This week I had the opportunity to get a demo of a new crowdsourcing tool developed at the University of Virginia. The project is dubbed Crowdsourcing the Crisis and is the result of a collaboration between the University’s School of Medicine and Computer Science department with funding provided by a Department of Defense grant. They have created a tool that enables the crowd to help authorities make a decision on whether to evacuate citizens in the event of a crisis.
Today, these decisions are made by authorities – for example, the mayor – based only on information they have from their employees and some interactions with other agencies. Crowdsourcing the Crisis allows citizens to communicate real-time status updates about events unfolding around them. Updates can be shared via the web, a mobile web interface, a standalone Android application, Twitter, and Flickr.
The updates are aggregated, rated, and organized in a way that allows decision makers to create filters for specific types of events overlaid on a map. For example: “at 11:35 AM: Power line down on Grady Avenue makes the road impassable!”
As they were demoing the tool, it brought back memories of the Snowmageddon example that popped up in Washington DC last year. This tool was based on the Ushahidi platform which is similar to the tool developed on this project.
Next up for the project is to improve the reputation system to allow authorities to better evaluate the credibility of submitted information. It seems the topic of reputation in crowdsourcing is coming up a lot recently. Users of crowdsourcing models are increasingly demanding reputation systems that can act as an indicator of trustworthiness.
Ultimately, to take this out of the University and into the commercial market, someone will have to figure out how to get this in the hands of consumers and motivate them to use it. As we all know, the hardest part of crowdsourcing is not the technology but the individual motivation and social dynamics in crowd participation.