains three columns tweet_id, tweet and label. 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>Convert all the columns type to string(str)</li>\n<li>Now click on submit button.</li>\n</ul>\n\n<h2>NOTE : </h2>\n<p>Upload your Assessment Notebook with FileName as YourName_Submission (In case using multiple files, upload a zip file) here <a>https://drive.google.com/drive/folders/1Ow-8epIPNDuxYPUjEKRGawZMn_HpIWLA?usp=sharing</a>\n</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "**1. Evaluation Metric**\n\nThe evaluation metric for this competition are\n<li>F1-score for each class</li>\n<li>Micro Averaged F1 scores</li>\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: tweet_id, label\n\nNOTE :: All coumns in the submission file file should be in string format. Please do this conversion before submission of results.\n\nExample:\ntweet_id,\tlabel\n1.268745e+18, 3 \n1.269175e+18, 3\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}