Computational Social Science
Lab at Penn

CSS unites computer science, statistics, and social science to solve challenging real-world problems using digital data and platforms. Through mass collaboration with industry, government, and civil society, our research generates insights that advance basic science in the service of practical applications.

Introduction to CSS Lab

Computational Social Science Lab at Penn

CSS unites computer science, statistics, and social science to solve challenging real-world problems using novel theories. Through our mass collaboration with industry, government, and civil society, our path-breaking research generates solutions which are both innovative and practical.

News

When Do Teams Outperform Individuals?

New Wharton research suggests decades of conflicting evidence can be explained by one overlooked factor: the task itself.

Mack Institute and CSS Lab Team Up On Media Bias Detection

This spring, a student team from the Mack Institute for Innovation Management collaborated with Penn’s Computational Social Science (CSS) Lab to explore how to bring the lab’s latest innovation, an AI-powered media bias detection tool, to market. The student team is...

How cable news has diverged from broadcast news

Walter Cronkite was often cited as “the most trusted man in America” as he delivered the news on CBS in the 1960s and ’70s—a time when fewer news options created a “shared reality” that scholars argue fostered civic engagement, empathy, and shared national identity. The situation looks quite different in today’s disparate media landscape.

Duncan Watts Presents Fake News, Echo Chambers, and Algorithms at Penn Engineering ASSET Seminar

Computational Social Science Lab (CSSLab) Director Duncan Watts presented: “Fake News, Echo Chambers, and Algorithms: A Data Science Perspective” at an ASSET(AI-enabled Systems: Safety, Explainability and Trustworthiness) Weekly Seminar on April 23, 2025.

Researcher Spotlight: CSSLab Members Present Work at Annenberg Workshop 

Annenberg PhD student Neil Fasching and Postdoctoral researcher Jennifer Allen of the Computational Social Science Lab (CSSLab) recently presented their research on April 15th at the 2nd annual Center for Information Network Democracy Workshop: The Impact of AI on (Mis)Information. CIND is an initiative led by Annenberg faculty members Sandra González-Bailón and Yphtach Lelkes, focused on the impact of information ecosystems on democratic participation in the digital age.

Can Social Media Be Less Toxic?

In an era where online interactions can be both motivational and toxic, researchers from the Computational Social Science Lab (CSSLab) at the University of Pennsylvania are interested in what encourages prosocial behavior — acts of kindness, support, and cooperation — on social media.

News On Climate Change Is More Persuasive Than Expected, Study Finds

Climate change is one of the most pressing challenges of our time, demanding urgent and effective action to mitigate its severe impacts. One barrier to effective climate change action is its polarizing nature largely driven by the media, as people prefer to consume news that aligns with their political beliefs. This tendency is especially strong among climate skeptics, who are more inclined to seek information that reinforces their views on climate change. In this context, communication—especially on social media—plays a crucial role in bridging cross-partisan boundaries. However, meaningful dialogue may be hampered if individuals do not believe these interactions will be effective.

From Cracks to Gardens: Creating a Thriving Social Media Through Research 

Early advocates of social media believed that the creation of these platforms would lead to positive outcomes. When Facebook was launched in 2004, it was praised for its ability to “connect the entire world.” In hindsight, many of these ideals were optimistic at their time as social media platforms are often criticized for spreading hate and misinformation.

New Study Challenges YouTube’s Rabbit Hole Effect on Political Polarization

With 2.1 billion monthly users, YouTube is a major media platform that has become an important component of many Americans’ news diets. Simultaneously, it has garnered a reputation for stoking the flames of political extremism, making it a focal point among researchers studying video-stream platforms and their intersection with political polarization. The mainstream media has also taken interest in extremism on YouTube—New York Times writer and Princeton professor Zeynep Tufekci has argued that YouTube’s recommendation algorithm radicalizes its users by exposing them to increasingly polarizing content.

How the Media Distorts Perceptions on Chronic Disease Risks

Silent illnesses, or chronic diseases, contribute to 70% of deaths in the US annually and six in ten Americans suffer from at least one chronic condition. Despite this, coverage of this public health crisis is disproportionately overshadowed by sensational risks, including terrorism, homicide, and traffic accidents- incidents that are far more likely to grab readers’ attention.

How cable news has diverged from broadcast news
How cable news has diverged from broadcast news

Walter Cronkite was often cited as “the most trusted man in America” as he delivered the news on CBS in the 1960s and ’70s—a time when fewer news options created a “shared reality” that scholars argue fostered civic engagement, empathy, and shared national identity. The situation looks quite different in today’s disparate media landscape.

Over the past 100 years, social science has generated a tremendous number of theories on the topics of individual and collective human behaviour. However, it has been much less successful at reconciling the innumerable inconsistencies and contradictions among these competing explanations.

Duncan Watts
CSSLab Founder

Over the past 100 years, social science has generated a tremendous number of theories on the topics of individual and collective human behaviour. However, it has been much less successful at reconciling the innumerable inconsistencies and contradictions among these competing explanations.

Duncan Watts
CSS Lab Founder

Researchers & Staff

Meet the CSSLab