Chapter 7 - Geospatial crime analysis and forecasting with machine learning techniques

Abstract

People use social media to engage, connect, and exchange ideas, for professional interests, and for sharing images, videos, and other contents. According to the investigation, social media allows researchers to examine individual behavior features and geographic and temporal interactions. According to studies, criminology has become a prominent subject of study globally, using data gathered from online social media sites such as Facebook, News feed articles, Twitter, and other sources. It is possible to obtain useful information for the analysis of criminal activity by using spatiotemporal linkages in user-generated content. The study refers to the application of text-based data science by gathering data from several news sources and visualizing it. This research is motivated by the abovementioned work from various social media crimes and government crime statistics. This chapter looks at 68 various crime keywords to help you figure out what kind of crime you are dealing with concerning geographical and temporal data. For categorizing crime into subgroups of categories with geographical and time aspects using news feeds, the Naive Bayes classification algorithm is used. For retrieving keywords from news feeds, the Mallet package is used. The hotspots in crime hotspots are identified using the K-means method. The KDE approach is utilized to address crime density and this methodology has solved the difficulties that the current KDE algorithm has. The study results demonstrated equivalence between the suggested crimes forecasting model as well as the ARIMA model.