## Evaluation Metric

Submissions are evaluated using **macro F1-score**. This metric was chosen because:
1. It accounts for both precision and recall
2. The macro averaging gives equal weight to each class, which is important for our balanced dataset
3. It handles the multi-class nature of our problem (positive, negative, neutral)

## Submission File Format

For each ID in the test set, you must predict the sentiment class. The file should contain a header and have the following format:

id,sentiment
0,positive
1,negative
2,neutral
...

The 'sentiment' column must contain one of three values: 'positive', 'negative', or 'neutral'.