It's not you, it's me -- Global urban visual perception varies across demographics and personalities

2025-05-19

AI Summary

Urban planning increasingly relies on street-level visual perception models trained on generalized demographic data, which obscures critical sociodemographic and psychological heterogeneity—exacerbating algorithmic bias. Method: We conducted a global street scene perception experiment across five countries, involving 1,000 demographically balanced participants from 45 nationalities, and systematically incorporated personality traits—a first in this domain—to construct SPECS, the inaugural benchmark dataset integrating socioeconomic attributes and psychological dimensions. Contribution/Results: We identify significant disparities across gender, age, income, education, race, and personality for all six conventional and four novel perceptual metrics. State-of-the-art global models consistently overestimate positive perceptions and underestimate negative ones. We uncover “regional affective transfer”—a phenomenon wherein models trained on one region misgeneralize emotional responses to others—and quantify localized perceptual biases. Our findings rigorously establish the necessity of region-specific modeling, providing both theoretical grounding and empirical infrastructure for equitable, inclusive urban perception computing.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Understanding people's preferences and needs is crucial for urban planning decisions, yet current approaches often combine them from multi-cultural and multi-city populations, obscuring important demographic differences and risking amplifying biases. We conducted a large-scale urban visual perception survey of streetscapes worldwide using street view imagery, examining how demographics -- including gender, age, income, education, race and ethnicity, and, for the first time, personality traits -- shape perceptions among 1,000 participants, with balanced demographics, from five countries and 45 nationalities. This dataset, introduced as Street Perception Evaluation Considering Socioeconomics (SPECS), exhibits statistically significant differences in perception scores in six traditionally used indicators (safe, lively, wealthy, beautiful, boring, and depressing) and four new ones we propose (live nearby, walk, cycle, green) among demographics and personalities. We revealed that location-based sentiments are carried over in people's preferences when comparing urban streetscapes with other cities. Further, we compared the perception scores based on where participants and streetscapes are from. We found that an off-the-shelf machine learning model trained on an existing global perception dataset tends to overestimate positive indicators and underestimate negative ones compared to human responses, suggesting that targeted intervention should consider locals' perception. Our study aspires to rectify the myopic treatment of street perception, which rarely considers demographics or personality traits.

Problem

• Examining demographic and personality influences on urban visual perception
• Identifying biases in global perception datasets and machine learning models
• Proposing new indicators for streetscape evaluation across diverse populations

Innovation

• Large-scale urban visual perception survey
• Dataset SPECS with socioeconomics and personality
• Machine learning model vs human perception comparison