WAPOR Webinar in February 2025:

Using NLP and Generative AI in Survey Research

Dear WAPOR Members, Subscribers, and Friends,

We are delighted to invite you to our next webinar, “Using NLP and Generative AI in Survey Research”, taking place today on Wednesday, February 26, 2025. This session will provide insights into the opportunities and challenges of integrating AI-driven methods into public opinion research.

The webinar will feature Joshua Y. Lerner and Soubhik Barari from NORC at the University of Chicago, with Alice Siu, Chair of the WAPOR Education Committee, as the moderator. They will discuss the fundamentals of NLP and Generative AI, exploring how these technologies are used in survey research to analyze open-ended responses, enhance dynamic survey probing, enable conversational interviewing, and improve tailored experiments and missing value imputation. The session will also address limitations and challenges, including the complexities of synthetic respondents, the feasibility of AI-generated survey questions, the potential for public opinion prediction, and the implications for cross-cultural research.

By attending this webinar, participants will gain a deeper understanding of how AI can be effectively applied in survey research while also considering its risks and limitations. The session is designed for researchers, practitioners, and anyone interested in the evolving role of AI in data collection and analysis.

Register to Attend!

Our speakers are:

Soubhik Barari is a research methodologist at NORC at the University of Chicago, specializing in statistical and computational methods for social science research. With over seven years of experience, he applies machine learning, generative AI, causal inference, and natural language processing to areas such as social media analysis, government program evaluation, and pre-election polling. At NORC, he leads key quantitative projects, including survey weighting for the National Center for Health Statistics’ Rapid Survey System and Pew Research Center’s Religious Landscape Study III, as well as data visualization tools for survey quality control and political polling. He has also evaluated mode effects in surveys and generative AI for interviews. Previously, Soubhik was a research scientist at SurveyMonkey and has held roles at Microsoft Research, Harvard, and MIT. His work has been published in Nature Scientific Data and featured in The Atlantic and Scientific American, and is often present at academic and industry conferences, including AAPOR.

Joshua Lerner is a research methodologist at NORC specializing in AI, NLP, machine learning, and causal inference for program evaluation. Since joining in 2021, he has led initiatives integrating NLP into survey research, including automated transcript analysis for the America in One Room deliberative poll and designing models to assess the long-term effects of deliberation on voting and polarization. He has also developed econometric models for large-scale evaluations, such as ACO REACH and SAPRO, and introduced innovations in difference-in-difference modeling for healthcare research. A political scientist with publications in American Political Science Review and Journal of Politics, he has taught graduate courses on machine learning at Duke and led workshops at Northwestern. His research spans political ideology, institutional economics, and NLP applications in legislative analysis.