group1-sentiment-model

This model is a binary sentiment classifier for English movie reviews It was fine-tuned from distilbert-based-uncased on the IMDB dataset

Sentiment classifier (positive / negative) fine-tuned from distilbert-base-uncased.

Intended Use

This model is intended for sentiment analysis of English movie reviews.

Group members: TODO -Mary Nabakka -Winnie Among Dataset: TODO (name of the Hugging Face dataset you used) The model was fine-tuned on the stanfordnlp/imdb dataset.

Results on the test set

Metric	Score
Accuracy	0.91444
F1	0.9153

Example predictions

TODO: paste 3 examples

Test the model with three example reviews.

examples = [ "This movie was absolutely fantastic!", "Terrible experience, I want my money back.", "It was an average movie with a few good moments." ]

Print predictions for the model card.

for review in examples: print(review) print(clf(review))

Limitations

TODO: e.g. trained on English movie reviews only; struggles with sarcasm and Luganda/English mixed text.

• Trained mainly on English movie reviews.
• May struggle with sarcasm and mixed Luganda-English text.
• May not generalize well outside the movie-review domain.