# Brazilian Tweet Sentiment Analysis Challenge — Data

来源：https://www.kaggle.com/competitions/TweetSentimentBR/data

采集时间：2026-10-19T20:41:42Z

We will have two sets of data in csv format, the data for training the model, with 50000 lines, and the data for classification with 5000 lines. The main variable you should sort on will be `sentiment`.

##Files

* **Train.csv** – the training set
* **Test.csv** – the test suite
* **Sample_Submission.csv** – a sample submission file in the correct format

## Columns

- `id`: Integer
- `tweet_text`: String
- `tweet_date`: Date and time
- `sentiment`: Categorical (`1` for Positive, `0` for Negative)
- `query_used`: Categorical ( `:(`, `:)` )