Correlated Impulses: Using Facebook Interests to Improve Predictions of Crime Rates in Urban Areas

Masoomali Fatehkia, Northeastern University
Dan O'Brien, Northeastern University
Ingmar Weber , Qatar Computing Research Institute

Much research has examined how crime rates vary across urban neighborhoods, focusing particularly on community-level characteristics or at individual levels as an expression of certain behavioral patterns. Little work has considered, however, whether the prevalence of such behavioral patterns in a neighborhood might be predictive of local crime. The Facebook Advertising API offers a special opportunity to examine this question. We conduct an analysis, using regression models, 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. 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.

See paper

 Presented in Session 128. Using Social Media in Population Research