# Bootcamp: The Basics of ML — Data

来源：https://www.kaggle.com/competitions/bootcamp-the-basics-of-mla/data

采集时间：2026-10-20T01:57:53Z

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.

Each tweet has been labelled as either positive or negative based on the sentiment of the tweet towards the airline.

The data has been split into training (3,963 rows) and testing (1,350 rows) datasets
`airline_tweets_train.csv` - The training set, we will use this dataset to train our models
`airline_tweets_test.csv` - The test set, we will evaluate and rank teams with this dataset
Columns
`Id` - Numeric Id of the tweet
`airline_sentiment` - Sentiment of the tweet, 'positive' 'negative' or 'neutral'
`airline` - Name of the airline referenced in the tweet
`text` - Content of the tweet
`retweet_count` - Number of retweets performed on tweet
`user_timezone` - Timezone of the user posting tweet