Automatically classify movies by genre from plot summaries. This model is intended for educational and academic purposes, such as demonstrating NLP text classification and fine-tuning transformer models.

Direct Use

python

from transformers import DistilBertTokenizerFast, DistilBertForSequenceClassification, pipeline

tokenizer = DistilBertTokenizerFast.from_pretrained("Raissa2502/movie-genre-classifier")
model = DistilBertForSequenceClassification.from_pretrained("Raissa2502/movie-genre-classifier")

classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)

prediction = classifier(
    "A young wizard discovers he has magical powers and attends a school for wizards."
)

print(prediction)

Bias, Risks, and Limitations

Movie plots may belong to multiple genres, but the model predicts only one.
Performance depends on the quality and balance of the training data.

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

Training Details

3 epochs, batch size 8, learning rate 5e-5

Testing Data, Factors & Metrics

Metrics

The model was evaluated using:

Accuracy
Weighted F1-score

These metrics are appropriate for multi-class genre classification and help measure overall performance while accounting for class imbalance.