Analysis of social media data allows us to identify and better understand crime hot spots. This research explores ways to identify which times and places have the largest concentrations of potential crime victims, and hence which hotspots pose the most significant problems. The aim is to help incident response and crime reduction organisations to focus their resource more effectively.
To demonstrate the value of our data holdings, researchers at our host universities are currently undertaking Big Data exemplar research projects in each of our key research themes.
Enumerating the ambient population in the context of crime
Population counts have traditionally been derived from decennial censuses, but these have tended to be limited in their ability to capture daily fluctuations in population size that can occur when people move between different activity types and locations.
Since reliable population figures are fundamental to the efficient allocation of public resources and service provision, there is growing interest in the use of alternative data sources as enumerators of the population. Accurate representations of the ambient population are extremely relevant for the field of crime analysis because they can facilitate the identification of areas where the risk of victimisation is comparatively high, or low, relative to the size of the underlying population.
Application of Natural Language Processing for identification of online hate on Twitter
The aim of this research was to investigate whether online hate on Twitter could be used as a proxy for ‘real life’ hate occurring in Lancashire. The ambition of the project was to enable Lancashire Constabulary to harness new forms of social media data (Twitter) for their own analysis of hate crime in the area – e.g. to identify possible emerging community tensions early – by applying machine learning.
Analysis of police-recorded hate crime in Lancashire
Understanding hate crime is a priority for police forces across England and Wales. Since the EU referendum in June 2016, there has been renewed emphasis on the importance of preventing hate crime and providing support for victims. The objective of this research was to describe the nature and spatial density of reported hate incidents and crimes in Lancashire by making sense of the police-recorded data.
The Centre delivers a national service to the social science research community by providing access to a large volume of consumer data for research. Users can access our datasets either directly from the datastore or by application.
Investigation into the correlation between footfall and violence levels
The average violent incident costs taxpayers £33k. Many incidents occur in and around licensed premises at night, the focus of the current investigation. Knowledge of when and where hotspots of violence are likely to occur can allow police to implement preventative measures to reduce risk of harm, and public health teams to make more informed licensing decisions. This project investigates the relationship between footfall and violence levels, and aims to enhance and validate an existing model of pedestrian footfall to assist police and public health teams.