Aptima’s ‘E-MEME’ Tracks Infectiousness Ideas
Aptima Develops ‘E-MEME’ to Track Infectiousness of Ideas across Groups and Geography
Epidemiological models applied to understanding information spread through populations
Woburn, MA, January 23, 2012 – From the Arab Spring to the summer U.K. riots, it was the spread of ideas from group to group, place to place that helped inspire rebellion and provoked unrest. But how do ideas flowing through the electronic landscape ‘infect’ and influence people? If epidemiology can model how illness spreads through populations, can the contagiousness of ideas across groups be similarly understood?
To address this challenge, Aptima, which applies expertise in how humans, think, learn, and behave, is developing E-MEME – the Epidemiological Modeling of the Evolution of MEssages. E-MEME is a system of web-based software designed to identify and track the flow of ideas or ‘memes’ through electronic media, helping model and forecast how sentiment can spread over time and place to influence susceptible populations.
Aptima and its partner, Circinus, are developing E-MEME through a contract with the Office of Naval Research (ONR). The technology is expected to help the U.S. military and intelligence communities better understand how information has become the new front line, where shaping or changing perceptions can have a large impact on outcomes.
“We witnessed the profound power of ideas to replicate in what began as anti-government sentiment in Tunisia, then moved like a virus, reaching and influencing new groups in Egypt, Syria, and Libya,” said Robert McCormack, Ph.D., Principal Investigator of E-MEME for Aptima. “Public health has used epidemiology for years to identify the origin and spread of illness through populations. If we can better understand the flow of ideas through electronic channels to sway the perceptions of groups, we may be better prepared to develop appropriate strategies, such as supporting democratic movements or perhaps dissuading suicide bombers.”
E-MEME applies natural language processing to extract the key memes and topics propagating through blogs, news sites, and real-time social platforms like Twitter. Its mathematically-based, epidemiological models plot how such ideas proliferate and spread amongst populations both geographically and over time.
E-MEME in Action
In a run up to an election, there may be rising chatter on Twitter, blogs, and news sites. What are the connections between what people are discussing? Will their attitudes and responses consequently influence others in villages and cities near and faraway? E-MEME’s statistical language processing, built on Aptima’s LaVATM platform for text analytics, scours large sets of Internet data sources and documents to characterize and quantify topics being discussed, such as ‘protests’ and ‘elections.’
Epidemiological models might capture the dynamics of the growing voice of opposition, as it occurs hourly, daily, and weekly, mapping where the sentiment is diffusing, and its potential to influence predisposed populations elsewhere. Such models may help forecast both where and when violent protests and potential uprisings are most likely to spark.
When complete, it’s expected that E-MEME will be used by U.S. intelligence analysts and watch officers, and for military operations more broadly at tactical, operational, and strategic scales.
“Today’s missions, whether counter-insurgency or support and stability, operate at multiple geographic and temporal scales – villages to nations, hours to months. Planning, executing, and assessing those operations depend on understanding the effects of our (and others’) actions on those perceptions,” McCormack added.