Recording available: how generative AI could improve survey measurement

On 15 September 2026, Professor Patrick Sturgis of the London School of Economics and Political Science (LSE) presented a survey methods webinar on the use of generative AI in surveys, as part of the European Social Survey (ESS) seminar series. The recording is now available on the ESS YouTube channel.

Large language models have the potential to transform many aspects of survey research, but their greatest contribution may be in improving measurement rather than replacing existing methods. The seminar presented findings from the Economic and Social Research Council (ESRC)-funded Survey Futures project “Integrating Generative AI in Question Design Evaluation and Testing”.

The presentation focused on two applications. In the first, large language models simulate cognitive interviewing and expert review in order to identify flaws in draft survey questions. In the second, they assign Standard Occupational Classification (SOC2020) codes from respondents’ descriptions of their jobs. Professor Sturgis presented the evidence on the accuracy, strengths and limitations of these approaches, compared them with conventional methods, and considered the opportunities and challenges of integrating generative AI into the survey lifecycle.

Patrick Sturgis is Professor of Quantitative Social Science at the LSE and Head of its Department of Methodology. His research focuses on survey methodology, social measurement and the application of new technologies to social research. He is a Fellow of the British Academy and of the Academy of Social Sciences.

The recording will be of interest to researchers, doctoral candidates and students who work with survey data or are curious about the role of AI in social science methodology.

Recording: ESS YouTube channel