{
  "fetched_at": "2026-10-20T05:16:04Z",
  "source_url": "https://www.kaggle.com/competitions/csse4375-assignment1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Files\n\n*  4375train.csv** - the training set\n*  4375test.csv** - the test set\n\n\n## Columns\n\n*   `example_id` - definition of example_id\n*   `sentence` - hate/non-hate sentence\n*    `dataset` - where the data is retrieved from\n*    `index` - index\n*    `guideline` - sub-category of the type of hate/non-hate sentence\n*    `label` - 0 for non-hate and 1 for hate sentences",
      "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
    },
    {
      "name": "abstract",
      "content": "The goal of this assignment is to build a classifier that can identify hate or non-hate sentences. \nYour task is to build an accurate binary classifier to detect hate or non-hate senteces (0 for non-hate sentences and 1 for hate sentences). \n\nThe 4375train.csv and 4375test.csv contains two datasets for training and testing. Both files contain additional columns that you may need to remove during the data preprocessing stage. Each data item contains its id, sentence, dataset, index, guideline, and label. Based on your implementation, you will eliminate some of the columns (e.g: dataset, index, and guideline columns). \n\nPlease refer to data section to obtain the two datasets.\n\nNote that your classifier should work on data apart from the provided .csv file. TA will test your code on data items that is not provided in train or test files. \n\nYour code should include the following, \n1. Data preprocessing\n2. Your classifier architecture\n3. Training your classifier using 4375train.csv\n4. Evaluating the performance of your classifier using the 4375test.csv\n5. Noting the performance of your classifier (accuracy). \n\nWhat to submit: \n1. Your code through kaggle notebook. Below are the guidelines to access the notebook:\na. Go to \"Submit Predictions\", then select \"Notebook\". This will open the notebook. \nb. Your notebook will use the dataset under data bar in the competition. However, I will provide you the path for datasets. \n-/kaggle/input/csse4375-assignment1/4375train.csv\n-/kaggle/input/csse4375-assignment1/4375test.csv\n\n2. You can implement your code, and save your model predictions into a \"submission.csv file\". This file should include \"id\" and the \"label\" (this label is your predicted label). \n3. Please include your name, netID as comments in your note book. \n4. Add comments describing your code. \n5. You may add additional comments such as challenges you faced, if the code is working or not, etc\"\n6. You should upload your solution through the notebook, uploading the .csv only may not consider as your final grade for the assignment. (i.e; kaggle will provide you a score, but this score is not your final score for the assignment). \nThe due data is 30th Oct, 2023 at 11.59pm",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}