Abstract
Research on the relationship between space and social interaction has focused on indoor spaces, such as museums and offices. However, empirical evidence on the connection between the intensity of social interaction and outdoor public spaces is still lacking. Applying machine learning algorithms to a 9-hour time-lapse video of an urban park, we decipher the effects of two spatial features, edges, and landmarks, on visitors’ activities. We identified dynamic visitor groups in the videos through a graph-based method and mapped the clustering pattern of interaction activities over time and space. In parallel, we used a computer vision algorithm to delineate fixed objects (notably the harbourfront, landside park boundary, a carousel, four benches, three pavilions, and four heart-shaped seating) and dynamic edges (formed by moveable furniture as park visitors repositioned them) onsite. We found that dynamic edges formed by moveable furniture and the fixed edge of a visual landmark consistently attracted more social interaction and group activities. In designing public spaces that encourage group activities, urban planners and designers can leverage the combination of fixed objects and flexible furniture to maximise the choices for visitors and curate a more engaging public open space.
Get full access to this article
View all access options for this article.
References
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
