Monitoring and preventing online hate speech

"IMSyPP – Innovative Monitoring Systems and Prevention Policies of Online Hate Speech" aims to automatically detect hate speech in several languages, to identify triggers, to recommend effective counter narratives, and to propose policies to the European communication regulators. The data will be manually annotated for types of hate speech, and quality carefully controlled. We will develop hate speech models by applying advanced machine learning methods. The models will be deployed in online settings and used to analyze the large amounts of data already collected. This will allow to analyze mechanisms and trends in hate speech, and identify different types of triggers. We will conduct a pilot study on possible counter narratives and develop recommendations.

Researcher: Fabiana Zollo
Duration: 01/03/2020 - 28/02/2022