{
  "fetched_at": "2026-10-19T10:59:28Z",
  "source_url": "https://www.kaggle.com/competitions/clickbait-news-detection/data",
  "pages": [
    {
      "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
    },
    {
      "name": "data-description",
      "content": "You are provided with labeled articles. Each article consists of label and body. The task is to predict the label (clickbait, news or other).\n\nFile descriptions:\n\n- **train.csv** - the training set\n- **test.csv** - the test set\n- **valid.csv** - the validation set\n- **unlabeled.csv** - additional articles to improve your models",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This competition is designed to explore various semi-supervised and transfer learning approaches to NLP, namely, to text classification.\n\nHere you're going to classify articles into news, clickbait and other. Do resort to unlabeled data to improve classification. Try various SotA approaches: ULMFiT, BERT fine-tuning etc.\n\nPlease share your findings via Kernels and Discussions.\n\nCredit for this competition goes to iPavlov research group and personally to Vladislav Lyalin. The competition is another launch of [this one](https://www.kaggle.com/c/dlinnlp-spring-2019-clf/overview) organized as a part of \"DL in NLP\" course by iPavlov. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is **micro-averaged of F1-Score**. \n\n## Submission Format\nFor every review in the dataset, submission files should contain two columns: **id** and **label**. Label should be one of the following: news, clickbait or other. See **sample_submission.csv**",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}