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.
Highlights
Urban criminologists have long sought to understand variations in crime across communities within a city
The analysis that follows is limited to ZIP codes with a population of at least 10,000 in the 2015 American Community Survey (ACS) and where the ratio of the Facebook users estimates to 2015 population was less than 1.5
We see that the combination of demographic factors and Facebook interests had the greatest predictive strength for both the initial in-sample and the out-of-sample prediction, though the advantage over the demographics-only model varied by crime type
Summary
Urban criminologists have long sought to understand variations in crime across communities within a city. Most of this work has focused on ecological theories of criminogenesis and the contextual factors that encourage and discourage crime. Work highlighted the elevated levels of crime in areas of high poverty and concentrated disadvantage Using Facebook interests to improve predictions of crime rates most influential theories in the study of crime in communities has been social disorganization theory, which posits that social ties and the ability to establish and enforce social norms are critical to socializing residents and managing local spaces [2,3,4]. Others have argued that income inequality instigates those lower on the socioeconomic spectrum to turn to crime for self-advancement [5]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
