How can you really tell a liar? Engineering researchers have found a novel technique to find out. The framework can be built up in order to extract opinion from 'fake news'. The article was part of a paper in Journal of Experimental & Theoretical Artificial Intelligence. Earlier studies looked at deception. But this one examined the intent. Even a true story can be managed to deceive listeners.
However, it is the intent, rather than content that determines whether it is a lie or not. Hence, a speaker might be misinformed or arrive at an incorrect assumption. He may have made an error that was not intended. Still, he did not try to fib. "Deceptive intent to mislead listeners on purpose poses a much larger threat than unintentional mistakes," said Eugene Santos Jr., co-author and professor of engineering at Thayer School of Engineering at Dartmouth. "To the best of our knowledge, our algorithm is the only method that detects deception and at the same time discriminates malicious acts from benign acts."
Scientists leveraged an algorithm to differentiate deception from benign communication. They thus retrieved some common and universal features of deceptive reasoning. Still, currently the framework faces some limitations. There is immense data needed to gauge how much a speaker can deviate from earlier arguments. Scientists used information from a 2009 survey of 100 participants, comparing their viewpoints on sensitive subjects, and also a 2011 dataset of 800 factual and 400 fake reviews of 20 hotels.
It is possible to develop the framework much more in order to enable readers to differentiate between the intent of "fake news." It would help a reader to find out if a reasonable and logical argument has been used or whether viewpoints are playing a strong role. In further studies, Santos hopes that he can probe into the various effects of misinformation, including its effects. The popular 2001 film, 'Ocean's Eleven' has been used to display how the framework can falsify the deceiver's arguments. It might even violate his beliefs and lead to false expectations in the end.
The movie shows a gang of thieves breaking into the vault and also telling the bank owner that he is being robbed. While giving him false assurance that they would rob only half the vault if he does not call the police, they then anticipate that he would. Once he calls the cops, the thieves dress up like policemen and rob all the money.
"People expect things to work in a certain way," said Santos, "just like the thieves knew that the owner would call the police when he found out he was being robbed. So, in this scenario, the thieves used that knowledge to convince the owner to come to a certain conclusion and follow the standard path of expectations. They forced their deception intent so the owner would reach the conclusions the thieves desired."
Usually, facial expressions help to indicate whether someone is lying or not. However, co-authors say that such hints are not always dependable. "We have found that models based on reasoning intent are more reliable than verbal changes and personal differences, and thus are better at distinguishing intentional lies from other types of information distortion," said co-author Deqing Li, who worked on the paper as part of her PhD thesis at Thayer.
