Marco Minici
@marcominici.bsky.social
Researcher at ICAR-CNR
I develop computational tools to identify threats to online users posed by malicious actors and algorithms that behave unpredictably.
Personal Website: https://mminici.github.io
I develop computational tools to identify threats to online users posed by malicious actors and algorithms that behave unpredictably.
Personal Website: https://mminici.github.io
Pinned
Marco Minici
@marcominici.bsky.social
· Dec 23
"IOHunter: Graph Foundation Model to Uncover Online Information Operations" goes to AAAI'25!
This is the result of an incredible collaboration with @luceriluc.bsky.social @frafabbri.bsky.social and @emilioferrara.bsky.social
Read the entire thread for a summary and the link to the preprint.
This is the result of an incredible collaboration with @luceriluc.bsky.social @frafabbri.bsky.social and @emilioferrara.bsky.social
Read the entire thread for a summary and the link to the preprint.
Reposted by Marco Minici
📢 New paper! We study urban location recommenders and their feedback with human mobility. Simulating this loop reveals a paradox: people explore more individually, yet city visits and encounters concentrate. Cities coevolve with AI, and inequality can grow.
📄 link.springer.com/article/10.1...
📄 link.springer.com/article/10.1...
Client Challenge
link.springer.com
January 9, 2026 at 8:06 PM
📢 New paper! We study urban location recommenders and their feedback with human mobility. Simulating this loop reveals a paradox: people explore more individually, yet city visits and encounters concentrate. Cities coevolve with AI, and inequality can grow.
📄 link.springer.com/article/10.1...
📄 link.springer.com/article/10.1...
Reposted by Marco Minici
Our new article in @science.org enables social media reranking outside of platforms' walled gardens.
We add an LLM-powered reranking of highly polarizing political content into N=1256 participants' feeds. Downranking cools tensions with the opposite party—but upranking inflames them.
We add an LLM-powered reranking of highly polarizing political content into N=1256 participants' feeds. Downranking cools tensions with the opposite party—but upranking inflames them.
December 1, 2025 at 7:33 PM
Our new article in @science.org enables social media reranking outside of platforms' walled gardens.
We add an LLM-powered reranking of highly polarizing political content into N=1256 participants' feeds. Downranking cools tensions with the opposite party—but upranking inflames them.
We add an LLM-powered reranking of highly polarizing political content into N=1256 participants' feeds. Downranking cools tensions with the opposite party—but upranking inflames them.
Reposted by Marco Minici
New paper in Science:
In a platform-independent field experiment, we show that reranking content expressing antidemocratic attitudes and partisan animosity in social media feeds alters affective polarization.
🧵
In a platform-independent field experiment, we show that reranking content expressing antidemocratic attitudes and partisan animosity in social media feeds alters affective polarization.
🧵
December 1, 2025 at 7:59 AM
New paper in Science:
In a platform-independent field experiment, we show that reranking content expressing antidemocratic attitudes and partisan animosity in social media feeds alters affective polarization.
🧵
In a platform-independent field experiment, we show that reranking content expressing antidemocratic attitudes and partisan animosity in social media feeds alters affective polarization.
🧵
Reposted by Marco Minici
What does coordinated inauthentic behavior look like on TikTok?
We introduce a new framework for detecting coordination in video-first platforms, uncovering influence campaigns using synthetic voices, split-screen tactics, and cross-account duplication.
📄https://arxiv.org/abs/2505.10867
We introduce a new framework for detecting coordination in video-first platforms, uncovering influence campaigns using synthetic voices, split-screen tactics, and cross-account duplication.
📄https://arxiv.org/abs/2505.10867
May 19, 2025 at 3:42 PM
What does coordinated inauthentic behavior look like on TikTok?
We introduce a new framework for detecting coordination in video-first platforms, uncovering influence campaigns using synthetic voices, split-screen tactics, and cross-account duplication.
📄https://arxiv.org/abs/2505.10867
We introduce a new framework for detecting coordination in video-first platforms, uncovering influence campaigns using synthetic voices, split-screen tactics, and cross-account duplication.
📄https://arxiv.org/abs/2505.10867
Reposted by Marco Minici
We constantly ask our apps where to visit, eat or drink.
AI tells us, and most of the time, we follow it. The loop continues.
But do AIs favor certain places? How would we even know if we don’t own the platforms?
We modeled this complex phenomenon, and results are fascinating!
Spoiler: rich get…
AI tells us, and most of the time, we follow it. The loop continues.
But do AIs favor certain places? How would we even know if we don’t own the platforms?
We modeled this complex phenomenon, and results are fascinating!
Spoiler: rich get…
arxiv.org
April 11, 2025 at 9:01 AM
We constantly ask our apps where to visit, eat or drink.
AI tells us, and most of the time, we follow it. The loop continues.
But do AIs favor certain places? How would we even know if we don’t own the platforms?
We modeled this complex phenomenon, and results are fascinating!
Spoiler: rich get…
AI tells us, and most of the time, we follow it. The loop continues.
But do AIs favor certain places? How would we even know if we don’t own the platforms?
We modeled this complex phenomenon, and results are fascinating!
Spoiler: rich get…
Reposted by Marco Minici
IU's Observatory on Social Media defends citizens from online manipulation – the opposite of censorship
osome.iu.edu/research/blo...
osome.iu.edu/research/blo...
IU's Observatory on Social Media defends citizens from online manipulation – the opposite of censorship
When thousands of fake accounts controlled by an unknown actor flood social media with some story, and platform algorithms amplify these messages, real...
osome.iu.edu
March 4, 2025 at 12:46 AM
IU's Observatory on Social Media defends citizens from online manipulation – the opposite of censorship
osome.iu.edu/research/blo...
osome.iu.edu/research/blo...
Preprint is available on arXiv arxiv.org/abs/2412.14663
IOHunter: Graph Foundation Model to Uncover Online Information Operations
Social media platforms have become vital spaces for public discourse, serving as modern agorás where a wide range of voices influence societal narratives. However, their open nature also makes them vu...
arxiv.org
March 3, 2025 at 5:24 PM
Preprint is available on arXiv arxiv.org/abs/2412.14663
This work would not have been possible without the other amazing coauthors @luceriluc.bsky.social @frafabbri.bsky.social @emilioferrara.bsky.social
Bonus Pic: myself beyond excited to stand next to my poster!
Bonus Pic: myself beyond excited to stand next to my poster!
March 3, 2025 at 5:23 PM
This work would not have been possible without the other amazing coauthors @luceriluc.bsky.social @frafabbri.bsky.social @emilioferrara.bsky.social
Bonus Pic: myself beyond excited to stand next to my poster!
Bonus Pic: myself beyond excited to stand next to my poster!
Our work provides a scalable approach for online moderation teams, public institutions, and independent organizations to audit the health of online environments—especially crucial during political events such as election cycles.
March 3, 2025 at 5:23 PM
Our work provides a scalable approach for online moderation teams, public institutions, and independent organizations to audit the health of online environments—especially crucial during political events such as election cycles.
2. We explore how our multimodal framework exhibits foundation model behavior in detecting online information operations. Our results show that pretraining IOHunter on past IO datasets enables it to generalize to new, emerging IOs with only a few labeled examples for fine-tuning.
March 3, 2025 at 5:23 PM
2. We explore how our multimodal framework exhibits foundation model behavior in detecting online information operations. Our results show that pretraining IOHunter on past IO datasets enables it to generalize to new, emerging IOs with only a few labeled examples for fine-tuning.
Key takeaways:
1. We propose a multimodal framework that effectively integrates textual and graph information using a cross-attention mechanism, which is then processed by a GNN.
1. We propose a multimodal framework that effectively integrates textual and graph information using a cross-attention mechanism, which is then processed by a GNN.
March 3, 2025 at 5:23 PM
Key takeaways:
1. We propose a multimodal framework that effectively integrates textual and graph information using a cross-attention mechanism, which is then processed by a GNN.
1. We propose a multimodal framework that effectively integrates textual and graph information using a cross-attention mechanism, which is then processed by a GNN.
Reposted by Marco Minici
The three horsemen of social media: brain rot, anxiety and foreign interference
voxeurop.eu/en/social-me...
voxeurop.eu/en/social-me...
The three horsemen of social media: brain rot, anxiety and foreign interference
With so many media institutions bidding farewell to X, it's a good time to reflect on the relationship status of social media and European society at large.
voxeurop.eu
December 26, 2024 at 7:31 PM
The three horsemen of social media: brain rot, anxiety and foreign interference
voxeurop.eu/en/social-me...
voxeurop.eu/en/social-me...
Read our preprint available on arXiv at: arxiv.org/abs/2412.14663
IOHunter: Graph Foundation Model to Uncover Online Information Operations
Social media platforms have become vital spaces for public discourse, serving as modern agorás where a wide range of voices influence societal narratives. However, their open nature also makes them vu...
arxiv.org
December 23, 2024 at 2:02 PM
Read our preprint available on arXiv at: arxiv.org/abs/2412.14663
Our effort highlights the critical role of multi-modality in modeling malicious user behavior, the value of attention to weight the modalities, and how we can advance toward a GFM for the IO Detection task by pre-training our architecture on a dataset of previous IOs.
December 23, 2024 at 2:02 PM
Our effort highlights the critical role of multi-modality in modeling malicious user behavior, the value of attention to weight the modalities, and how we can advance toward a GFM for the IO Detection task by pre-training our architecture on a dataset of previous IOs.
Our work demonstrates how a multi-modal framework based on GNN+LM and massive pre-training produces a model that effectively generalizes to IOs not present in the original training dataset — the most realistic scenario for IO detection.
December 23, 2024 at 2:02 PM
Our work demonstrates how a multi-modal framework based on GNN+LM and massive pre-training produces a model that effectively generalizes to IOs not present in the original training dataset — the most realistic scenario for IO detection.
Our model delivers substantial improvements over current IO detection methods across three learning tasks:
1️⃣ Supervised IO Detection
2️⃣ Scarcely-Labeled Supervised IO Detection
3️⃣ Cross-IO Detection (with minimal or no labeled data from emerging IOs)
1️⃣ Supervised IO Detection
2️⃣ Scarcely-Labeled Supervised IO Detection
3️⃣ Cross-IO Detection (with minimal or no labeled data from emerging IOs)
December 23, 2024 at 2:02 PM
Our model delivers substantial improvements over current IO detection methods across three learning tasks:
1️⃣ Supervised IO Detection
2️⃣ Scarcely-Labeled Supervised IO Detection
3️⃣ Cross-IO Detection (with minimal or no labeled data from emerging IOs)
1️⃣ Supervised IO Detection
2️⃣ Scarcely-Labeled Supervised IO Detection
3️⃣ Cross-IO Detection (with minimal or no labeled data from emerging IOs)
Maintaining the integrity of online discourse is essential for safeguarding fair democratic processes.
Our multi-modal learning framework IOHunter integrates both content and contextual information to identify actors attempting to manipulate online discussions - i.e., IO Drivers
Our multi-modal learning framework IOHunter integrates both content and contextual information to identify actors attempting to manipulate online discussions - i.e., IO Drivers
December 23, 2024 at 2:02 PM
Maintaining the integrity of online discourse is essential for safeguarding fair democratic processes.
Our multi-modal learning framework IOHunter integrates both content and contextual information to identify actors attempting to manipulate online discussions - i.e., IO Drivers
Our multi-modal learning framework IOHunter integrates both content and contextual information to identify actors attempting to manipulate online discussions - i.e., IO Drivers
"IOHunter: Graph Foundation Model to Uncover Online Information Operations" goes to AAAI'25!
This is the result of an incredible collaboration with @luceriluc.bsky.social @frafabbri.bsky.social and @emilioferrara.bsky.social
Read the entire thread for a summary and the link to the preprint.
This is the result of an incredible collaboration with @luceriluc.bsky.social @frafabbri.bsky.social and @emilioferrara.bsky.social
Read the entire thread for a summary and the link to the preprint.
December 23, 2024 at 2:02 PM
"IOHunter: Graph Foundation Model to Uncover Online Information Operations" goes to AAAI'25!
This is the result of an incredible collaboration with @luceriluc.bsky.social @frafabbri.bsky.social and @emilioferrara.bsky.social
Read the entire thread for a summary and the link to the preprint.
This is the result of an incredible collaboration with @luceriluc.bsky.social @frafabbri.bsky.social and @emilioferrara.bsky.social
Read the entire thread for a summary and the link to the preprint.
Reposted by Marco Minici
New evidence of cross-platform foreign interference on social media during the 2024 U.S. Election that drove the spread of highly-partisan, low-credibility, and conspiratorial content, from Cinus, Minici, @luceriluc.bsky.social @emilioferrara.bsky.social arxiv.org/pdf/2410.22716
December 8, 2024 at 8:43 PM
New evidence of cross-platform foreign interference on social media during the 2024 U.S. Election that drove the spread of highly-partisan, low-credibility, and conspiratorial content, from Cinus, Minici, @luceriluc.bsky.social @emilioferrara.bsky.social arxiv.org/pdf/2410.22716