Posts tagged ‘Crowdsourcing’

SwiftRiver sorts realtime social media streams

We are drowning in information, while starving for wisdom. The world henceforth will be run by synthesizers, people able to put together the right information at the right time, think critically about it and make important choices wisely.

E.O. Wilson, Consilience: The Unity of Knowledge

How can we evaluate citizen media for breaking news? Hurricanes? Earthquakes? Contested elections? Crowdsourced crisis information produces a flood of data. Individuals send emails, write blog posts, text friends, post to Twitter. Popular tweets are echoed and amplified. Eyewitness reports may be reliable, or mistaken – or planted disinformation.

SwiftRiver, an initiative of the Ushahidi project, aims to help humans aggregate and evaluate streams of social media. SwiftRiver is an open source platform for managing realtime data streams. Its services can be combined in different ways to serve the needs of crisis responders, journalists, and so on.

The first such app is Sweeper (now in beta), which intelligently filters data feeds for volunteers who then validate and geolocate the information.

Jon Goslin, TED Fellow and SwiftRiver director, talks about the five services underlying the apps.

  • Natural language processing to extract meaning.
  • Location context: considering how local the source is to reported events.
  • Reducing duplicates, especially those from Twitter.
  • Accounting for popularity separately from accuracy.
  • Reputation management: authority accruing to those for those who have a history of valued posts.
Advertisements

August 31, 2010 at 3:45 pm Leave a comment

Wikipedia color-codes consensus

Starting this fall, an optional extension to Wikipedia will automatically color-code text backgrounds to indicate how “trusted” the text is.

WikiTrust (via Wired Science)Currently, text on a Wikipedia page is agglutinated from the contributions of multiple, anonymous authors. Anyone can contribute and over-write existing text. This leaves entries open to bias, vandalism, and editing wars.

The WikiTrust extension computes the author of every word of text and determines the author’s reputation based on previous, lasting, contributions. Less trusted text is backgrounded with an orange shade, which fades to white as the text survives later edits and is considered increasingly trustworthy.

Note that trust isn’t truth, it’s consensus. If you’re a new contributor to Wikipedia, your contributions will be colored with a bright orange shade. Established contributors’ new text is colored with a paler orange. But even as an established contributor, if you write something controversial that gets edited in and out, that text will also be flagged with color.

Readers won’t be facing a sea of orange, however. The overall levels of orange text-tagging are kept low in the interest of readability. And the entire trust mechanism will be a separate tab on the Wikipedia page, so you can choose whether to view your pages with or without it.

(via Wired Science)

September 1, 2009 at 5:00 pm Leave a comment

Crowdsourced election protection

In following innovative uses of SMS (text) messaging, I’ve been delving into the work of Ushahidi. The name means “testimony” in Swahili, and the platform crowdsources crisis information such as political upheavals or natural disasters. Anyone can submit updates through text messaging using a mobile phone, email or web form.

Ushahidi was developed to map reports of violence in Kenya after the post-election fallout at the beginning of 2008.

In breaking news, Alive in Afghanistan is using the Ushahidi mapping system to report election irregularities.

Map of citizen-reported Afghan election irregularities

Text messages are collected via Frontline SMS, another great system which uses free open source software to turn a laptop + mobile phone into a central communications hub. Easy to set up, portable, and resilient: just what is needed in chaotic circumstances.

The next issue is what to do with the flood of information that comes in beyond a heat map of incidence reporting. What do you pull out of the SMS or Twitter stream? What’s credible? What’s important? In particular, how do you deal with the first three hours of a crisis? Ushahidi founder and TED fellow Erik Hersman is tackling that problem now.

Graph: Quantity vs. quality of hour by hour crisis reporting data

A small team at Swift River is looking to the crowd to filter data as well as generate it.

Swift … is an initiative that seeks to do two very important things, both of which are crucial for not just Ushahidi, but for many emergency response activities in the future. First, it gathers as many possible streams of data about a particular crisis event as possible. Second, using a two-part filter, that stream of data is filtered through both machine based algorithms and humans to better understand the veracity and level of importance of any piece of information. –Erik

See it in action at Vote Report India.

August 20, 2009 at 11:32 am 1 comment


Twitter Updates

Recent Posts

Feeds


%d bloggers like this: