The internet has given us access to incredible amounts of information. We have what could be considered access to the world’s largest library at our fingertips. We have the ability to speak with friends and family face to face from pretty much anywhere in the world and essentially engage anybody in conversation. Although the list of advantages is long, the list of disadvantages is becoming just as long.
Everybody has the tools to voice their opinion, write down their points of view and share knowledge and information with the world. However, this deluge of information has created enormous problems for all of us. Namely trying to ascertain what points of view are valid, what opinions are based on experience and which ones are based on ignorance. Or simply, what information is based on facts and trustworthy!
The ability for individuals to hide behind a veil of deceit, remain anonymous, and spread false truths has become commonplace. The rapid technological advances have now placed us in the precarious situation where we can’t even be sure if we are communicating with computer generated text or a real person. This has made it all the more complicated for us as individuals to identify who is lying, who is trustworthy or what is factual?
Our best defence against these technological advances, or any fighting chance at filtering out all of the distortions of the truth among the masses of information and data is through technology.
For this reason, Florida State University researcher Shuyuan Ho is working towards creating a revolutionary online polygraph. According to Ho, “You could use it for online dating, Facebook, Twitter — the applications are endless. I think the future is unlimited for an online polygraph system.” Towards this goal, she created an online game to measure truthful and deceptive communications between two people. The findings were then detailed in the journal of Computers in Human Behavior. After having parsed the words in those conversations she extracted context from millions of bits of data and a large number of messages in order to indentify who was telling the truth and who was lying. The experiments revealed a person could spot lies in messages about 50 percent of the time, while a machine-learning approach could identify deception with an accuracy rate ranging from 85 to 100 percent.
Some of the interesting tendancies that were exposed included, liars were found to be less expressive, yet they used more decorative words per message and they took less time to respond. Those telling the truth tended to say ‘no’ a lot.
Dr Tom van Laer, Senior Lecturer in Marketing at Cass Business School, believes that this kind of research opens up the possibility of fraud prevention and deception detection technology across lots of in-person domains. By combining statistics with natural language processing patterns that have the ability to identify deception, authorities and companies will now be able to figure out the plausibility of fraud and identify lying individuals.
An online polygraph test that has the ability to identify liars, deception or fake news could be a game changer. The only question then would be which eventually technology wins out, the one that has been developed to create lies, or the one that has been developed to identify them?
Shuyuan Ho currently supervises the iSensor Lab on FSU’s campus where researchers have been conducting experiments to better understand deception in online communications.