Publications

You can also find my articles on my Google Scholar profile.

Papers

Toxic Bias: Perspective API Misreads German as More Toxic

Published in Proceedings of the International AAAI Conference on Web and Social Media, 19, pp. 1346–1357, 2025

This paper exposes a language bias in Google’s Perspective API, revealing that German text is systematically rated as more toxic than other languages. The findings raise concerns about the use of proprietary APIs for content moderation and social science research.

Recommended citation: Gianluca Nogara, Francesco Pierri, Stefano Cresci, Luca Luceri, Petter Törnberg, Silvia Giordano. (2025). "Toxic Bias: Perspective API Misreads German as More Toxic." Proceedings of the International AAAI Conference on Web and Social Media, 19, pp. 1346–1357.
Download Paper

A Longitudinal Analysis of Misinformation, Polarization and Toxicity on Bluesky after Its Public Launch

Published in arXiv preprint arXiv:2505.02317, 2025

This paper presents a longitudinal analysis of Bluesky’s growth and dynamics after its public launch in February 2024, focusing on misinformation, polarization, and toxicity. It highlights platform trends, political leanings, and moderation challenges.

Recommended citation: Gianluca Nogara, Erfan Samieyan Sahneh, Matthew R DeVerna, Nick Liu, Luca Luceri, Filippo Menczer, Francesco Pierri, Silvia Giordano. (2025). "A Longitudinal Analysis of Misinformation, Polarization and Toxicity on Bluesky after Its Public Launch." arXiv preprint arXiv:2505.02317.
Download Paper

Delayed Takedown of Illegal Content on Social Media Makes Moderation Ineffective

Published in arXiv e-prints arXiv:2502.08841, 2025

This paper analyzes how delays in the removal of illegal content affect moderation efficacy on social media. Using empirical data and simulations, it demonstrates that timely takedowns drastically reduce exposure and reach, while delays diminish moderation impact.

Recommended citation: Bao Tran Truong, Sangyeon Kim, Gianluca Nogara, Enrico Verdolotti, Erfan Samieyan Sahneh, Florian Saurwein, Natascha Just, Luca Luceri, Silvia Giordano, Filippo Menczer. (2025). "Delayed Takedown of Illegal Content on Social Media Makes Moderation Ineffective." arXiv e-prints arXiv:2502.08841.
Download Paper

The Dawn of Decentralized Social Media: An Exploration of Bluesky’s Public Opening

Published in International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 422–437, 2024

This paper presents a longitudinal analysis of Bluesky—a decentralized social media platform—around its public launch in February 2024. It investigates shifts in user behavior, content dynamics, language trends, and the emergence of suspicious accounts.

Recommended citation: Erfan Samieyan Sahneh, Gianluca Nogara, Matthew R DeVerna, Nick Liu, Luca Luceri, Filippo Menczer, Francesco Pierri, Silvia Giordano. (2024). "The Dawn of Decentralized Social Media: An Exploration of Bluesky’s Public Opening." International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 422–437.
Download Paper

Tracking Fringe and Coordinated Activity on Twitter Leading up to the US Capitol Attack

Published in Proceedings of the International AAAI Conference on Web and Social Media, 18, pp. 1557–1570, 2024

This study investigates the spread of conspiracy theories and coordinated fringe activity on Twitter in the months before the January 6th Capitol attack. It highlights adversarial techniques like targeted amplification and manufactured consensus, linking online narratives to offline violence.

Recommended citation: Padinjaredath Suresh Vishnuprasad, Gianluca Nogara, Felipe Cardoso, Stefano Cresci, Silvia Giordano, Luca Luceri. (2024). "Tracking Fringe and Coordinated Activity on Twitter Leading up to the US Capitol Attack." Proceedings of the International AAAI Conference on Web and Social Media, 18, pp. 1557–1570.
Download Paper

Misinformation and Polarization around COVID-19 Vaccines in France, Germany, and Italy

Published in Proceedings of the 16th ACM Web Science Conference, pp. 119–128, 2024

This study investigates vaccine-related misinformation and polarization on Twitter in Italy, Germany, and France. It analyzes structural patterns of discussion, revealing country-specific dynamics of pro- and anti-vaccine factions and the role of alternative platforms like Telegram and YouTube.

Recommended citation: Gianluca Nogara, Francesco Pierri, Stefano Cresci, Luca Luceri, Silvia Giordano. (2024). "Misinformation and Polarization around COVID-19 Vaccines in France, Germany, and Italy." Proceedings of the 16th ACM Web Science Conference, pp. 119–128.
Download Paper

Exposing Influence Campaigns in the Age of LLMs: A Behavioral-Based AI Approach to Detecting State-Sponsored Trolls

Published in EPJ Data Science, 12(1):46, 2023

We propose a novel AI-based method to detect state-sponsored troll accounts on social media using only behavioral activity patterns—without analyzing the content they share. The approach introduces the Troll Score to quantify troll-like behavior.

Recommended citation: Fatima Ezzeddine, Omran Ayoub, Silvia Giordano, Gianluca Nogara, Ihab Sbeity, Emilio Ferrara, Luca Luceri. (2023). "Exposing Influence Campaigns in the Age of LLMs: A Behavioral-Based AI Approach to Detecting State-Sponsored Trolls." EPJ Data Science, 12(1):46.
Download Paper

Not My Fault: Studying the Necessity of the User Classification & Employment of Fine-Level User-Based Moderation Interventions in Social Networks

Published in International Conference on Complex Networks and Their Applications, pp. 354–365, Springer Nature Switzerland, 2023

This study classifies users based on behavioral groups to enable fine-grained, user-based moderation interventions on social media, aiming to protect communities while respecting user diversity in reactions to content and platform actions.

Recommended citation: Sara Nasirian, Gianluca Nogara, Silvia Giordano. (2023). "Not My Fault: Studying the Necessity of the User Classification & Employment of Fine-Level User-Based Moderation Interventions in Social Networks." International Conference on Complex Networks and Their Applications, pp. 354–365, Springer Nature Switzerland.
Download Paper

User’s Reaction Patterns in Online Social Network Communities

Published in arXiv preprint arXiv:2309.03701, 2023

This paper investigates how users in online social network communities react to specific events, revealing that certain triggers can invert community behavior dynamics. The study highlights the importance of user-centered intervention strategies to improve platform health.

Recommended citation: Azza Bouleimen, Nicolò Pagan, Stefano Cresci, Aleksandra Urman, Gianluca Nogara, Silvia Giordano. (2023). "User's Reaction Patterns in Online Social Network Communities." arXiv preprint arXiv:2309.03701.
Download Paper

The Disinformation Dozen: An Exploratory Analysis of COVID-19 Disinformation Proliferation on Twitter

Published in Proceedings of the 14th ACM Web Science Conference 2022, pp. 348–358, 2022

An exploratory analysis on the Twitter activity of the so-called Disinformation Dozen (Disinfo12), responsible for a major share of COVID-19 misinformation. The study investigates their sharing strategies, favorite information sources, and supporting actors.

Recommended citation: Gianluca Nogara, Padinjaredath Suresh Vishnuprasad, Felipe Cardoso, Omran Ayoub, Silvia Giordano, Luca Luceri. (2022). "The Disinformation Dozen: An Exploratory Analysis of COVID-19 Disinformation Proliferation on Twitter." Proceedings of the 14th ACM Web Science Conference, pp. 348–358.
Download Paper