Sentiment classification is a challenging research issue in a resource-poor language like Bengali. The inadequacy of the benchmark dataset and the limited amount of e-textual content or reviews in the Bengali language resulted in the sentiment classification task being more complicated. Moreover, in recent years people frequently using code-mixed or code-switched texts which is also a crucial concern for machine learning model developers.

 **For this competition,  we released a dataset comprised of around 8.5K code-mixed texts labeled in two sentiment categories: `Positive (1)`, and `Negative (0)`.** 

## Files

*   **train.csv** - the training set
*   **test.csv** - the test set
*   **sample_submission.csv** - a sample submission file in the correct format


## Columns

*   `Id` - Unique Number
*   `Reviews` - Bengali reviews
*   `Sentiment` - Sentiment category either `0 or 1`