Spatial-Temporal-Textual Point Processes for Crime Linkage Detection

TL;DR

This paper introduces a novel statistical framework using spatio-temporal-textual point processes to improve crime linkage detection by modeling complex interactions and incorporating free-text descriptions as marks, demonstrating superior performance on real data.

Contribution

It presents a new multivariate marked Hawkes process model that integrates spatial, temporal, and textual data for crime analysis, a novel approach in this domain.

Findings

Enhanced crime linkage detection accuracy

Revealed meaningful spatial dependence patterns

Improved police operational insights

Abstract

Crimes emerge out of complex interactions of human behaviors and situations. Linkages between crime incidents are highly complex. Detecting crime linkage given a set of incidents is a highly challenging task since we only have limited information, including text descriptions, incident times, and locations. In practice, there are very few labels. We propose a new statistical modeling framework for {\it spatio-temporal-textual} data and demonstrate its usage on crime linkage detection. We capture linkages of crime incidents via multivariate marked spatio-temporal Hawkes processes and treat embedding vectors of the free-text as {\it marks} of the incident, inspired by the notion of {\it modus operandi} (M.O.) in crime analysis. Numerical results using real data demonstrate the good performance of our method as well as reveals interesting patterns in the crime data: the joint modeling of space, time, and text information enhances crime linkage detection compared with the state-of-the-art, and the learned spatial dependence from data can be useful for police operations.