This is a live blog. It may contain grammatical errors, but I tried to be as true to the essence of the comments as possible?.
Juliana Rotich spoke about Ushahidi, the crowdsourced crisis reporting platform. I’ve written about Ushahidi before, and I have written about Swift River last year. During a rapidly developing event, how do you manage that torrent of information, Juliana said. You have to create an ‘information slider’, she said to help evaluate information. How do you separate signal from noise, wheat from chaff? They wanted to know how to deal with a “hot flash” event:
It was that crisis that started two members of the Ushahidi dev community (Chris Blow and Kaushal Jhalla) thinking about what needs to be done when you have massive amounts of information flying around. We’re at that point where the barriers for any ordinary person sharing valuable tactical and strategic information openly is at hand. How do you ferret the good data from the bad??
What if we listened to the crowd? Not just what is popular, that might not be pertinent.
What if we listened to victims?
What about creating a crisis dashboard. They showed how to us Tweetdeck to curate information. Information can be filtered by crowd or by algorithms. Swift River is an “aggregator with entity extraction”. By pulling together relevant feeds, they can then parse content, creating a rich database of people, places and organisations in real time. They can create a taxonomy to deal with the data. Swift can help determine the authority of sources with algorithms. The location data can help them figure out what is happening where.
They are trying to save time, identify and rate trusted sources, surface relevant content (suppress noise) and curate it all.
Jon Gossier of Appfrica, who I met last year, has been helping to move the Swift River project forward. I’ve been meaning to write about this for a while, but Swift recently released a web service. This is definitely a project to watch.