Hate speech is a language that attacks or denigrates a specific group based on their characteristics, such as their race, ethnicity, or sexual orientation. Hate speech became widespread and spread through social networks, blogs, videos, and other communication channels. With anonymity and a sense of impunity, people feel encouraged to spread their hatred on the internet. In this work, we used the BERT model for the Portuguese language called BERTimbau to classify hate speech in three datasets in Portuguese, available in the literature: OFFCOMBR-2, OFFCOMBR-3, and Fortuna et. al. (2019) dataset. Still, we performed some preprocessing and an oversampling technique on the datasets. Finally, we compared the results obtained with results obtained by works available in the literature. Experiments with BERTimbau, using preprocessing and oversampling obtained better results than other classification techniques.

Social Media has revolutionized how individuals, groups, and communities interact. This immense quantity of unstructured data holds valuable information expressed in informal language. However, automatically extracting this information using Natural Language Processing requires adaptations of traditional methods or the development of new strategies capable of extracting information tackling web-prone language. BERT, a Deep Learning methodology proposed by Google in 2018, brought transfer learning to Natural Language Processing. In this work, we used a BERT model for the Portuguese language called BERTimbau to create models for Sentiment Analysis, Aspect Extraction, Hate Speech Detection, and Irony Detection. We experimented with the two BERTimbau models, base and large. Finally, we compared the results obtained in each task. Experiments with BERTimbau based models obtained improved results, F-Measure of 0.88 and 0.89 in Sentiment Analysis and Hate Speech Detection tasks, respectively, compared to classical Machine Learning approaches.