metadata

language:
  - en
tags:
  - bert
  - hate-speech
  - hatespeech
  - hate
license: cc-by-nc-sa-4.0

hate-speech-bert (base-uncased)

Fine-tuned hate speech detection model on English language using Toraman22 v2 dataset published at https://github.com/avaapm/hatespeech

Class labels:

"0": Neutral

"1": Offensive

"2": Hate

We split 80-20 train-test randomly.

5 epochs train_loss: 0.0948

eval_f1 is 0.9426, eval_accuracy is 0.9430

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}
}