Cambridge University boffins have begun exploring an alternative to the traditional polygraph approach to detecting liars and cheats.
Instead of calculating variations in a person's respiration, pulse and sweat production, the fib-detecting tech looks at the subject's body movements. As a first stage in investigating the approach, researcher Sophie van der Zee put 90 pairs of volunteers in motion capture suits before asking them to interview each other. Half the interviewees were told to lie.
Early tests suggested it was possible to detect the difference between deception from mimicry achieved results equivalent to conventional polygraphs. Computer scientists at Cambridge University are confident that results can be improved and that unconscious fidgeting offers a better "tell" for lying than elevated heart-rate or other physiological indicators, as a post by Cambridge University Computer Laboratory's Light Blue Touchpaper blog by Professor Ross Anderson explains.
We found that total body motion was a reliable indicator of guilt, and works about 75 per cent of the time. Put simply, guilty people fidget more; and this turns out to be fairly independent of cultural background, cognitive load and anxiety – the factors that confound most other deception detection technologies. We believe we can improve that to over 80 per cent by analysing individual limb data, and also using effective questioning techniques (as our method detects truth slightly more dependably than lies).
A paper (PDF) - To freeze or not to freeze: A motion-capture approach to detecting deceit - on the research is due to be published at the Hawaii International Conference on System Sciences (HICSS). The research went beyond previous tests that looked at s fidgeting or looking away, as an abstract for the paper explains.
Building on previous work that uses automatic analysis of facial videos and rhythmic body movements to diagnose stress, we set out to see whether a full body motion capture suit, which records the position, velocity and orientation of 23 points in the subject’s body, could yield a better signal of deception.
Furthermore, movement was guilt-related, and occurred independently of anxiety, cognitive load and cultural background. Further analyses indicate that including individual limb data in our full body motion measurements, in combination with appropriate questioning strategies, can increase its discriminatory power to around 82 per cent
Further work will include building a revised system using low-cost commodity hardware instead of expensive full body suits.
Various techniques to beat conventional polygraphs, which have been in use for close to 100 years, have been suggested. Anderson suggests body movements characteristic of someone telling the truth would be harder to fake.
"A guilty man can always just freeze, but that will rather give the game away; we suspect it might be quite hard to fidget deliberately at exactly the same level as you do when you’re not feeling guilty," Anderson writes. ®