The researchers used machine-learning techniques to analyse 120 video clips of actual trials. Based on the outcome of those trials, they knew which witnesses were (presumably) lying when they were on the stand.

75 per cent accurate

It was determined that liars were more likely to do things such as look directly at the questioner or say ‘I’. Running algorithms based on that data, the software subsequently analysed videos of people, half of whom were lying. It was able to identify the liars with 75 percent accuracy; considerably better than the 50 percent managed by human test subjects.

Effective tool in law

Technology of this sort is being honed to include metrics such as the breathing and heart rate of those giving evidence using thermal imaging, which allows for non-contact. It is hoped that once developed further, the software could become an effective lie-detection tool in fields such as law, security and mental health. Sources: Engadget; Gizmag