Can a Twitter-Based Measure of Racial Heterogeneity Explain Neighborhood Crime Differences? Proposing an Ambient Population Measure of Social Disorganization

Social disorganization theory traditionally studies neighborhood social dynamics through residential demographic indicators. However, insights from routine activities theory show that people spend time outside their home neighborhoods, suggesting that the populations who use places may differ from those who reside there. Building on this tension, this study uses an ethically informed approach to introduce a social media-derived measure of ambient racial heterogeneity and assess whether dynamic population compositions explain crime variation across neighborhoods. Using a Gaussian Naïve Bayes approach to estimate race with geotagged mobility data, we track the spatial footprints of 6,547 Twitter users who posted in Boston in 2018. These data are used to construct census-tract measures capturing the racial diversity of neighborhood users rather than residents. Validation indicates 90.5% agreement with reference classifications and demographic comparability to Boston’s population. Negative binomial models show that ambient racial heterogeneity is positively associated with violent and nonviolent crime in nonresidential tracts.

Authors

Publication Details

Journal
Figshare
Published
2026-11-13
DOI
https://doi.org/10.6084/m9.figshare.34999240
Primary Topic
Crime Patterns and Interventions
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Can a Twitter-Based Measure of Racial Heterogeneity Explain Neighborhood Crime Differences? Proposing an Ambient Population Measure of Social Disorganization

Forrest Hangen, Riley Tucker, Dan O'Brien (18963505)
Figshare
Crime Patterns and Interventions
article

Can a Twitter-Based Measure of Racial Heterogeneity Explain Neighborhood Crime Differences? Proposing an Ambient Population Measure of Social Disorganization

Forrest Hangen, Riley Tucker, Dan O'Brien (18963505)
article en

Abstract

Social disorganization theory traditionally studies neighborhood social dynamics through residential demographic indicators. However, insights from routine activities theory show that people spend time outside their home neighborhoods, suggesting that the populations who use places may differ from those who reside there. Building on this tension, this study uses an ethically informed approach to introduce a social media-derived measure of ambient racial heterogeneity and assess whether dynamic population compositions explain crime variation across neighborhoods. Using a Gaussian Naïve Bayes approach to estimate race with geotagged mobility data, we track the spatial footprints of 6,547 Twitter users who posted in Boston in 2018. These data are used to construct census-tract measures capturing the racial diversity of neighborhood users rather than residents. Validation indicates 90.5% agreement with reference classifications and demographic comparability to Boston’s population. Negative binomial models show that ambient racial heterogeneity is positively associated with violent and nonviolent crime in nonresidential tracts.

Figshare
Reduced inequalities, Sustainable cities and communities, Peace, justice, and strong institutions
Crime Patterns and Interventions
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon