Nicolo' Fontana is a PhD candidate at Delft University of Technology in the Multi-Actor Systems department. His work focuses on online harms on social media, with particular attention to detecting illegal hate speech and evaluating how well multimodal large language models can support this task.
His research looks at how AI systems interact with social dynamics. He has published work on the behavior of large language models in game-theoretic settings, their use in automated fact-checking, and methods for assessing youth safety on platforms such as TikTok. He is also interested in predicting radicalization in toxic online communities and in using AI agents to simulate contentious online discussions.
Before starting his PhD, Nicolo' worked as a research assistant at Politecnico di Milano, where he obtained an MSc in Computer Science and Engineering with honors. He was also a visiting student at the IT University of Copenhagen, supported by scholarships from the Danish Data Science Academy and Politecnico di Milano.
His research looks at how AI systems interact with social dynamics. He has published work on the behavior of large language models in game-theoretic settings, their use in automated fact-checking, and methods for assessing youth safety on platforms such as TikTok. He is also interested in predicting radicalization in toxic online communities and in using AI agents to simulate contentious online discussions.
Before starting his PhD, Nicolo' worked as a research assistant at Politecnico di Milano, where he obtained an MSc in Computer Science and Engineering with honors. He was also a visiting student at the IT University of Copenhagen, supported by scholarships from the Danish Data Science Academy and Politecnico di Milano.
Latest
- No publications listed yet.