Image Structure of Cities Formed by Social-Networking Service Posts—Spatial Distribution and Content Similarity Evaluation on the Urban Landscape Images in Central Tokyo From Flickr

Abstract

This research investigated the impact of social-networking service posts on the formation of image structure of cities, focusing on the spatial distribution of images and their content similarity. It aimed to delineate the image structure of cities created by numerous users, moving beyond traditional qualitative methods towards a more quantitative and objective approach with big data. Taking central Tokyo as an example, this study extracted geotagged image data of 33 major railway station areas from Flickr’s API (Application Programming Interface). Four coverage types of viewpoint distribution, namely planar, intersecting linear, linear, and nodal, were identified, reflecting the unique urban structures respectively. Further investigation of the image contents, primarily consisting of “urban landscape” and “landscape/street trees,” showed that such contents significantly influenced the formation of the image structure of cities. The study concluded that as the number of photo posts increased and the representative viewpoints concentrated, the digital information received by users became more homogeneous, leading to strongly stereotyped images of urban landscapes. These findings highlight the role of social networking services in shaping perceptions of the urban environment and provide insights into the image structure of cities as formed by digital information.

Keywords

Social Networking Service / Image Structure of the City / Flickr / Image Analysis / Stereotyped City Image / Perception / Tokyo

RIGHTS & PERMISSIONS

2024 Higher Education Press