PEACE: Providing Explanations and Analysis for Combating Hate Expressions

Greta Damo, Nicolás Benjamín Ocampo, Elena Cabrio, Serena Villata

Abstract: The increasing presence of hate speech (HS) on social media poses significant societal challenges. While efforts in the Natural Language Processing community have focused on automating the detection of explicit forms of HS, subtler and indirect expressions often go unnoticed. This demo presents PEACE, a novel tool that, besides detecting if a social media message contains explicit or implicit HS, also generates detailed natural language explanations for such predictions. More specifically, PEACE addresses three main challenging tasks: i) exploring the characteristics of HS messages, ii) predicting hatefulness, and iii) elucidating the reasoning behind system predictions. A REST API is also provided to exploit the tool’s functionalities.