Using Big Data to Understand Urban Movements
Cities are complex social systems. To truly understand a city we need to understand the behaviour of the people who inhabit and use it on a daily basis. For example, London’s Trafalgar Square is not simply a space to house Nelson’s Column. To truly understand the place, we need to know who visits the area, where they have come from, why they go there, where they travel to afterwards, etc. With this knowledge we would have a much clearer picture of how the place is really used by society. This, in turn, will have major implications for phenomena such as crime, sustainability and health to name a few. For example:
- To accurately measure crime patterns in the area it is necessary to understand the number of visitors and their characteristics (the population at risk). Building this picture of potential victims is extremely difficult for a dynamic population such as visitors to Trafalgar Square.
- In an effort to improve sustainability, visitors to the area could be encouraged to use public transport. By better understanding the population who visit the area and how they get there, it will be possible to identify effective infrastructure improvements.
- In terms of health, identifying personal exposure to air pollution is extremely difficult for non residential populations. Understanding the true personal risks requires detailed information about popular daily movements at a high spatio-temporal resolution.
Trafalgar Square is a tiny illustrative example. In general, a broader understanding of spatio-temporal behavioural patterns across the city as a whole will have considerable impact on our understanding of urban dynamics, human behaviour and society more generally. However, data limitations and methodological barriers have previously rendered this type of research impossible.
I’m designing a research project that will make use of new Big Data which are created by the public and include information about their spatial location. Sources include photos posted on Flickr, messages on Twitter, FourSquare checkins, etc. Using these data it will be possible to build a clearer picture of the spatio-temporal behavioural patterns across the city as a whole will have considerable impact on our understanding of urban dynamics, human behaviour and society more generally. I will then apply this new knowledge to the study of policy-relevant phenomena (e.g. in health, crime or sustainability). A case study in Leeds will show how a better understanding of urban dynamics can be used to improve resource targeting by local government – e.g. more accurately identifying crime hotspots and hence diverting resources to the places of greatest need.
P.S. I’m certainly not the only person doing this! In a couple of weeks I’ll have put a brief literature review together and will post it here.