Filippo Menczer
Indiana University, IN·Computer Science
Content spreads across social media through networks of people. Along the way, misleading signals can warp how people see the world.
- Fields
Computer Science
Social Science
Mathematics & Statistics
- Topics
agent-based modeling
information diffusion
social networks
- Grants
- 2 known grants, through May 2028
What they work on
- Build an agent-based simulation of how content spreads through human social networks, modeling individual traits and network structure to predict large-scale information flow.
- Use the simulation infrastructure to evaluate how well different interventions improve the information ecosystem, while balancing accuracy, scalability and robustness.
- Identify social media polls that misrepresent public opinion by inferring the demographics of the users who engage with them, and measure how common such polls are and how they are used.
- Develop a bias-correction algorithm for social polls using regression and post-stratification based on inferred user attributes, and test with survey experiments how biased versus corrected results shift perceived public opinion.
More about the research
This research uses computer models and data analysis to study two such problems. One project builds simulations of how information moves through human networks and tests which interventions might improve the information ecosystem. The other project examines informal opinion polls on social media and the distorted picture of public opinion they can create.
Why it matters
Biased social media polls can mislead people about what the public actually believes. Unchecked information dynamics can also distort how content spreads online. Tools that detect and correct poll bias, together with simulations that predict the effects of interventions, could help platforms, researchers and the public keep a more accurate picture of public opinion.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Kenneth Joseph
University at Buffalo, NY·Computer Science·Early-career
Develop mixed methods combining graph-based and natural-language machine learning with qualitative analysis to identify dominant beliefs about social issues in large datasets from X and Parler.
Ted Hsuan Yun Chen
George Mason University, VA·Social Science
Develop a survey-based measurement approach and conceptual framework for belief networks, capturing how attitudes on climate, migration and social fairness influence one another within individuals.
Jaideep Srivastava
University of Minnesota, MN·Computer Science
Investigate how information spreads through online social networks and develop tools that trace content back to its original sources and identify authentic information.
The school
Indiana University: 21 labs on PI Pages, $897M a year on research, 438 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.