Correlated impulses: Using Facebook interests to improve predictions of crime rates in urban areas

Masoomali Fatehkia, Dan O'Brien, Ingmar Weber

Research output: Contribution to journalArticle

Abstract

Much research has examined how crime rates vary across urban neighborhoods, focusing particularly on community-level demographic and social characteristics. A parallel line of work has treated crime at the individual level as an expression of certain behavioral patterns (e.g., impulsivity). Little work has considered, however, whether the prevalence of such behavioral patterns in a neighborhood might be predictive of local crime, in large part because such measures are hard to come by and often subjective. The Facebook Advertising API offers a special opportunity to examine this question as it provides an extensive list of “interests” that can be tabulated at various geographic scales. Here we conduct an analysis of the association between the prevalence of interests among the Facebook population of a ZIP code and the local rate of assaults, burglaries, and robberies across 9 highly populated cities in the US. We fit various regression models to predict crime rates as a function of the Facebook and census demographic variables. In general, models using the variables for the interests of the whole adult population on Facebook perform better than those using data on specific demographic groups (such as Males 18-34). In terms of predictive performance, models combining Facebook data with demographic data generally have lower error rates than models using only demographic data. We find that interests associated with media consumption and mating competition are predictive of crime rates above and beyond demographic factors. We discuss how this might integrate with existing criminological theory.

Original languageEnglish
Article numbere0211350
JournalPLoS One
Volume14
Issue number2
DOIs
Publication statusPublished - 1 Feb 2019

Fingerprint

crime
Crime
urban areas
demographic statistics
Demography
prediction
Application programming interfaces (API)
Impulsive Behavior
Censuses
Marketing
Population
Research

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Correlated impulses : Using Facebook interests to improve predictions of crime rates in urban areas. / Fatehkia, Masoomali; O'Brien, Dan; Weber, Ingmar.

In: PLoS One, Vol. 14, No. 2, e0211350, 01.02.2019.

Research output: Contribution to journalArticle

@article{ac31900db07c42c699be287ef631bf18,
title = "Correlated impulses: Using Facebook interests to improve predictions of crime rates in urban areas",
abstract = "Much research has examined how crime rates vary across urban neighborhoods, focusing particularly on community-level demographic and social characteristics. A parallel line of work has treated crime at the individual level as an expression of certain behavioral patterns (e.g., impulsivity). Little work has considered, however, whether the prevalence of such behavioral patterns in a neighborhood might be predictive of local crime, in large part because such measures are hard to come by and often subjective. The Facebook Advertising API offers a special opportunity to examine this question as it provides an extensive list of “interests” that can be tabulated at various geographic scales. Here we conduct an analysis of the association between the prevalence of interests among the Facebook population of a ZIP code and the local rate of assaults, burglaries, and robberies across 9 highly populated cities in the US. We fit various regression models to predict crime rates as a function of the Facebook and census demographic variables. In general, models using the variables for the interests of the whole adult population on Facebook perform better than those using data on specific demographic groups (such as Males 18-34). In terms of predictive performance, models combining Facebook data with demographic data generally have lower error rates than models using only demographic data. We find that interests associated with media consumption and mating competition are predictive of crime rates above and beyond demographic factors. We discuss how this might integrate with existing criminological theory.",
author = "Masoomali Fatehkia and Dan O'Brien and Ingmar Weber",
year = "2019",
month = "2",
day = "1",
doi = "10.1371/journal.pone.0211350",
language = "English",
volume = "14",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "2",

}

TY - JOUR

T1 - Correlated impulses

T2 - Using Facebook interests to improve predictions of crime rates in urban areas

AU - Fatehkia, Masoomali

AU - O'Brien, Dan

AU - Weber, Ingmar

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Much research has examined how crime rates vary across urban neighborhoods, focusing particularly on community-level demographic and social characteristics. A parallel line of work has treated crime at the individual level as an expression of certain behavioral patterns (e.g., impulsivity). Little work has considered, however, whether the prevalence of such behavioral patterns in a neighborhood might be predictive of local crime, in large part because such measures are hard to come by and often subjective. The Facebook Advertising API offers a special opportunity to examine this question as it provides an extensive list of “interests” that can be tabulated at various geographic scales. Here we conduct an analysis of the association between the prevalence of interests among the Facebook population of a ZIP code and the local rate of assaults, burglaries, and robberies across 9 highly populated cities in the US. We fit various regression models to predict crime rates as a function of the Facebook and census demographic variables. In general, models using the variables for the interests of the whole adult population on Facebook perform better than those using data on specific demographic groups (such as Males 18-34). In terms of predictive performance, models combining Facebook data with demographic data generally have lower error rates than models using only demographic data. We find that interests associated with media consumption and mating competition are predictive of crime rates above and beyond demographic factors. We discuss how this might integrate with existing criminological theory.

AB - Much research has examined how crime rates vary across urban neighborhoods, focusing particularly on community-level demographic and social characteristics. A parallel line of work has treated crime at the individual level as an expression of certain behavioral patterns (e.g., impulsivity). Little work has considered, however, whether the prevalence of such behavioral patterns in a neighborhood might be predictive of local crime, in large part because such measures are hard to come by and often subjective. The Facebook Advertising API offers a special opportunity to examine this question as it provides an extensive list of “interests” that can be tabulated at various geographic scales. Here we conduct an analysis of the association between the prevalence of interests among the Facebook population of a ZIP code and the local rate of assaults, burglaries, and robberies across 9 highly populated cities in the US. We fit various regression models to predict crime rates as a function of the Facebook and census demographic variables. In general, models using the variables for the interests of the whole adult population on Facebook perform better than those using data on specific demographic groups (such as Males 18-34). In terms of predictive performance, models combining Facebook data with demographic data generally have lower error rates than models using only demographic data. We find that interests associated with media consumption and mating competition are predictive of crime rates above and beyond demographic factors. We discuss how this might integrate with existing criminological theory.

UR - http://www.scopus.com/inward/record.url?scp=85061039359&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061039359&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0211350

DO - 10.1371/journal.pone.0211350

M3 - Article

C2 - 30716110

AN - SCOPUS:85061039359

VL - 14

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 2

M1 - e0211350

ER -