Fine tunning of bert-base-german-cased[1] using the HASOC dataset[2] to detect hate speech, specifically in german language.
Interpreting results:
- Label 0 -> No hate speech detected
- Label 1 -> Hate speech detected
References:
-
[1] Chan, B. Möller, T. Pietsch, M. et al. (2019). bert-base-german-cased. Retrieved from: https://huggingface.co/bert-base-german-cased
-
[2] Mandl, T. Modha, S., Shahi, G., et al. (2020). Overview of the HASOC track at FIRE 2020: Hate Speech and Offensive Content Identification in Indo-European Languages. Forum for Information Retrieval Evaluation. Dataset retrieved from: https://hasocfire.github.io/hasoc/2019/dataset.html