7th Annual Likert Symposium – Generating and Classifying Text: Challenges and Benefits of Using Language Models in Social Research
When:
Friday, March 14, 2025
10:00 am – 1:00 pm (EST)
Registration is required. The symposium is free. Zoom information will be sent after registration.
Speakers
Welcome: Fred Conrad, University of Michigan, Survey Research Center
Trent Buskirk, Old Dominion University, School of Data Science
LLMs are Large, but should they be in Charge? Exploring the Possibility and Implausibility of Large Language Models in Survey Science
Haomiao Jin, University of Surrey, School of Health Sciences
Exploring an AI-Powered Survey Interviewing Agent for Individuals Who Are Blind or Severely Visually Impaired
Joelle Abramowitz, University of Michigan, Institute for Social Research
Using Artificial Intelligence to Improve the Panel Study of Income Dynamics and Health and Retirement Study
James Bisbee, Vanderbilt University, Data Science Institute
“What To Do When Your Language Model is Not State of the Art: When (not) to Worry About Misclassification and How to Correct for It in Social Science Applications”
Bios & Abstracts (PDF) | Agenda (PDF)