Polygraph Tests for e-mails

Interesting article from Popular Science.


Researchers at several are developing software to identify lies in cyberspace. The software can detect lies in online communications such as instant messages, e-mails, and chatrooms. According to Jeff Hancock, an assistant professor for communication and a member of the faculty of computing and information science at Cornell University, who conduct studies for digital deception, there is a growing body of evidence that the language of dishonest messages is different from that of honest ones. One study conducted by Hancock found that deceptive e-mail messages contained 28% more words on average and used a higher percentage of words associated with negative emotions than did truthful messages. Liars also tend to use fewer first person references (“I”) and more third person references (“he” and “they”). According to the study, this may be the liars subconscious way of distancing himself from his lie.


Hancock is trying to identify patterns of deceit. To do this, Hancock has developed an instant-messaging system at Cornell that asks users to rate the deceptiveness of each message they send. According to the article, the system has already collected 10,000 messages, of which about 6% qualify as patently deceptive. The results will later be incorporated into a software that analyzes incoming messages. If a person receives a message that fits a pattern of deceptiveness, he will get an onscreen warning that the message may warrant special attention.

This is technology with a little bit of psychology.