Detection and Censorship of Offensive Language in Extended Texts in Portuguese
Lucas Lenoch de Souza, Franciele Beal, André Roberto Ortoncelli, Marlon Marcon · 2024
This article addresses the problem of detecting and censoring offensive language in extensive Brazilian Portuguese texts on the web. This paper proposes a pipeline for classifying and censoring extensive texts, focusing on comments, posts, and articles using NLP techniques. The results include an in-depth review of current methods for offensive content classification in Portuguese and the implementation of a BERTimbau-based pipeline for offense detection. This work represents a significant advancement in the state-of-the-art NLP in Portuguese, promoting safer and more respectful online environments for users, especially children.