Persona-aware and Explainable Bikeability Assessment: A Vision-Language Model Approach
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915712673513472 |
|---|---|
| author | Dai, Yilong Wang, Ziyi Wang, Chenguang Zhou, Kexin Qian, Yiheng Xu, Susu Yan, Xiang |
| author_facet | Dai, Yilong Wang, Ziyi Wang, Chenguang Zhou, Kexin Qian, Yiheng Xu, Susu Yan, Xiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03534 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Persona-aware and Explainable Bikeability Assessment: A Vision-Language Model Approach Dai, Yilong Wang, Ziyi Wang, Chenguang Zhou, Kexin Qian, Yiheng Xu, Susu Yan, Xiang Computation and Language Computer Vision and Pattern Recognition Human-Computer Interaction Machine Learning 68T50 (Primary) 68T07, 91C99 (Secondary) I.2.7; I.4.8; J.4 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. |
| title | Persona-aware and Explainable Bikeability Assessment: A Vision-Language Model Approach |
| topic | Computation and Language Computer Vision and Pattern Recognition Human-Computer Interaction Machine Learning 68T50 (Primary) 68T07, 91C99 (Secondary) I.2.7; I.4.8; J.4 |
| url | https://arxiv.org/abs/2601.03534 |