In a Wikipedia world of openly submitted and shared data, it can often be a daunting task to differentiate fact from fiction. Social media networks like Facebook and Twitter have made it possible for any and all information (or often, misinformation) to spread through cities, across nations and over oceans in a matter of seconds. Take for example the London Riots of 2011, in which a group of individuals Tweeted rumors of escaped animals from the London Zoo and fire-engulfed national landmarks over Twitter to cause panic and divert police (which worked, by the way). Smartphones, tablets, and other portable devices enabled nearly all of London to share and re-tweet the devastating “news”, which even made its way to televisions and radio stations before being confirmed as a hoax. So what if there had been some sort of “BS detector” in place, so to speak? Some device that could spot a false rumor or blatant untruth before it had the chance to have a negative impact? Researchers in Europe saw the need for just this type of program as well, and have developed a system called Pheme to try and flag the false before it gets to you.

Pheme, named after the Greek mythological creature famed for his scandalous rumors, would essentially function as a lie detector for Twitter and other sites. The idea is to break online rumors into four categories – speculation, controversy, misinformation and disinformation. The first two are fairly self-explanatory; speculative statements of neither fact nor fiction would be speculation, while controversy addresses the vast opinions offered on a daily basis that are merely controversial in nature. Misinformation and Disinformation both address the spread of untruths, but differ in their intent; misinformation is spread unwittingly, while disinformation is shared with malicious intent. In theory, Pheme would display the accuracy of a rumor via a virtual dashboard, giving you real-time access to the validity of the information you are receiving. This could be especially useful to journalists fact-checking a story, as well as prevent law enforcement agencies from wasting valuable time responding to false emergencies.

In addition to its ability to determine the level of “truthiness” associated with Tweets, researchers have equipped Pheme with the know-how to evaluate individual sources and determine even their authority. Its many functions are currently undergoing testing in groups of journalists and health care professionals to determine if, as lead researcher on the project Dr. Kalina Bontcheva stated, “we’ve got the balance right between automation and human analysis” (am I the only one fascinated by the notion of someone pulling this off?). We won’t have to wait much longer to see if this digital polygraph pans out as planned - the project should have its first set of test results in about 18 months, and prototypes of the system may be available even sooner than that.