Dataset Information

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.

SUBMITTER: Fatehkia M

PROVIDER: S-EPMC6361434 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Fatehkia Masoomali M O'Brien Dan D Weber Ingmar I

PloS one 20190204 2

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 ...[more]

PMID: 30716110

Similar Datasets

Project description:Background: Many regions worldwide reported a decline of stroke admissions during the early phase of the coronavirus disease 2019 (COVID-19) pandemic. It remains unclear whether urban and rural regions experienced similar declines and whether deviations from historical admission numbers were more pronounced among specific age, stroke severity or treatment groups. Methods: We used registry datasets from (a) nine acute stroke hospitals in Berlin, and (b) nine hospitals from a rural TeleNeurology network in Northeastern Germany for primary analysis of 3-week-rolling average of stroke/TIA admissions before and during the COVID-19 pandemic. We compared course of stroke admission numbers with regional cumulative severe acute respiratory syndrome coronavirus 2 (Sars-CoV-2) infections. In secondary analyses, we used emergency department logs of the Berlin Charité University hospital to investigate changes in age, stroke severity, and thrombolysis/thrombectomy frequencies during the early regional Sars-CoV-2 spread (March and April 2020) and compared them with preceding years. Results: Compared to past years, stroke admissions decreased by 20% in urban and 20-25% in rural hospitals. Deviations from historical averages were observable starting in early March and peaked when numbers of regional Sars-CoV-2 infections were still low. At the same time, average admission stroke severity and proportions of moderate/severe strokes (NIHSS >5) were 20 and 20-40% higher, respectively. There were no relevant deviations observed in proportions of younger patients (<65 years), proportions of patients with thrombolysis, or number of thrombectomy procedures. Stroke admissions at Charité subsequently rebounded and reached near-normal levels after 4 weeks when the number of new Sars-CoV-2 infections started to decrease. Conclusions: During the early pandemic, deviations of stroke-related admissions from historical averages were observed in both urban and rural regions of Northeastern Germany and appear to have been mainly driven by avoidance of admissions of mildly affected stroke patients.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets