Criminological data can be very costly or hard to access as they contain sensitive information on criminal behavior and victimization. Recent developments in data science and computing, however, are opening up new ways to gather this once elusive data. In a short article for the University of Florida Bureau of Economic and Business Research, Tom Smith and I wrote about using R to scrape criminological data from the web and analyze patterns of crime and victimization in US cities.
Data scraped from online “daily bulletins” of local police departments can be used to study patterns of arrests, citations, summons, ordinance violations, victimizations, and traffic accidents.
Among other things, these data enable the mapping of co-offending networks – networks of people who commit crimes together. These can be analyzed to identify network subgroups, such as gangs or crime families; detect the most central offenders, who participate in criminal activities with many other partners; and examine how crime “partnerships” and groups form.
The full article, with more details about the R tools used in this project, is here.
