nattlyandrahma-sentiment-model
Sentiment classifier (positive / negative) fine-tuned from distilbert-base-uncased.
Group members: Namugwanya Rahmah and Nattabi Joanitah Dataset: nattlyandrahma-sentiment-model
Results on the test set
| Metric | Score |
|---|---|
| Accuracy | 0.91 |
| F1 | 0.91 |
Example predictions
| Review | Predicted sentiment | Score |
|---|---|---|
| This movie was fantastic! The acting was brilliant. | POSITIVE | 0.9974 |
| Terrible experience, I want my money back. | NEGATIVE | 0.9901 |
| The movie was okay, but the story was predictable. | NEGATIVE | 0.9989 |
Limitations
Trained on English movie reviews only. Struggles with sarcasm and Luganda/English mixed text.
- Downloads last month
- -