Persona-aware and Explainable Bikeability Assessment: A Vision-Language Model Approach

2026-01-07

arXiv.org

AI Summary

This study addresses the limitations of existing perception-based approaches to assessing bicycle-friendliness, which struggle to capture the complexity of road environments and overlook the heterogeneity of users’ subjective perceptions. To overcome these challenges, the authors propose a vision-language model framework that integrates cyclist role characteristics to generate personalized and interpretable evaluations through chain-of-thought reasoning. Key innovations include a role-conditioning mechanism grounded in cyclist typology, a multi-granularity supervised fine-tuning strategy, and controllable AI-driven data augmentation. Evaluation on a crowdsourced dataset comprising 12,400 role-annotated samples demonstrates that the proposed method significantly outperforms current approaches in both predictive accuracy and interpretability.

Technology Category

• Computer Vision: Language and Vision
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Bikeability assessment is essential for advancing sustainable urban transportation and creating cyclist-friendly cities, and it requires incorporating users'perceptions of safety and comfort. Yet existing perception-based bikeability assessment approaches face key limitations in capturing the complexity of road environments and adequately accounting for heterogeneity in subjective user perceptions. This paper proposes a persona-aware Vision-Language Model framework for bikeability assessment with three novel contributions: (i) theory-grounded persona conditioning based on established cyclist typology that generates persona-specific explanations via chain-of-thought reasoning; (ii) multi-granularity supervised fine-tuning that combines scarce expert-annotated reasoning with abundant user ratings for joint prediction and explainable assessment; and (iii) AI-enabled data augmentation that creates controlled paired data to isolate infrastructure variable impacts. To test and validate this framework, we developed a panoramic image-based crowdsourcing system and collected 12,400 persona-conditioned assessments from 427 cyclists. Experiment results show that the proposed framework offers competitive bikeability rating prediction while uniquely enabling explainable factor attribution.

Problem

• bikeability assessment
• user perception heterogeneity
• road environment complexity
• explainable assessment
• persona-aware modeling

Innovation

• persona-aware
• explainable AI
• vision-language model
• bikeability assessment
• data augmentation