{
  "fetched_at": "2026-10-20T01:58:01Z",
  "source_url": "https://www.kaggle.com/competitions/airbus-finance-ml-basics-workshop/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The Twitter airline dataset is a collection of comments posted by Twitter users about their travel experiences with different airlines. The dataset is composed of a total of 5,313 tweets that were gathered over a period of six months.\n\nEach tweet has been labelled as either positive or negative based on the sentiment of the tweet towards the airline.\n\nThe data has been split into training (3,963 rows) and testing (1,350 rows) datasets\nairline_tweets_train.csv - The training set, we will use this dataset to train our models\nairline_tweets_test.csv - The test set, we will evaluate and rank teams with this dataset\nColumns\nId - Numeric Id of the tweet\nairline_sentiment - Sentiment of the tweet, 'positive' 'negative' or 'neutral'\nairline - Name of the airline referenced in the tweet\ntext - Content of the tweet\nretweet_count - Number of retweets performed on tweet\nuser_timezone - Timezone of the user posting tweet",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Welcome to the Airbus Finance NLP Kaggle Competition on classifying Twitter comments regarding airlines.\n\nParticipants will be provided with a dataset of tweets related to various airlines, along with their sentiment labels (positive or negative)(airline_sentiment_train.csv)\nWe will process the text using common Natural Language Processing (NLP) techniques\nWe will train a ML Classification Model\nParticipants will also be provided with a dataset of tweets without a sentiment label (airline_sentiment_test.csv)\nEach team will submit their predictions and see their ranking in the Leaderboard section",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric used will be Accuracy: The number of instances correctly classified divided by the total number of instances. In this case our dataset is very balanced (same number of positives and negatives) so this metric is an appropriate one.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": " - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": " Competition Overview",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Prize",
      "content": "None",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}