Narrative data from police agencies on arrest or offense incidents and tips to police departments are rich in information and largely unavailable to the public for analysis. Dallas has published over 45,000 de-identified incidents containing narrative data from 2013 and 2014. Assessing large quantities of narrative data for patterns using manual analysis alone can be time consuming and produces limited qualitative results. How can modern methods in text analytics assist? This presentation used the data set available from https://www.dallasopendata.com as a model for how text analytics can assist with assessing police narrative data for patterns, enhancing both time-to-value and quality of analysis. While this presentation assessed the data for crime-related patterns, it specifically covered methods to identify risk indicators for human trafficking. AI capabilities were showcased for developing relevant concepts for extraction from the narratives and demonstrate how to visualize these AI-supported extraction results in a user-friendly environment. These methods can be replicated across any police agency to comb narrative event data for human trafficking indicators or to surface other crime-related patterns of interest.
Presentation slides are attached to this post.
