A Caccia di Fake News (PCTO Summer Camp 2026)
School outreach seminar - PCTO Summer Camp Informatica & Intelligenza Artificiale 2026, University of Udine.
Michael Soprano
Researcher
Welcome to my personal webpage. I am a Researcher at the University of Udine and a member of the Social, Mobile, Data & Crowd Laboratory . I hold a PhD in Computer Science and Mathematical and Physical Sciences.
My research interests include Human Computation, Crowdsourcing, Information Retrieval, and Large Language Models. My current work focuses in particular on the use of crowdsourcing to address the growing challenge of misinformation.
You can explore my PhD thesis (written in English), as well as my Master’s , Bachelor’s , and High School theses (written in Italian).
Crowdsourced Fact-Checking for Misinformation: A Journey Through Nine Years of Research (2018–2026)
Workshop Talk - Workshop "AI and Disinformation", held as part of the 6th National CINI Conference on Artificial Intelligence (Ital-IA 2026). June 18, 2026, Rome, Italy.
Crowdsourced Keypoint Matching for Region of Interest Identification in Cross-Stain Whole Slide Image Registration
Poster - 22nd European Congress on Digital Pathology (ECDP 2026). June 18, 2026, Graz, Austria.
alessio-fiorin
Beyond Seeing Is Believing: On Crowdsourced Detection of Audiovisual Deepfakes
Deepfakes are increasingly realistic and easy to produce, raising concerns about the reliability of human judgments in misinformation settings. We study audiovisual deepfake …
Beyond Seeing Is Believing: On Crowdsourced Detection of Audiovisual Deepfakes
Workshop Talk - The 6th Workshop on Reducing Online Misinformation through Credible Information Retrieval (ROMCIR 2026), held as part of The 48th European Conference on Information …
Large Language Models as Assessors: On the Impact of Relevance Scales
Poster - The 48th European Conference on Information Retrieval (ECIR 2026). Delft, The Netherlands.
riccardo-zamolo
Analyzing AI Evaluation Benchmarks Through Information Retrieval and Network Science
Poster - The 48th European Conference on Information Retrieval (ECIR 2026). Delft, The Netherlands.
gaia-simeoni
Large Language Models as Assessors: On the Impact of Relevance Scales
Traditionally, relevance judgments have relied on human annotators, but recent advances in Large Language Models (LLMs) have prompted growing interest in their use as a proxy for …
riccardo-zamolo
Analyzing AI Evaluation Benchmarks Through Information Retrieval and Network Science
Many analyses have been performed on Information Retrieval (IR) evaluation benchmarks. Benchmarking also plays a central role in evaluating the capabilities of Large Language …
gaia-simeoni
Large Language Models for Combinatorial Optimization: A Systematic Review
This systematic review explores the application of Large Language Models (LLMs) in Combinatorial Optimization (CO). We report our findings using the Preferred Reporting Items for …
francesca-da-ros