Since earlier this year we’ve been working on Swift River, our attempt to use both machine algorithms and crowdsourcing to verify incoming streams of information. You can read more about the initiative and why it’s important, and you can take a look at a video where we were planning out what exactly it would do, and finally my short talk at TED earlier this year on Swift.
We’ve had a problem though, our team is small and we’ve had to use the lion’s share of our time and energy just to keep Ushahidi on track. Meaning, we’ve not been able to put as much resources into Swift necessary to make it what it should be by now.
Our answer to this is Jon Gosier.
Jon is the founder of Appfrica Labs in Uganda, a Senior TED Fellow and a name well-known amongst the African technology and blogging crowd (on Twitter at JonGos). Jon will be leading the Swift River initiative from our side. Besides his technical and organizational skills, we’re excited to have Jon on board because he shares the same ethos, energy and African roots as the rest of us.
Jon will also work alongside the rest of the Swift River community, including the ones who came up with the idea; Kaushal Jhalla and Chris Blow who have been doing most of the work over the past year on this project.
A little more on Swift River’s purpose
The purpose of the Swift River initiative is to develop a free and open-source platform to validate crowdsourced crisis information in near real-time. User-generated content is becoming an increasingly important source of information during crises while traditional media continues to play a pivotal role in documenting crises as they unfold. These two trends are expected to continue well into the future. The challenge is how to filter this growing torrent of information while keeping the “floodgates” open?
There is an apparent tradeoff between crowdsourcing (opening the floodgates) and data validation (the filter). One of the strengths of crowdsourcing is the ability to collect a high volume of information from highly diverse sources in near real time. One of the challenges, however, is to validate this vast amount of information in near real-time in order to inform crisis early warning and rapid response operations.