Michael Soprano

Michael Soprano

Postdoctoral 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 download my Curriculum Vitae in English or Italian. You can also explore my PhD thesis, together with my Master’s, Bachelor’s, and High School theses.

AIDME: A Scalable, Interpretable Framework for AI-Aided Scoping Reviews

Scientific publishing is expanding rapidly across disciplines, making it increasingly difficult for researchers to organize, filter, and synthesize the literature. Systematic …

avatar
Michael Soprano
The Magnitude of Truth: On Using Magnitude Estimation for Truthfulness Assessment featured image

The Magnitude of Truth: On Using Magnitude Estimation for Truthfulness Assessment

Conference Talk - The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. Padua, Italy.

avatar
Michael Soprano

The Magnitude of Truth: On Using Magnitude Estimation for Truthfulness Assessment

Evaluating the truthfulness of online content is critical for combating misinformation. This study examines the efficiency and effectiveness of crowdsourced truthfulness …

avatar
Michael Soprano

PILs of Knowledge: A Synthetic Benchmark for Evaluating Question Answering Systems in Healthcare

Patient Information Leaflets (PILs) provide essential information about medication usage, side effects, precautions, and interactions, making them a valuable resource for Question …

riccardo-lunardi

Efficiency and Effectiveness of LLM-Based Summarization of Evidence in Crowdsourced Fact-Checking

Assessing the truthfulness of information is a critical task in fact-checking, and is typically performed using binary or coarse ordinal scales (2-6 levels), though fine-grained …

kevin-roitero
AIDME: A Scalable, Interpretable Framework for AI-Aided Scoping Reviews featured image

AIDME: A Scalable, Interpretable Framework for AI-Aided Scoping Reviews

Workshop Talk - Workshop “AI, Misinformation and Disinformation”, held as part of the 5th National CINI Conference on Artificial Intelligence (Ital-IA 2025). June 23, 2025, …

avatar
Michael Soprano

In Crowd Veritas: Leveraging Human Intelligence To Fight Misinformation

The spread of online misinformation poses serious threats to democratic societies. Traditionally, expert fact-checkers verify the truthfulness of information through investigative …

avatar
Michael Soprano

Agent-Based Healthcare Chatbots for Regional System Services: A Case Study in the Friuli-Venezia Giulia Region

The scholarly publishing process relies on peer review to uphold the quality of scientific knowledge. However, challenges such as increasing submission volumes and potential …

riccardo-lunardi

Search Trajectory Networks Applied to a Real-World Parallel Batch Scheduling Problem

We investigate solution methods for the Oven Scheduling Problem (OSP), a parallel batch scheduling optimization problem in semiconductor manufacturing, using Search Trajectory …

francesca-da-ros

Evaluation of Crowdsourced Peer Review using Synthetic Data and Simulations

The scholarly publishing process relies on peer review to uphold the quality of scientific knowledge. However, challenges such as increasing submission volumes and potential …

avatar
Michael Soprano