The expression of hate speech against Afro-descendant, Roma, and LGBTQ+ communities in YouTube comments

What is it about?

This paper explores online hate speech targeting Afro-descendant, Roma, and LGBTQ+ communities in Portugal. It uses a dataset of 20,590 YouTube comments, which were manually annotated based on specific guidelines. The study applies linguistic methods to measure the presence of overt and covert hate speech, counter-speech, and offensive speech, and to identify the main language strategies used in hateful messages. The findings emphasize the need to address covert hate speech, which often relies on irony and misleading arguments. This research aims to improve the analysis of online hate speech and support the development of effective detection models for the Portuguese language.

Featured Image