An algorithm may automatically spot deception in emails and other computer-based communication.
You may know not to send money to a Nigerian prince to access his windfall, but not all e-lies are as easy to spot. Researchers have designed an algorithm to identify linguistic cues of deception in computer-mediated communication. According to the soon-to-be-published paper “Untangling a Web of Lies: Exploring Automated Detection of Deception in Computer-Mediated Communication,” there are certain tells when communication is fraudulant, including the minimization of self-deprecation, inclusion of flattery and mimicking of the “linguistic style of the recipient across e-mail exchanges, because they want to make themselves appear more accommodating and likeable.”
Among practical applications, this automated text analysis could be helpful to companies looking to pre-classify potentially fraudulent customer claims. As Dr. Tom van Laer, Senior Lecturer in Marketing at Cass Business School, points out: "This research opens up the possibility of fraud prevention and deception detection technology across lots of in-person domains, not just e-mail. Our approach comes from big data - combining statistics with natural language processing patterns that tip us off to deception. Authorities and companies will now be able to figure out the plausibility of fraud and identify lying individuals."
