11 papers
UST-GNN: A Unified Spatial--Topological Graph Neural Network Framework for Urban Analytics--Demonstrated through a Case Study on Urban Health Prediction
Minwei Zhao, Sanja Scepanovic, Stephen Law +3
Understanding how social, demographic, environmental, and spatial factors jointly shape urban outcomes is essential for sustainable urban development and evidence-based policy. Tra…
The Quiet Path from Seemingly Minor Design Errors to Workplace AI Incidents
Julia De Miguel Velázquez, Sanja Å ÄepanoviÄ, Andrés Gvirtz +1
Recent human-computer interaction (HCI) research has revealed a widespread misalignment between how developers design workplace artificial intelligence (AI) systems, and what worke…
When and How AI Should Assist Brainstorming for AI Impact Assessment
Jarod Govers, Sanja Å ÄepanoviÄ, Daniele Quercia
A key task in AI practice is to assess potential impacts to prevent harm. Current AI tools assisting AI impact assessment have not been designed or evaluated for collaborative team…
Why AI Harms Can't Be Fixed One Identity at a Time: What 5300 Incident Reports Reveal About Intersectionality
Edyta Bogucka, Sanja Å ÄepanoviÄ, Daniele Quercia
AI risk assessment is the primary tool for identifying harms caused by AI systems. These include intersectional harms, which arise from the interaction between identity categories…
Health-promoting Potential of Parks in 35 Cities Worldwide
Linus W. Dietz, Sanja Å ÄepanoviÄ, Ke Zhou +2
Urban parks are important for public health, but the role of specific spaces, such as playgrounds or lakes, and elements, such as benches or sports equipment, in supporting well-be…
Impact Assessment Card: Communicating Risks and Benefits of AI Uses
Edyta Bogucka, Marios Constantinides, Sanja Å ÄepanoviÄ +1
Communicating the risks and benefits of AI is important for regulation and public understanding. Yet current methods such as technical reports often exclude people without technica…