Guided Persona-based AI Surveys: Can we replicate personal mobility preferences at scale using LLMs?
Ioannis Tzachristas, Santhanakrishnan Narayanan, Constantinos Antoniou
TL;DR
The paper tackles the problem of scalable, privacy-preserving data generation for mobility preferences by leveraging LLMs to create artificial surveys. It introduces guided Persona-based AI surveys and compares them against five other synthetic approaches using the MiD 2017 mobility dataset as a benchmark. The Guided Persona-based AI Survey achieves near-perfect alignment with real data, evidenced by MAE $0.03$, RMSE $0.17$, and JS distance $0.0016$, by encoding demographic–response dependencies through population weights $\pi_P$ and conditional probabilities. The results demonstrate the method's potential to support transportation planning and social science research, with future work exploring hybrids, efficiency gains, and broader applications.
Abstract
This study explores the potential of Large Language Models (LLMs) to generate artificial surveys, with a focus on personal mobility preferences in Germany. By leveraging LLMs for synthetic data creation, we aim to address the limitations of traditional survey methods, such as high costs, inefficiency and scalability challenges. A novel approach incorporating "Personas" - combinations of demographic and behavioural attributes - is introduced and compared to five other synthetic survey methods, which vary in their use of real-world data and methodological complexity. The MiD 2017 dataset, a comprehensive mobility survey in Germany, serves as a benchmark to assess the alignment of synthetic data with real-world patterns. The results demonstrate that LLMs can effectively capture complex dependencies between demographic attributes and preferences while offering flexibility to explore hypothetical scenarios. This approach presents valuable opportunities for transportation planning and social science research, enabling scalable, cost-efficient and privacy-preserving data generation.