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.

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

Research Assistant Spotlight: Priya D’Costa Presents at NeurIPS
Research Assistant Spotlight: Priya D’Costa Presents at NeurIPS

This past weekend CSSLab alumna Priya DCosta presented a poster titled What do you say or how do you say it? at NeurIPS 2024 Behavioral ML Workshop, a first-time workshop on exploring the incorporation of insights from the behavioral sciences into AI models/systems in Vancouver on December 10-15. In this RA spotlight, Priya shares more on her background and research leading up to NeurIPS.

Grumpy Voters Want Better Stories. Not Statistics
Grumpy Voters Want Better Stories. Not Statistics

In the final count, Trump collected 312 electoral votes to 226 for Democratic nominee Kamala Harris. While some votes are still being counted, the broad trends that won the election for Trump are also coming into focus. Echoing public opinion scholars, Duncan Watts of the University of Pennsylvania’s Annenberg School for Communication, author of Everything Is Obvious Once You Know the Answer, believes that Trump benefited from a broad anti-incumbent trend seen in elections worldwide; that sentiment swung enough undecided voters to his tally to win him the swing states needed for victory.

Commonsensicality: A New Platform to Measure Your Common Sense
Commonsensicality: A New Platform to Measure Your Common Sense

Most of us believe that we possess common sense; however, we find it challenging to articulate which of our beliefs are commonsensical or how “common” we think they are. Now, the CSSLab invites participants to measure their own level of common sense by taking a survey on a new platform, The common sense project.
Since its launch, the project has received significant media attention; it was recently featured in The Independent, The Guardian, and New Scientist, attracting over 100,000 visitors to the platform just this past week.

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