Revealing the amenity-perception connection: Integrating social sensing with generative AI

Mingyi Ma, Anni Hu, Koei Enomoto, Yuan Zhou and Yuan Lai

Environment and Planning B, 2026, vol. 53, issue 1, 32-48

Abstract: This study proposes a novel approach to social analysis through social media data and generative artificial intelligence (GAI). To demonstrate its practical application, we examine the relationship between visitor perceptions and the amenity mix of urban places, specifically Internet Famous Sites (IFSs). Social media data of 50 IFS across 26 Chinese cities were collected from platforms such as Ctrip and Rednote. Using GPT-4 as the semantic analysis model alongside prompt engineering techniques, we identified the perceived thematic characteristics of these IFS. Additionally, Points of Interest (POI) data were utilized to calculate the amenity mix, reflecting the actual thematic characteristics of the sites. The study tests four hypotheses: the perceptibility of themes, the correlation between visitor perceptions and the amenity mix, the disparity between perceived themes, and the correlation between different theme perceptions. The results demonstrate that the themes of IFS are highly perceptible and diverse, closely linked to the amenity mix. Significant disparities in theme perception were observed within the same site, and evidence of synergistic or competitive relationships between themes at the same site was also identified. This innovative method enhances the efficiency of social sensing, particularly in capturing visitor perceptions of places. By providing a nuanced understanding of visitor perceptions and their relationship to the amenity mix, this approach offers valuable insights for planners, enabling more informed decision-making and practical guidance for optimization and management of these sites.

Keywords: Generative AI; social sensing; POI; amenity mix; LLMs (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.1177/23998083251348746 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:envirb:v:53:y:2026:i:1:p:32-48

DOI: 10.1177/23998083251348746

Access Statistics for this article

More articles in Environment and Planning B
Bibliographic data for series maintained by SAGE Publications ().