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

TL;DR

This study leverages online reviews and advanced language models to analyze public perceptions of urban accessibility, revealing socio-spatial disparities and demonstrating crowdsourcing as a valuable tool for inclusive urban planning.

Contribution

It introduces a novel approach using fine-tuned large language models on crowdsourced online reviews to assess accessibility perceptions at a large scale.

Findings

Most POI categories show negative accessibility sentiment.

Higher socioeconomic areas report more positive perceptions.

No significant link between disability presence and sentiment.

Abstract

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.