Toward satisfactory public accessibility: A crowdsourcing approach through online reviews to inclusive urban design

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Lingyao, Hu, Songhua, Dai, Yinpei, Deng, Min, Momeni, Parisa, Laverghetta, Gabriel, Fan, Lizhou, Ma, Zihui, Wang, Xi, Ma, Siyuan, Ligatti, Jay, Hemphill, Libby
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916391901200384
author Li, Lingyao
Hu, Songhua
Dai, Yinpei
Deng, Min
Momeni, Parisa
Laverghetta, Gabriel
Fan, Lizhou
Ma, Zihui
Wang, Xi
Ma, Siyuan
Ligatti, Jay
Hemphill, Libby
author_facet Li, Lingyao
Hu, Songhua
Dai, Yinpei
Deng, Min
Momeni, Parisa
Laverghetta, Gabriel
Fan, Lizhou
Ma, Zihui
Wang, Xi
Ma, Siyuan
Ligatti, Jay
Hemphill, Libby
contents As urban populations grow, the need for accessible urban design has become urgent. Traditional survey methods for assessing public perceptions of accessibility are often limited in scope. Crowdsourcing via online reviews offers a valuable alternative to understanding public perceptions, and advancements in large language models can facilitate their use. This study uses Google Maps reviews across the United States and fine-tunes Llama 3 model with the Low-Rank Adaptation technique to analyze public sentiment on accessibility. At the POI level, most categories -- restaurants, retail, hotels, and healthcare -- show negative sentiments. Socio-spatial analysis reveals that areas with higher proportions of white residents and greater socioeconomic status report more positive sentiment, while areas with more elderly, highly-educated residents exhibit more negative sentiment. Interestingly, no clear link is found between the presence of disabilities and public sentiments. Overall, this study highlights the potential of crowdsourcing for identifying accessibility challenges and providing insights for urban planners.
format Preprint
id arxiv_https___arxiv_org_abs_2409_08459
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Toward satisfactory public accessibility: A crowdsourcing approach through online reviews to inclusive urban design
Li, Lingyao
Hu, Songhua
Dai, Yinpei
Deng, Min
Momeni, Parisa
Laverghetta, Gabriel
Fan, Lizhou
Ma, Zihui
Wang, Xi
Ma, Siyuan
Ligatti, Jay
Hemphill, Libby
Social and Information Networks
As urban populations grow, the need for accessible urban design has become urgent. Traditional survey methods for assessing public perceptions of accessibility are often limited in scope. Crowdsourcing via online reviews offers a valuable alternative to understanding public perceptions, and advancements in large language models can facilitate their use. This study uses Google Maps reviews across the United States and fine-tunes Llama 3 model with the Low-Rank Adaptation technique to analyze public sentiment on accessibility. At the POI level, most categories -- restaurants, retail, hotels, and healthcare -- show negative sentiments. Socio-spatial analysis reveals that areas with higher proportions of white residents and greater socioeconomic status report more positive sentiment, while areas with more elderly, highly-educated residents exhibit more negative sentiment. Interestingly, no clear link is found between the presence of disabilities and public sentiments. Overall, this study highlights the potential of crowdsourcing for identifying accessibility challenges and providing insights for urban planners.
title Toward satisfactory public accessibility: A crowdsourcing approach through online reviews to inclusive urban design
topic Social and Information Networks
url https://arxiv.org/abs/2409.08459