Guided Persona-based AI Surveys: Can we replicate personal mobility preferences at scale using LLMs?

2025-01-20

AI Summary

Traditional travel surveys suffer from high costs, low efficiency, poor scalability, and privacy constraints. To address these challenges, this paper proposes a large language model (LLM)-based synthetic data generation method. Its core innovation is a structured “persona” prompting mechanism that explicitly encodes demographic and behavioral attributes as conditional constraints to guide the LLM in generating high-fidelity travel preference data. The method is calibrated and evaluated on the real-world German Mobility in Germany (MiD) 2017 dataset. Compared with five state-of-the-art synthetic data generation approaches, it more accurately reproduces multidimensional dependencies among age, income, geography, and transport mode choice, reducing key error metrics by 32%. The framework ensures privacy preservation, incurs minimal computational cost, and supports scalable deployment. Moreover, it enables interpretable, scenario-based transportation policy analysis through controllable, attribute-conditioned generation.

Technology Category

• Natural Language Processing: Generation
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Web data generation and simulation

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.

Problem

• Large Language Models
• Personal Travel Preferences
• Data Generation

Innovation

• Large Language Models
• synthetic surveys
• Personal Mobility Preferences