Applying dynamic human activity to disentangle property crime patterns in London during the pandemic: An empirical analysis using geo-tagged big data

Applying dynamic human activity to disentangle property crime patterns in London during the pandemic: An empirical analysis using geo-tagged big data

Citation

If you use the functions in this project in your research, please cite this source:

[MDPI and ACS Style]:
Chen, T.; Bowers, K.; Cheng, T. Applying Dynamic Human Activity to Disentangle Property Crime Patterns in London during the Pandemic: An Empirical Analysis Using Geo-Tagged Big Data. ISPRS Int. J. Geo-Inf. 2023, 12, 488. https://doi.org/10.3390/ijgi12120488

[AMA Style]:
Chen T, Bowers K, Cheng T. Applying Dynamic Human Activity to Disentangle Property Crime Patterns in London during the Pandemic: An Empirical Analysis Using Geo-Tagged Big Data. ISPRS International Journal of Geo-Information. 2023; 12(12):488. https://doi.org/10.3390/ijgi12120488

[Chicago/Turabian Style]:
Chen, Tongxin, Kate Bowers, and Tao Cheng. 2023. "Applying Dynamic Human Activity to Disentangle Property Crime Patterns in London during the Pandemic: An Empirical Analysis Using Geo-Tagged Big Data" ISPRS International Journal of Geo-Information 12, no. 12: 488. https://doi.org/10.3390/ijgi12120488

Project introduction

This study aimed to evaluate the relationships between different groups of explanatory variables (i.e., dynamic human activity variables, static variables of social disorganisation and crime generators, and combinations of both sets of variables) and property crime patterns across neighbourhood areas of London during the pandemic (from 2020 to 2021). Using the dynamic human activity variables sensed from mobile phone GPS big data sets, three types of ‘Least Absolute Shrinkage and Selection Operator’ (LASSO) regression models (i.e., static, dynamic, and static and dynamic) differentiated into explanatory variable groups were developed for seven types of property crime. Then, the geographically weighted regression (GWR) model was used to reveal the spatial associations between distinct explanatory variables and the specific type of crime. The findings demonstrated that human activity dynamics impose a substantially stronger influence on specific types of property crimes than other static variables. In terms of crime type, theft obtained particularly high relationships with dynamic human activity compared to other property crimes. Further analysis revealed important nuances in the spatial associations between property crimes and human activity across different contexts during the pandemic. The result provides support for crime risk prediction that considers the impact of dynamic human activity variables and their varying influences in distinct situations.

Code usage

The source codes in this project are in py file human_activity_property_crime.py.

All codes can be executed in Conda environment with the installed pkgs listed on the top of this file.

Open data

All sample data and our generated result files are in data folder.

Contact

Please contact the main code contributor in this project.

• Tongxin Chen (tongxin.chen.18@ucl.ac.uk), PhD researcher, SpacetimeLab for Big Data Analytics, University College London, London, UK.