Automating the Collection of Online Criminal Justice Data

• In Event: Putting Text Together: Criminal Justice Applications of Text Analytics

Abstract

A wealth of unstructured text data exists online that, in a different format, could be analyzed on its own or used to enhance existing criminal justice data sources. Web scraping is a popular technique for automating the extraction of this type of data from websites so that it can be processed and stored in an analyzable format in a fraction of the time and with a fraction of the effort that would be required to collect the data manually. This presentation introduces the web scraping process and describes an application of the technique on Environmental Protection Agency (EPA) criminal prosecution case summaries available on the EPA website.

Authors

• Emily Tiry, Urban Institute

• KiDeuk Kim, Urban Institute