IMSyPP/hate_speech_slo

1---2pipeline_tag: text-classification3 4inference: true5 6widget:7- text: "Sem Mark in živim v Ljubljani. Sem doktorski študent na Mednarodni podiplomski šoli Jožefa Stefana."8language: 9  - sl10license: mit11---12 13# Hate Speech Classifier for Social Media Content in Slovenian Language14 15A monolingual model for hate speech classification of social media content in Slovenian language. The model was trained on 50,000 Twitter comments and tested on an independent test set of 10,000 Twitter comments. It is based on multilingual CroSloEngual BERT pre-trained language model.16 17## Please cite:18Kralj Novak, P., Scantamburlo, T., Pelicon, A., Cinelli, M., Mozetič, I., & Zollo, F. (2022, July). __Handling disagreement in hate speech modelling__. In International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (pp. 681-695). Cham: Springer International Publishing.19https://link.springer.com/chapter/10.1007/978-3-031-08974-9_5420 21## Tokenizer22 23During training the text was preprocessed using the original CroSloEngual BERT tokenizer. We suggest the same tokenizer is used for inference.24 25## Model output26 27The model classifies each input into one of four distinct classes:28* 0 - acceptable29* 1 - inappropriate30* 2 - offensive31* 3 - violent