AI Social Simulation: LLM Agents in a Virtual World
Classic social psychology experiments are too ethically fraught to rerun on people. What happens when the participants are LLM agents?
am Carey Okal, a master's student in Information Science at Cornell University (B.S. May 2026). My research interests are in computational social science: simulating social behavior with LLM agents, persuasion and misinformation in political news, and data science for humanitarian response. This site is a window into my work.
Selected research
-
-
Persuasive AI and the Spread of Misinformation and Disinformation Online
I built the roughly 2-million-article corpus of U.S. news articles (14 outlets, 2000–2025) the lab used to study how persuasive strategies vary with outlet credibility and ideology, collecting articles via sitemap crawling and archival scraping, then deduplicating and standardizing them into a unified schema.
-
Data Science to Build Resilience and Improve Humanitarian Response
The Data Science to Build Resilience and Improve Humanitarian Response Thought Summit, held at Cornell in May 2026, convened researchers and humanitarian leaders from institutions including the World Bank, the World Food Programme, UNHCR, IFPRI, NASA JPL, and Kenya's National Drought Management Authority.
-
Sustainable Ecotourism Commerce Platform
Community conservancies in East Africa do conservation-critical work, then compete for visibility against international booking platforms that take big cuts.
Teaching
-
SP 26
Course Assistant
Practical Tools for Operations Research, Machine Learning & Data Science
I supported instruction for ORIE 3120, a large undergraduate applied data science course in Cornell Engineering. Each week I led recitation sections covering SQL, Python, Tableau, regression, classification, time-series forecasting, and the design and analysis of A/B tests. Outside of section, I held office hours, graded homework and project milestones, and monitored Ed Discussion so students got timely help between classes.
- SQL
- Python
- Tableau
- Regression
- Classification
- Time series
- A/B testing
-
FA 24
Teaching Assistant
Introduction to Data Science
I taught weekly lab sections for INFO 2950, an introductory data science course with roughly 300 students per semester. Most of my time in lab went toward Python, statistical analysis, and helping students build the confidence to debug their own work when something broke. I held office hours, responded to Ed Discussion posts within a day, and met weekly with the professor to relay student feedback and refine the course. I received perfect TA evaluations three consecutive semesters.
- Python
- Regression
- Hypothesis testing
- Data visualization
-
SP 25, FA 25, FA 24
Teaching Assistant
Introduction to Web Development
I taught weekly lab sections for INFO 1300, an introductory web design and programming course, alongside my INFO 2950 assignment, together covering about 300 students per semester across data science and web development. In lab, students designed and shipped their first accessible websites, working from markup and layout through basic UX decisions. I also held office hours, graded exams and projects, and answered questions on Ed Discussion throughout the week.
- HTML
- CSS
- JavaScript
- UX design
- Accessibility