
SoDa Symposium: Prompt Engineering to Support AI Enabled Research
A webinar presentation and discussant followed by Q&A
presented on
Tuesday, April 1, 2025
12 pm – 1 pm (Online)
Abstract:
Generative AI tools are an increasingly integral part of the social science research process. AI tools can be used to support idea generation, data extraction, data analysis, literature review, coding, data visualization and scientific writing. Recent research highlights the importance of prompt engineering (i.e. writing the instructions used to interact with large language models) for effective use of AI in research. In this presentation I will describe recent literature in the field, including several research backed frameworks for prompt engineering, and present the results of a recent case study we conducted on optimizing AI prompts for use in systematic literature review.
Presenter:
Claire Kelley:
Senior Data Scientist and Co-Director of Data Science
Child Trends
Bio:
Claire Kelley is a senior data scientist and co-director for data science at Child Trends. Her work focuses on the applications of data science and AI techniques to social science problems: particularly those in the domains of education and health. Her current work includes use of AI to develop customized interactive tools, experiments with natural language processing approaches to qualitative data analysis and research on how AI impacts educators and students in k-12 classrooms.
Discussant:
Trent D. Buskirk
Professor and Provost Fellow Data Science
Old Dominion University
Bio:
Trent D. Buskirk, Ph.D. has recently joined the new School of Data Science at Old Dominion University as one of several founding faculty members. Prior to this appointment, Trent was the Novak Family Distinguished Professor of Data Science and outgoing Chair of the Applied Statistics and Operations Research Department at Bowling Green State University. Dr. Buskirk is a Fellow of the American Statistical Association and his research interests include big data quality, recruitment methods through social media, the use of big data and machine learning methods for health, social and survey science design and analysis, mobile and smartphone survey designs and in methods for calibrating and weighting non-probability samples and fairness in AI models and interpretable ML methods. When Trent is not geeking out over data science, big data or survey methodology, you can find him playing a competitive game of Pickleball!