This paper presents an initial investigation of which are the best machine learning techniques to detect offensive language in tweets. An experiment obtained 92% of accuracy and 95% of recall to detect offensive language with Naive Bayes and 90% of accuracy and 92% of recall with Linear SVM.
Full citation
DA COSTA ABREU, Marjory and ARAUJO DE SOUZA, Gabriel (2020). Automatic offensive language detection from Twitter data using machine learning and feature selection of metadata. In: IEEE World Congress on Computational Intelligence 2020 (IEEE WCCI 2020). IEEE.