Computers can be programmed to measure boredom or interest by watching people fidget, a study has found.

The findings could pave the way for “empathic” robots or online teachers that can tell when a pupil is not paying attention, say scientists.

Researchers showed that boredom levels can be assessed by measuring “non-instrumental” small body movements – in other words, fidgeting.

• Samsung launches next generation S7 phones
• The best mobile phone video games of 2016
• ABC slammed for ‘scientifically bankrupt’ report

When people are thoroughly absorbed in what they are watching or doing, they tend to fidget less.

Lead scientist Dr Harry Witchel, from Brighton and Sussex Medical School, said: “Our study showed that when someone is really highly engaged in what they’re doing, they suppress these tiny involuntary movements. It’s the same as when a small child, who is normally constantly on the go, stares gaping at cartoons on the television without moving a muscle.”

He said the discovery could have a significant impact on the development of artificial intelligence.

Potential future applications included the creation of online teaching schemes that adapt to students’ level of interest and attempt to re-engage them if they show signs of boredom.

Empathic companion robots were another possibility. The technology could also be used to give movie directors or game makers an idea of how interesting or dull people think their creations are, said Dr Witchel.

In the study, 27 participants were faced with three-minute computer sessions that ranged from fascinating games to tedious readings from EU banking regulations.

At the same time, video motion tracking technology was used to measure their movements.

For two comparable reading tasks, the one that was most engaging resulted in a 42 per cent fidgeting reduction.

The results are published in the journal Frontiers in Psychology.

-AAP