Appendix A9 - Using Social Media Content To Inform Agent-based Models For Humanitarian Crisis Response
The Hotspots model (Wise, 2014) was created using MASON and utilises open data to generate asynthetic population with realistically distributed social ties to one another. This synthetic population is then used to populate a model of households being interrupted from their daily activities by the presence of a developing threat. Households make decisions about the wildfire that threatens them based on their own observations, public announcements through conventional media, and communications from their sociallylinked peers. Traffic flow modelling reflects the emergent result of those individual decisions to stay or evacuate, capturing the location and timing of traffc jams in the emergency situation. Thus, the tool allows for researchers to better explore the way interventions might cascade across the environment andtranslate into different evacuation outcomes.
Graphical user interface of the Hotspots model showing the spatial environment where the red dots denotes agents.
Model Available at: https://github.com/swise5/Hotspots while the data is at: http://css1.gmu.edu/swise/thesis/. Alternatively for a more upto date version of the model see: https://github.com/eclab/mason/tree/master/contrib/geomason/sim/app/geo.
Reference:
Wise, S. (2014), Using Social Media Content To Inform Agent-based Models For Humanitarian Crisis Response, PhD Dissertation, George Mason University, Fairfax, VA.
Click on the image below to see a YouTube movie of the model:
