Assessing the feasibility of a video-based conversational chatbot survey for measuring perceived cycling safety: A pilot study in New York City

Bicycle safety is essential for bikeability and transport efficiency, yet conventional surveys often fail to capture how people perceive cycling environments in real time because they depend on retrospective recall. This study proposes a video-based conversational AI chatbot survey, powered by large language models (LLMs), to collect perceptions of cycling safety and the reasons behind them. The chatbot was developed using a modular LLM architecture that integrates prompt engineering, state management, and rule-based control. Its feasibility was evaluated through a pilot study involving 16 participants across nine street segments in New York City. The method feasibility was assessed using a seven-point scale rating for user experience (i.e., ease of use, supportiveness, efficiency) and a five-point scale for chatbot usability (i.e., personality, roboticness, friendliness), yielding positive results with mean scores of 5.00 out of 7 (standard deviation = 1.60) and 3.47 out of 5 (standard deviation = 0.43), respectively. The data feasibility was assessed using multiple techniques: (1) natural language processing (NLP), such as KeyBERT, for overall safety and feature analysis to extract built-environment attributes; (2) K-means clustering for semantic analysis to identify reasons and suggestions; and (3) regression to estimate the effects of built-environment and demographic variables on perceived safety outcomes. The results show the potential of AI chatbots as a novel approach to collecting data on human perception, behavior, and future visions for transport planning.