Can tools be developed to detect lies in humans? Thinking about answering this question may have seemed insane years ago, but after the rapid revolution of artificial intelligence, these tools could be available in the near future.
Researchers in Japan have been working on improving lie detection and deception detection systems using machine learning, according to a study published last April in the “Artificial Life and Robotics” journal and reported by “PSYPOST” website.
Machine learning is a part of artificial intelligence, using algorithms and statistical models to enable computers to learn without direct programming.
In another way, this is a method for teaching computer systems how to perform specific tasks based on learning from data, patterns, and examples, rather than relying on predefined rules.
Detecting deception can be crucial in various contexts, such as interrogating victims or suspects in criminal cases, conducting interviews with patients suffering from mental health issues, or even in recruitment processes.
The aim was to create a fair and accurate system to help interviewees to be truthful and identify suspects correctly without falsely accusing the innocent.
Researchers in Japan focused on using facial expressions and heart rates to identify potential deception in humans. In the study involving 4 male graduate students, the results showed high accuracy rates.
The results included some common signs that the machine used to detect deception, such as changes in heart rate, eye movements, specific areas around the eyes and mouth on the face.
Researchers believe that the machine learning system they rely on could be a valuable tool for detecting deception in human interactions.
Related
