Stevens Researchers Use ML to Map Emerging Online Communities

Study examines how online communities form, evolve, and influence society

Mar. 27, 2026 at 1:06am

Got story updates? Submit your updates here. ›

Researchers at Stevens Institute of Technology used machine learning tools and social network theory to better understand how people interact and form communities online. The study focused on elucidating the complex patterns of relationships and shared interests that link people together across the internet, and how these online communities can create echo chambers, increase polarization, and spread misinformation.

Why it matters

Understanding how online communities work is important not only for scientists who study social interactions, but also for policymakers who make decisions about technology and society. By studying how these online communities form, grow, and interact, researchers may be able to identify early warning signs of harmful discourse and help policymakers develop strategies to reduce potential risks while still supporting the positive aspects of online communication.

The details

The researchers developed a framework that tracks digital communities over time and classifies the topics they discuss, allowing them to examine how conversations split into smaller subtopics and how these groups emerge and disappear. The framework leverages machine learning classification models to analyze user posts and interactions, revealing underlying group structures. The researchers also identified several key analytical elements based on social science theories to better understand the structure and dynamics of these online communities and how real-world events influence them.

  • The research team published their findings in the journal of Risk Analysis on March 26, 2026.

The players

Jose Ramirez-Marquez

Stevens Associate Professor at the Department of Systems Engineering who studies how communities evolve and interact.

Amirhossein Dezhboro

A PhD candidate who worked with Ramirez-Marquez on the research.

Stevens Institute of Technology

A premier, private research university situated in Hoboken, New Jersey that has been known for technological innovation since its founding in 1870.

Got photos? Submit your photos here. ›

What they’re saying

“A community in this study is not merely a collection of users tweeting about similar topics but an interactional cluster. In other words, it's a networked structure where users are thematically aligned and actively connected through retweets, mentions or replies.”

— Jose Ramirez-Marquez, Associate Professor, Department of Systems Engineering

“As a member of an online community, I can disguise myself, and then I can say all sorts of things without social repercussions. In real life there are consequences.”

— Jose Ramirez-Marquez, Associate Professor, Department of Systems Engineering

“We found that social media interactions can create echo chambers and increase societal polarization, while the framework can help detect emerging misinformation communities and track how narratives spread over time.”

— Jose Ramirez-Marquez, Associate Professor, Department of Systems Engineering

“By studying how these online communities form, grow and interact, we may be able to identify early warning signs of harmful discourse. And that may help policymakers develop strategies to reduce potential risks while still supporting the positive aspects of online communication.”

— Jose Ramirez-Marquez, Associate Professor, Department of Systems Engineering

What’s next

The researchers plan to continue studying how online communities evolve and influence society, with the goal of informing policymakers on strategies to address the risks while preserving the benefits of digital communication.

The takeaway

This research highlights the complex and evolving nature of online communities, which have transformed from geographically-bound groups to global networks shaped by shared interests and digital interactions. Understanding these dynamics is crucial for addressing the challenges posed by echo chambers, misinformation, and societal polarization in the digital age.