CrimeTelescope: crime hotspot prediction based on urban and social media data fusion

Abstract

Crime is a complex social issue impacting a considerable number of individuals within a society. Preventing and reducing crime is a top priority in many countries. Given limited policing and crime reduction resources, it is often crucial to identify effective strategies to deploy the available resources. Towards this goal, crime hotspot prediction has previously been suggested. Crime hotspot prediction leverages past data in order to identify geographical areas susceptible of hosting crimes in the future. However, most of the existing techniques in crime hotspot prediction solely use historical crime records to identify crime hotspots, while ignoring the predictive power of other data such as urban or social media data. In this paper, we propose CrimeTelescope, a platform that predicts and visualizes crime hotspots based on a fusion of different data types. Our platform continuously collects crime data as well as urban and social media data on the Web. It then extracts key features from the collected data based on both statistical and linguistic analysis. Finally, it identifies crime hotspots by leveraging the extracted features, and offers visualizations of the hotspots on an interactive map. Based on real-world data collected from New York City, Published in "World Wide Web doi: 10.1007/s11280-017-0515-4, 2017" which should be cited to refer to this work.we show that combining different types of data can effectively improve the crime hotspot prediction accuracy (by up to 5.2%), compared to classical approaches based on historical crime records only. In addition, we demonstrate the usability of our platform through a System Usability Scale (SUS) survey on a full prototype of CrimeTelescope.

A Novel Method of Spatiotemporal Dynamic Geo-Visualization of Criminal Data, Applied to Command and Control Centers for Public Safety

“…Some studies can serve this purpose, since their approach include one or several characteristics. In this regard, these studies include: Investigations with methodology that include georeferencing and spatial and statistical analysis to find critical points such as [5,[24][25][26][27][28] or; visualizations with predictive usefulness, such as [29][30][31][32][33]; simulations of criminal behavior aimed at analyzing collateral effects and resources allocations [34][35][36]; systems that use algorithms for trajectory analysis to identify crimes from different sources of information [37,38]; mechanisms for calculating severity of incidents determined by distance, time and type of transition, plotted on heatmaps with dynamic transition, to extract information on street crimes [39,40]; systems for merging, associating and clustering data attributes, as well as for associating with other nodes to extract patterns from evolving criminal networks, based on observation and analysis of temporary data [41][42][43]; and finally, visualizations that use comparisons to find similarities in criminal patterns through associative searches with knowledge graphs [44] and multivariate reduction plots for comparative analysis of cases [45].…”

Research Hotspot Prediction and Regular Evolutionary Pattern Identification Based on NSFC Grants Using NMF and Semantic Retrieval

“…Xiao et al [40] proposed a prediction method for social hotspots that is based on dynamic tensor decomposition. Yang et al [41] used urban and social media data fusion for crime hotspot prediction. Xia et al [42] introduced an efficient approach that uses support vector machine (SVM) to predict hot spot residues in protein interfaces.…”

Systematic Literature Review of Crime Prediction and Data Mining

“…Method used Tasks Gaps [9,12,14,15,31,32,33] Association rule mining Crime pattern analysis from crime data Model's processing time and visualization were not considered. [1,2,10,17,27,35]…”