This study used social media (Twitter) data to construct estimates of the population at various locations at different times of day, and assessed whether these estimates helped predict the amount of crime during 2-hour time periods over the course of the day.
A challenge for studies that assess routine activities theory is accounting for the spatial and temporal confluence of offenders and targets, given that people move about during the daytime and nighttime. The current study addressed these issues by using crime data for 97,428 blocks in the Southern California region, along with geocoded information on tweets in the region over an 8-month period. The results show that this measure of the temporal ambient population helped explain the level of crime in blocks during particular time periods. The use of social media data are promising for testing various implications of routine activities and crime- pattern theories, given their explicit spatial and temporal nature. (publisher abstract modified)
Downloads
Similar Publications
- A ROC-based Approximate Bayesian Computation Algorithm for Model Selection: Application to Fingerprint Comparisons in Forensic Science
- A Study on the Asymmetry of the Human Left and Right Pubic Symphyseal Surfaces Using High-Definition Data Capture and Computational Shape Methods
- Love of a Good Man?: Romantic Relationships as a Source of Support or Hindrance for Female Ex-Offenders