Modelling Real-Life Cycling Decisions in Real Urban Settings Through Psychophysiology and LLM-Derived Contextual Data

TL;DR

This study addresses how real-world urban contexts shape cyclists' decisions by coupling psychophysiological indicators with rich, LLM-derived contextual data. It advances discrete choice modeling by integrating latent arousal and fatigue through an Integrated Choice and Latent Variable framework and by using a Large Language Model to extract semantically detailed environmental descriptors from video. The field study in Santiago demonstrates that latent states and multimodal context improve predictive accuracy and offer actionable insights for infrastructure design, highlighting the value of combining physiological data with AI-assisted environmental interpretation in urban mobility research. The approach provides a scalable way to quantify how safety, infrastructure quality, and traffic conditions influence cyclist behavior, with potential policy implications for safer urban cycling design.

Abstract

Measuring emotional states in transportation contexts is an emerging field. Methods based on self-reported emotions are limited by their low granularity and their susceptibility to memory bias. In contrast, methods based on physiological indicators provide continuous data, enabling researchers to measure changes in emotional states with high detail and accuracy. Not only are emotions important in the analysis, but understanding what triggers emotional changes is equally important. Uncontrolled variables such as traffic conditions, pedestrian interactions, and infrastructure remain a significant challenge, as they can have a great impact on emotional states. Explaining the reasons behind these emotional states requires gathering sufficient and proper contextual data, which can be extremely difficult in real-world environments. This paper addresses these challenges by applying an innovative approach, extracting contextual data (expert annotator level) from recorded multimedia using large language models (LLMs). In this paper, data are collected from an urban cycling case study of the City of Santiago, Chile. The applied models focus on understanding how different environments and traffic situations affect the emotional states and behaviors of the participants using physiological data. Sequences of images, extracted from the recorded videos, are processed by LLMs to obtain semantic descriptions of the environment. These discrete, although dense and detailed, contextual data are integrated into a hybrid model, where fatigue and arousal serve as latent variables influencing observed cycling behaviors (inferred from GPS data) like waiting, accelerating, braking, etc. The study confirms that cycling decisions are influenced by stress-related emotions and highlights the strong impact of urban characteristics and traffic conditions on cyclist behavior.

Figures (10)

• Figure 1: Cycling study route.
• Figure 2: LLM Video Descriptor (LVD) process.
• Figure 3: Heatmaps of semantic causes of cyclist's stress generated by LLM Video Descriptor (LVD).
• Figure 4: Diagram of the proposed ICLV model. Observable variables in rectangles; latent variables in ellipses.
• Figure 5: MNL model diagram.