Saturday, December 11, 2010

Emerging Technology for MS Analysis

I reproduce below a recent post on a new technology for detecting the difference between "grassroots" dissemination of information, and "orchestrated campaigns". It should be obvious that if this can be detected on the internet, the same techniques should be able to establish whether for instance the Byzantine text-type is a real "grassroots" type, or an "artificial" (formal) recension.

Truthy: Visualizing the Diffusion of Information on Twitter

"Truthy [] is a recently developed online system to analyze and visualize the diffusion of information on Twitter. It evaluates 1,000s of tweets an hour to identify new bursts of activity around specific topics and memes, to reveal when, where and how they emerged .

For instance, Truthy claims it can distinguish organically emerging grass-roots viral campaigns from those that [are] forged (i.e. 'astroturfing', which denotes political, advertising, or public relations campaigns that are formally planned by an organization, but are disguised as spontaneous, popular 'grassroots' behavior). It therefore uses a combination of text and data mining, social network analysis, and complex networks models, together with a training algorithm based on input from users who are invited to flag dubious injections.

Next to a network diagram that shows the relationships between Twitter members that retweet or mention a specific of meme, the interface also contains a meme activity timeline graph and various numerical statistics and mood-identifying semantic analysis results."

For more information, see also here. See also Tracking the Mood on Twitter.



No comments: