Systematic Social Observation at Scale
Using Crowdsourcing and Computer Vision to Measure Visible Neighborhood Conditions
Dados Bibliográficos
| ID | 6169922 |
|---|---|
| Autores | Jackelyn Hwang (0000-0003-2370-2796, Stanford University, Stanford, CA, USA, autor correspondente), Nikhil Naik (0000-0002-5191-2726, Salesforce Research, Palo Alto, CA, USA) |
| Ano | 2023 |
| Volume | 53 |
| Fascículo | 2 |
| Páginas | 183-216 |
| Data de publicação | 2023-04-10 |
| Peer Reviewed | Sim |
| Open Access | Sim |
| Tipo | ARTICLE |
| Periódico | Sociological Methodology (JOURNAL) |
| Identificadores do periódico | ISSN: 0081-1750 • E-ISSN: 1467-9531 |
| Editora | SAGE Publishing (PUBLISHER • US) |
| DOI | 10.1177/00811750231160781 |
| OpenAlex | W4363676506 |
| Idioma | EN |
| Citações recebidas | 14 |
| Referências citadas | 69 |
Analysis of neighborhood environments is important for understanding inequality. Few studies, however, use direct measures of the visible characteristics of neighborhood conditions, despite their theorized importance in shaping individual and community well-being, because collecting data on the physical conditions of places across neighborhoods and cities and over time has required extensive time and labor. The authors introduce systematic social observation at scale (SSO@S), a pipeline for using visual data, crowdsourcing, and computer vision to identify visible characteristics of neighborhoods at a large scale. The authors implement SSO@S on millions of street-level images across three physically distinct cities—Boston, Detroit, and Los Angeles—from 2007 to 2020 to identify trash across space and over time. The authors evaluate the extent to which this approach can be used to assist with systematic coding of street-level imagery through cross-validation and out-of-sample validation, class-activation mapping, and comparisons with other sources of observed neighborhood characteristics. The SSO@S approach produces estimates with high reliability that correlate with some expected demographic characteristics but not others, depending on the city. The authors conclude with an assessment of this approach for measuring visible characteristics of neighborhoods and the implications for methods and research
Built environment · Cartography · Crowdsourcing · Data mining · Data science · Geography · Measure (data warehouse · Pipeline (software · Sample (material · Scale (ratio · Walkability · World Wide Web · Computer Science · Health disparities and outcomes · Urban Transport and Accessibility · Urban, Neighborhood, and Segregation Studies
Neighborhood Desirability and Decision-Making in Online, Multiracial, Metropolitan America
Thinking about the Chicago School, 100 years on
Nationally Representative, Locally Misaligned
Event-Centered Interviewing
Streetscapes at Scale
Psycho-behavioral responses to urban scenes
An investigation of the use of Google Street View for identifying gentrification across diverse United States morphological city types
From disorder to distress
Black in blue networks
Artificial Intelligence Policymaking
Cleaning Up the Neighborhood
Generative Multimodal Models for Social Science
From Codebooks to Promptbooks
Curating Training Data for Reliable Large-Scale Visual Data Analysis
Great American City
Systematic social observation of children’s neighborhoods using Google Street View
Computer vision uncovers predictors of physical urban change
Measuring Urban Streetscapes for Livability
ImageNet classification with deep convolutional neural networks
Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States
Computing Inter-Rater Reliability for Observational Data
Building instance classification using street view images
Developing a reliable audit instrument to measure the physical environment for physical activity
Islands of decay in seas of renewal
Using Google Street View to Audit Neighborhood Environments
Child Development and the Physical Environment
The physical environment of street blocks and resident perceptions of crime and disorder
Deep learning
Measuring the Built Environment with Google Street View and Machine Learning
Segregation by Design
The Use of Surveillance Technologies in Planning Enforcement
Gentrification, Land Use, and Crime
Looking Through Broken Windows
Relying on the Census in Urban Social Science
Ethnography, Neighborhood Effects, and the Rising Heterogeneity of Poor Neighborhoods across Cities
Development and deployment of the Computer Assisted Neighborhood Visual Assessment System (Canvas) to measure health-related neighborhood conditions
Paths of Neighborhood Change
Seeing Disorder
Preserving history or restricting development? The heterogeneous effects of historic districts on local housing markets in New York City
Systematic Observation of Natural Social Phenomena
Crowdsourcing Subjective Perceptions of Neighbourhood Disorder
Ecometrics
Learning to See
Measuring and Explaining Political Sophistication through Textual Complexity
Casm
The Philadelphia Negro
Community Attachment in Mass Society
Divergent Pathways of Gentrification
Block, Tract, and Levels of Aggregation
The Truly Disadvantaged
Crowd-sourced Text Analysis
Neighborhood Disadvantage, Disorder, and Health
Video Data Analysis
Assessing 'Neighborhood Effects
Machine Learning for Sociology
Where, When, Why, and For Whom Do Residential Contexts Matter? Moving Away from the Dichotomous Understanding of Neighborhood Effects
Systematic Social Observation of Public Spaces
| Obras citantes distintas | 14 |
|---|---|
| Citações por ano | 4,67 |
| Intervalo de citações | 2023 - 2026 (4) |
| Velocidade de citação | current |
| Altamente citado | Não |
| Tipos de citação | Neutras: 14 |