CrimeVec—Exploring Spatial-Temporal Based Vector Representations of Urban Crime Types and Crime-Related Urban Regions

Alessandro Crivellari,Alina Ristea

doi:10.3390/ijgi10040210

Abstract

The traditional categorization of crime types relies on a hierarchical structure, from high-level categories to lower-level subtypes. This tree-based classification treats crime types as mutually independent when they do not branch from the same higher-level category, therefore lacking inter-category semantic relations. The issue then extends over crime distribution analysis of urban regions, often reporting statistics based on crime type counts, but neglecting implicit relations between different crime categories. Our study aims to fill this information gap, providing a more complete understanding of urban crime in both qualitative and quantitative terms. Specifically, we propose a vector-based crime type representation, constructed via unsupervised machine learning on temporal and geographic factors. The general idea is to define crime types as “related” if they often occur in the same area at the same time span, regardless of any initial hierarchical categorization. This opens to a new metric of comparison that goes beyond pre-defined structures, revealing hidden relationships between crime types by generating a vector space in a completely data-driven manner. Crime types are represented as points in this space, and their relative distances disclose stronger or weaker semantic relations. A direct application on urban crime distribution analysis stands out in the form of visualization tools for intuitive data investigations and convenient comparison measures on composite vectors of urban regions. Meaningful insights on crime type distributions and a better understanding of urban crime characteristics determine a valuable asset to urban management and development.

Highlights

The study of crime distribution in urban regions is a major source of information for local authorities, leading to appropriate measures and convenient strategies by the police and municipality
Urban region evaluation focuses on the result of the compositional approach that combines representations of crime types into representations of urban regions, in the form of qualitative thematic maps obtained through the customization of the crime type vector space, or in the form of actual compositional vectors of urban regions obtained by averaging embeddings of single crime types
The traditional approach of making statistics towards the crime counts on separate types neglects the implicit semantic relations between the different types, missing a meaningful aspect of the urban crime configuration

Summary

Introduction

The study of crime distribution in urban regions is a major source of information for local authorities, leading to appropriate measures and convenient strategies by the police and municipality. The investigation of urban crime distribution is often affected by the data source of the study area, whereby different national and local organizations provide different crime type definitions and categorizations. It has been researched that once a crime event occurs in a defined location, further crime events are likely to occur in nearby areas, defining intra-category crime patterns. In this sense, the focus on near-repeat situations commonly concentrates only on a very small set of distinctive categories, namely burglary, robbery, and weapon violations [9,10,11]. There are a few works combining multiple categories into single classes based on similar environmental characteristics [15] or pre-defined crime type aggregation properties (e.g., violent and non-violent crimes) [16]

Methods

Results

Conclusion