Invied Talk
NLP for CounterSpeech - Trends and Open Challenges
Marco Guerini - Fondazione Bruno Kessler (FBK)
This talk addresses the use of argumentation-based textual responses—referred to as counterspeech—to combat online hate speech, an emerging topic in Natural Language Processing. Specifically, it explores the automated generation of counterspeech as an effective strategy for intervening in harmful online discourse. Following an overview of the field, various methodologies for collecting high-quality data and effective generation strategies, including state-of-the-art LLMs, are discussed. The talk also examines critical challenges at the intersection of online safety, argumentation strategies and the effectiveness of NLP interventions.
Marco Guerini is the head of the Language and Dialogue Technologies (LanD) group at Fondazione Bruno Kessler (FBK). He works on NLP for persuasive communication, sentiment analysis and social media. In recent years his research has focused on the development of AI technologies to support counter speech generation to fight online hate and misinformation. He graduated in Philosophy and received his Ph.D. in Information and Communication Technologies from the University of Trento. He is author of several scientific publications in top-level conferences and international journals, organiser of workshops and shared tasks and coordinator of European projects.