Edit model card
YAML Metadata Error: "datasets[1]" with value "movies subtitles" is not valid. It should not contain any whitespace. If possible, use a dataset id from the huggingface Hub.

bert-based-uncased-hatespeech-movies:

A hatespeech model used to classify text as normal, offensive, hatespeech in Movie subtitles. The model is initially a pre-trained transformer model(bert-based-uncased) which is further trained on Twitter comments which can be normal, offensive and hate to learn the context from social media data. It is then fine-tuned using the movie subtitles dataset.

Please check our paper and if used please cite

@article{von2021hateful,
  title={How Hateful are Movies? A Study and Prediction on Movie Subtitles},
  author={von Boguszewski, Niklas and Moin, Sana and Bhowmick, Anirban and Yimam, Seid Muhie and Biemann, Chris},
  journal={arXiv preprint arXiv:2108.10724},
  year={2021}
}

The dataset and models are available on https://github.com/uhh-lt/hatespeech

Downloads last month
91
Hosted inference API
Text Classification
Examples
Examples
This model can be loaded on the Inference API on-demand.