The Application and Evaluation of Large Language Models in Survey Research

Описание: The Application and Evaluation of Large Language Models in Survey Research

SurveyMonkey is a leading online survey platform that enables organizations to design, distribute, and analyze surveys. This talk explores how large language models (LLMs) are applied at SurveyMonkey to improve survey research, from enhancing question design to analyzing responses. Dr. Peng Jiang will demonstrate how LLMs help collect higher-quality data and how to evaluate survey quality while ensuring system security. Her paper Impact of a Deployed LLM Survey Creation Tool through the IS Success Model, written with her team at SurveyMonkey, has been accepted at the The International Conference on Information Systems (ICIS), and can be read here, where the topics discussed at our Webinar are outlined.

Our speaker for this webinar is Peng Jiang, Senior Manager of Produce Data Science Team at SurveyMonkey. She has been a Machine Learning leader at SurveyMonkey for over five years, and earned her Ph.D. in Computer Science with a focus on AI at the University of Illinois at Urbana-Champaign. With deep experience in both survey methodology and AI, she is passionate about leveraging her cross-functional expertise to amplify individual voices to produce insights that support informed decision-making.