{
  "fetched_at": "2026-10-19T08:19:38Z",
  "source_url": "https://www.kaggle.com/competitions/dm2020-hw2-nthu/data",
  "pages": [
    {
      "name": "data-description",
      "content": "- tweets_DM.json - Raw data from Twitter\n\n- emotion.csv - Lists the emotion labels per tweet_id\n\n- data_identification.csv - A file that identifies membership of training or testing set per tweet_id. Note that you won´t be \nprovided with the labels for the testing set, but you will have to predict for these when you make your submission.\n\n- sampleSubmission.csv - A submission format you should follow for submitting to the competition\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this competition, we provide a dataset which was crawled from Twitter, and we have already labeled the emotion for these tweets by some specific hashtags in the original text. There are 8 classes (or say emotions) in our dataset: anger, anticipation, disgust, fear, sadness, surprise, trust, and joy.\n\nYou have to clean the data by doing some pre-processing first. Then, apply feature engineering or any other data mining technique you have or haven't learned in the Data Mining course. The final goal is to learn a model that is able to predict the emotion behind each tweet.\n\n## Acknowledgements\nWe thank IDEA Lab for providing this dataset, as well as evanyu and thisray for making all of this possible.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "You will be evaluated by comparing your Submission CSV to the ground truth Solution CSV with respect to a chosen the Mean F1 Score.\n\nThis competition is worth 30% of your grade for the DM2020\\_Lab2\\_Homework. The scoring will be given according to your place in the Private Leaderboard ranking:\n\n- Bottom 40%: Get 20% of the score (ie. 20% of 30% )\n- Top 41% - 100%: Get (101-x)% of the score, where x is your ranking in the leaderboard (ie. (101-x)% of 30% )\n\n## Submission Format\nSubmit a CSV file with your predictions. It should contain two string type columns: id and emotion. Make sure you include the headers as well\n\nid, emotion\n0x356d9a, surprise\n0x2c7743, surprise\n0x2c1eed, surprise\n0x2826ea, surprise\netc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "## Competition Rules\n \n- You can only submit 20 submissions per day\n- Only one student per team\n- Only one team per student\n- Don´t share code directly with other people\n- Don´t cheat\n- Have fun",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}