Studying Socially Unacceptable Discourse Classification (SUD) through different eyes: "Are we on the same page ?"

Abstract

We study Socially Unacceptable Discourse (SUD) characterization and detection in online text. We first build and present a novel corpus that contains a large variety of manually annotated texts from different online sources used so far in state-of-the-art Machine learning (ML) SUD detection solutions. This global context allows us to test the generalization ability of SUD classifiers that acquire knowledge around the same SUD categories, but from different contexts. From this perspective, we can analyze how (possibly) different annotation modalities influence SUD learning by discussing open challenges and open research directions. We also provide several data insights which can support domain experts in the annotation task.

References in corpus (4)

• Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizations
• Transfer Learning for Hate Speech Detection in Social Media
• Hate Towards the Political Opponent: A Twitter Corpus Study of the 2020 US Elections on the Basis of Offensive Speech and Stance Detection
• Leveraging Multilingual Transformers for Hate Speech Detection