🤖 AI Summary
Social media accelerates the dissemination of far-right extremism and anti-democratic discourse, necessitating intelligent monitoring tools that balance freedom of expression with societal safety. To address this, we develop a multimodal AI monitoring platform tailored to Germany’s digital public sphere. Our approach introduces the first event-driven–routine-tracking dual-mode framework that jointly optimizes sensitive content detection and freedom-of-expression preservation. It leverages a German-specific BERT variant and a temporal classifier, integrated with incrementally crawled, multi-source social media data and a fact-checking knowledge graph. The platform enables high-accuracy, dynamic modeling of far-right discourse: in early validation, it successfully flagged multiple extremist mobilization events; its trend prediction accuracy improved by 37% over baseline methods. This significantly enhances responsiveness for journalists, researchers, and policymakers confronting democratic threats.
📝 Abstract
Social media increasingly fuel extremism, especially right-wing extremism, and enable the rapid spread of antidemocratic narratives. Although AI and data science are often leveraged to manipulate political opinion, there is a critical need for tools that support effective monitoring without infringing on freedom of expression. We present KI4Demokratie, an AI-based platform that assists journalists, researchers, and policymakers in monitoring right-wing discourse that may undermine democratic values. KI4Demokratie applies machine learning models to a large-scale German online data gathered on a daily basis, providing a comprehensive view of trends in the German digital sphere. Early analysis reveals both the complexity of tracking organized extremist behavior and the promise of our integrated approach, especially during key events.