Generative AI as a Playful yet Offensive Tourist: Exploring Tensions Between Playful Features and Citizen Concerns in Designing Urban Play

TL;DR

The paper investigates how image-to-image Generative AI (GAI) can enable playful urban interactions while surfacing citizen concerns. Using iWonder, a mobile GAI tool, the study engages 14 designers in situ to extract six Playful Features and six design ideas, then evaluates these ideas with 14 citizens to reveal benefits and risks. Through reflexive thematic analysis, the authors identify opportunities to enhance agential, emotional, and social dimensions of urban spaces, alongside concerns such as misalignment, safety, cultural preservation, and privacy. The authors propose design considerations and the metaphor of GAI as a playful yet offensive tourist to guide responsible deployment in city contexts and inform future urban-computing research.

Abstract

Play is pivotal in fostering the emotional, social, and cultural dimensions of urban spaces. While generative AI (GAI) potentially supports playful urban interaction, a balanced and critical approach to the design opportunities and challenges is needed. This work develops iWonder, an image-to-image GAI tool engaging fourteen designers in urban explorations to identify GAI's playful features and create design ideas. Fourteen citizens then evaluated these ideas, providing expectations and critical concerns from a bottom-up perspective. Our findings reveal the dynamic interplay between users, GAI, and urban contexts, highlighting GAI's potential to facilitate playful urban experiences through generative agency, meaningful unpredictability, social performativity, and the associated offensive qualities. We propose design considerations to address citizen concerns and the `tourist metaphor' to deepen our understanding of GAI's impact, offering insights to enhance cities' socio-cultural fabric. Overall, this research contributes to the effort to harness GAI's capabilities for urban enrichment.

Figures (21)

• Figure 1: The interfaces of our image-to-image GAI tool: iWonder.
• Figure 2: A Summary Illustrating the Tensions of GAI-enabled Urban Play.
• Figure 3: The Backgrounds of Designer Participants.
• Figure 4: An example of the canvas in the ideation session.
• Figure 5: Top: DP8 painted over the unsightly signage on the building and generated a street view without them. Bottom: DP6 noticed the open lawn and generated a device detecting rabbit activities. This creation integrated his place memories.