A new study from Brigham Young University finds that when people are lying in digital messages, such as texting, instant messaging or social media, they take longer to respond, have to edit more and write shorter than usual responses.
“Digital conversations are a fertile ground for deception because people can easily conceal their identity and their messages often appear credible,” says Tom Meservy, BYU professor of information systems. “Unfortunately, humans are terrible at detecting deception. We’re creating methods to correct that.”
Meservy says humans can accurately detect a lie about 54 percent of the time, which isn’t much better than flipping a coin. Detecting a lie through a digital message is even more difficult because you can’t hear the person’s voice or see any of their facial expressions.
Meservy and fellow BYU professor Jeffrey Jenkins teamed up with colleagues from the University of Nebraska-Omaha and the University of Arizona to set up an experiment that looked for potential cues for online deception.
The researchers developed a computer program to carry out online conversations with study participants that were similar to what you would experience with online customer service questions.
More than 100 students from two universities, one in the southeast United States and the other in the southwest, held conversations with the computer where they were each asked a set of 30 questions.
Study participants were instructed to lie in about half of their responses to the questions. What the researchers saw was that it took the participants about 10 percent longer to craft a lie and they needed to edit them more than a truthful message.
“We are starting to identify signs given off by individuals that aren’t easily tracked by humans,” Meservy adds. “The potential is that chat-based systems could be created to track deception in real-time.”
Meservy and Jenkins, co-authors of the study, say people shouldn’t automatically assume someone is telling a lie if they take longer to respond, but the study does reveal a general pattern of deception.
The group of researchers are furthering their line of research by using several other sensors, like Microsoft’s Kinect, to track behavior and see how it is connected with deception.
“We are just at the beginning of this,” Jenkins says. “We need to collect a lot more data.”
The findings of this study can be found online in the academic information systems journal ACM Transactions on Management Information Systems.