The revolt that started a year ago today in Egypt was spread by Twitter and YouTube, or so the popular conception goes. But a group of Navy-backed researchers has a more controversial thesis:Egyptians were infected by the idea of overthrowing their dictator.
Using epidemiological modeling to chart the discussions and their trajectory online is an interesting idea, I don’t think that they are the first ones to do it. It’s a different approach to social network analysis which analyzes social phenomena through the properties of relations between and within units instead of the properties of these units themselves. This approach apparently considers trajectories of content combined with natural language analysis to determine what people in certain regions, of certain age groups, genders, or any number of other demographics, are discussing.
We’ve seen how content interception, classification and analysis has had success in the enterprise information security space – in particular with identifying data leaks by trusted insiders and unauthorized disclosure of intellectual property. Doing it on a national or global scale, is much more than computing power. It’s also understanding the political milieu and intent of the subjects, a powerful challenge for any intelligence organization.
I’m not sure how they collect the actual demographics, handle historical data, deliberate disinformation or feedback effects or even if their model is a good fit for the problem but it’s thought provoking.