Hate Speech Berturk

🚀 hate-speech-berturk (base-uncased)

A fine-tuned hate speech detection model for the Turkish language, leveraging the Toraman22 v2 dataset available at https://github.com/avaapm/hatespeech.

🚀 Quick Start

This is a fine-tuned hate speech detection model for the Turkish language. It uses the Toraman22 v2 dataset published at https://github.com/avaapm/hatespeech.

Class Labels

• "0": Neutral
• "1": Offensive
• "2": Hate

Dataset Split

We randomly split the dataset into 80% for training and 20% for testing.

Training Results

• After 5 epochs, the train_loss is 0.1571.
• The eval_f1 is 0.9094, and the eval_accuracy is 0.9092.

📚 Documentation

BibTeX entry and citation info

@InProceedings{toraman2022large,
  author    = {Toraman, Cagri  and  \c{S}ahinu\c{c}, Furkan and Yilmaz, Eyup Halit},
  title     = {Large-Scale Hate Speech Detection with Cross-Domain Transfer},
  booktitle = {Proceedings of the Language Resources and Evaluation Conference},
  month     = {June},
  year      = {2022},
  address   = {Marseille, France},
  publisher = {European Language Resources Association},
  pages     = {2215--2225},
  url       = {https://aclanthology.org/2022.lrec-1.238}
}

📄 License

This model is released under the CC BY-NC-SA 4.0 license.