Crowdsourcing emergency response Pt. 1

January 2011: One of the largest hurdles facing emergency responders is how to handle the amount of real-time information during a crisis. In order to get a clear picture of what is happening right after an earthquake, during a hurricane, in the aftermath of a terrorist attack, or before a flood hits, emergency response personnel and officials are increasingly turning to crowdsourcing as a way to digest large amounts of data and turn that data into actionable intelligence. Through social networking, text messaging and video crowdsourcing allows for multimedia information to be amalgamated and synthesized.

Over the last few years, international response organizations and governments have been using technology in increasing measures to track information in real time. During the initial response effort in Haiti after the 7.0 magnitude earthquake flattened the country's capital Port-au-Prince, killing more than 300,000 people, US Military officials used crowdsourcing to help decipher Kreyol text messages.

In a paper by Robert Munro from the University of Stanford, US Military officials recruited Kreyol and French-speaking volunteers "to translate, categorize, and geolocate" incoming text messages. "Collaborating online," the volunteers "employed their local knowledge of locations, regional slang, abbreviations and spelling variants to process more than 40,000 messages in the first six weeks alone. According to responders this saved hundreds of lives and helped direct the first food and aid to tens of thousands."

Aside from text messaging, tools like Ushahidi allow for end users (responders in the field, or citizens volunteers) to supply information which is then generated into a map which can have several layers of detail to give a clear, real-time picture about what is happening. Ushahidi is currently being used by the Australian government in Queensland in response to the historic floods inundating the country. The software platform is also being used for the responses in Haiti and in Pakistan.

Then, there is also the question of social media and how emergency management can use the intelligence generated through sites like Twitter, MySpace, and Facebook. iDisaster wrote about another Ushahidi-related platform called SwiftRiver which allows emergency management and government officials to use social networking sites as information-delivery pathways.

"If your community is using social media to connect to citizens during non-disaster events, you should expect your citizens will use that same conduit to ask for assistance or to information the city/county of problems during a major crisis," iDisaster wrote. Newark Mayor Cory Booker had an active twitter account with more than one-million followers. During the storm, many of his followers used twitter to send Booker information about the state of their neighborhoods. Having that much information could be overwhelming.

Needing to "curate" relevant and new information coming from users; verifying that information; removing duplicate messages; and displaying that information to emergency and volunteer response personnel are the three hurdles facing social media data. SwiftRiver "offer organizations an easy way to combine natural language/articial intelligence process, data-mining for SMS and Twitter, and verification algorithms for different sources of information," SwiftRiver's website read.

"Swift's user-friendsly dashboard means that users need not be experts in artificial intelligence or algorithms to aggregate and validate information. The intuitive dashboard allows users to easily manage sources of information they wish to triangulate, such as email, Twitter, SMS and RSS feeds from the web," the website read.

See also:

Tech companies partner with computer users to search for missing pilot

Geo-imaging formatting by company helps firefighters in California