Research & Papers

NUS study: AI street view analysis reveals personality-neighborhood links

Openness best predicted by built environment (R²=0.47) at ZIP code level

Deep Dive

New research maps Big Five personality traits against built environment features derived from street view imagery across four Texas cities. Combining fine-resolution self-reported personality data with computer vision analysis of urban environments, the team identified significant spatial clustering of personality traits at the ZIP code level. Regression analyses showed that built environment features and socioeconomic characteristics explain substantial variance in personality distributions, with Openness having the strongest model fit (R² = 0.47), followed by Agreeableness, Conscientiousness, Extraversion, and Neuroticism. Grouped built environment categories, socioeconomic factors, and demographic composition showed trait-specific patterns of association. These findings suggest personality traits may be associated with physical spaces at a smaller geographic scale than previously examined, providing empirical evidence for understanding links between psychological characteristics and environmental features. The paper has been accepted for publication in the Annals of the American Association of Geographers (AAG).

Key Points
  • CV analysis of Google Street View imagery links Big Five traits to built environment in 4 Texas cities
  • Openness strongest predictor with R²=0.47; significant spatial clustering found at ZIP code level
  • Published in Annals of AAG; 44 pages including supplementary material

Why It Matters

Shows AI-driven street view analysis can map psychological traits at neighborhood scale, aiding urban design and mental health research.

📬 Get the top 10 AI stories daily