{
  "fetched_at": "2026-10-20T07:26:47Z",
  "source_url": "https://www.kaggle.com/competitions/annihilate-hates/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n*   **train.csv** - the training set is a CSV file containing S. No., text and task_1 columns. \n*   **test.csv** - the test set is a CSV file containing S. No. and text columns.\n*   **sample_submission.csv** - a sample submission file with the S. No. and task_1 columns in the correct format.\n\n## Columns\n\n*   `S. No.` - row numbers\n*   `text ` - sentences in native scripts\n*   `task_1 ` - classes (HOF or NOT)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# HASOC-2023 Task 4 (FIRE 2023): Annihilate Hates\n\n## Task objective:\nThe objective of the task is to detect hate speech in Bengali, Bodo, and Assamese languages. It is a binary classification task. Each dataset (for the three languages) consists of a list of sentences with their corresponding class (hate or offensive (HOF) or not hate (NOT)). Data is primarily collected from Twitter, Facebook, or youtube comments. The Macro F1 score will be the yardstick of the task. Team rank will be determined based on the Macro F1 score.\n\n## Run submission guidelines:\n- Submission should be in a CSV file. \n- CSV file must contain S. No. and task_1 column.\n- DO NOT SHUFFLE ROWS ON THE TEST SET.\n\n### For more details, participants can refer to\n\nHate Speech Detection in Hindi, Marathi and Bengali: https://aclanthology.org/2022.paclic-1.94.pdf\nAssamese Hate Speech Detection: https://ieeexplore.ieee.org/abstract/document/10183497/\n\n##### Please visit our website: https://sites.google.com/view/hasoc-2023-annihilate-hates/home and join the WhatsApp group for further queries.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Team rank will be determined based on the Macro F1 score. \n\n\n## Submission File\nThe submission file should be in CSV format.  S.No column contains text numbers, and task_1 contains the predicted class, either HOF or NOT.\n\n\n    S.No,task_1\n    1,NOT\n    2,HOF\n    3,NOT\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!\n\n# IMPORTANT NOTES:\n- The maximum submission per day per team is 5.\n- The teams must officially register at the  HASOC-2023 (FIRE 2023) Google Form to participate in the task. HASOC form is available under the **Registration**tab on the **Annihilate Hate** website, and you need to agree to the terms of the participation.\n- The samples in this task contain explicitly hateful statements that can be harmful to vulnerable groups. The organizers neither supported nor authored these statements. They are picked from Facebook and Youtube.\n- DO NOT SHUFFLE ROWS ON THE TEST SET.\n\n##### In case of any issues, contact the organizers here https://sites.google.com/view/hasoc-2023-annihilate-hates/home.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}