The TruthAware project, supported by Zanasi & Partners and coordinated by SIMAVI (RO), is funded by the European Commission under the Horizon Europe Framework Programme between 2026 and 2029.
The rapid digitalisation of public communication has increased Europe’s exposure to misinformation, hate speech, and online manipulation that erode trust, provoke tensions, and endanger vulnerable communities. TruthAware will develop an AI-based system for the real-time detection, cross-verification, and contextual analysis of misinformation circulating across multilingual and multimodal social-media streams. Combining natural-language processing, computer vision, virality-pattern analysis, and explainable AI, TruthAware will identify emerging viral narratives, verify their credibility across multiple sources, and evaluate their potential for social impact or harm. The system will provide timely alerts and analytical dashboards to support Law Enforcement Agencies (LEAs), Civil Society Organisations (CSOs), and Non-Governmental Organisations (NGOs) in recognising and mitigating online manipulation campaigns.
The project will conduct three real-world pilot use cases addressing: (i) Misinformation targeting vulnerable groups, (ii) Hate-driven online mobilisation, and (iii) Crisis-related viral falsehoods. Each pilot will validate TruthAware’s performance under realistic data and operational conditions, demonstrating the scalability and effectiveness of the platform. The TruthAware consortium brings together 18 partners from 11 European and associated countries, including large technology developers, research institutes, universities, SMEs, LEAs, NGOs, and authorities, and guaranteeing that the project’s outcomes are both scientifically advanced and operationally relevant to European security and democratic resilience. Z&P leads the development of TruthAware’s multilingual NLP AI model.
