January 29, 2010
Friday night I was getting ready to spend the weekend working on my board meeting slides when my friend Ian Monroe came by the office and told me to talk to Robert Munro. Robert is a computational linguist who does research on large scale processing of text messages — an obscure subject until the earthquake in Haiti happened two weeks ago.Robert had been working with Josh Nesbit, cofounder of FrontLineSMS:Medic, an awesome NGO dedicated to building SMS based communication infrastructure for people in the developing world.
Just after the earthquake, Josh convinced Digicel and Comcel, the two largest mobile carriers in Haiti to setup a number, 4636, that anyone could text message to. They advertised it all over Haiti and pretty soon they were getting a message every few seconds. A team of techies including Robert and (in particular) Brian Herbert of Ushahidi (a very cool organization which creates various kinds of crowdsourced mapping projects) hacked together an infrastructure which aggregates and processes the SMS messages coming from Haiti. This allowed a team of volunteers to translate, classify and geocode the messages. From launch, InSTEDD/Thompson Reuters worked with the Red Cross on the ground, responding to emergency requests. Within days, Ushahidi and a second team of volunteers were mapping incidents and coordinating actionable responses with the US Coast Guard.
Robert and Brian were looking for a scalable solution to route tasks to a distributed workforce that could handle the high volume and low latency necessary to make their program a success — exactly what CrowdFlower does. They were also looking for a more stable, long term solution than a strictly volunteer workforce. Our partners at Samasource, a socially responsible outsourcing organization, had just setup a large bilingual digital workforce in Haiti.
It felt like we had a perfect solution to an important problem and I stopped working on the board slides and started writing code to glue the Digicel and Comcel feeds into our API and build the task within our framework. Our engineers were extremely responsive to bug reports from a CEO who may not have read the API documentation as thoroughly as he could have at first. I presented my most underprepared board slides to a very understanding board ☺ and on Wednesday night we became the live feed and essentially the 911 switchboard for the 4636 project in Haiti.
You can learn more about the project at Mission 4636 on the Samasource website where, if you speak Kreyol or know someone that does, you can sign up to volunteer. Samasource has been hard at work building up the infrastructure in Haiti needed to process the messages. In the meantime, we’re recruiting volunteers around the world to help meet the demand. As I write this, more than 12,000 messages have been translated and processed by the amazing volunteers.
If you don’t speak Kreyol and want to support the project, another way to help is by donating money directly to Samasource.