CYBER-CHEATS be warned. People who lie in their e-mails and text messages face being rumbled by new “truth detection” software being developed by researchers.

The academics have analysed tens of thousands of electronic messages and claim to have identified telltale signs that show if a person is being economical with the truth.

The software could one day enable bosses to discover if staff are feigning illness to avoid coming to work, while husbands who claim to be stuck at the office when they have gone to the pub risk being caught out the moment they press “send”.

The academics behind the software — which could be commercially available from next year — say it has also attracted the interest of law enforcement agencies.

Police believe it could help trap online fraudsters and make it easier to identify internet paedophiles who pose as youths to groom victims in chat-rooms or on social networking websites.

British internet users spend an average 30 minutes a day managing their inbox, according to a recent poll, with e-mails now routinely replacing telephone conversations and face-to-face meetings.

The lie-detection software is being developed by a team led by Jeff Hancock, director of the Computer-Mediated Communication Research Laboratory at Cornell University in New York state.

Unlike a conventional lie detector, which looks for physiological signs of anxiety such as a quickening pulse, the so-called “digital polygraph” scans the contents of an e-mail or mobile phone text message for specific word patterns.

“There are certain cues that appear when someone is lying in an e-mail,” said Hancock, whose team has been awarded a £346,000 grant by the American authorities.

“We’ve had people come into the labs and write us a deliberate lie, and then tell us, and we’ve had some people come in and tell us the deliberate truth. Using this method, we’ve built up a database of tens of thousands of e-mails.”

Hancock has identified five basic indicators to determine whether a person is likely to be lying or telling the truth, with tests so far showing accuracy ratings of up to 70%.

One of the main giveaways is the length of a message. E-mails that mask a lie have, on average, 28% more words than truthful messages. “When you’re lying, you are trying to give a credible story so you provide more detail, you are in persuasive mode,” said Hancock.

Liars are also more likely to use third-person pronouns, such as “they” and “he”, in a bid to distance themselves from a lie because of the guilt associated with it.

“People also tend to use negative emotional terms because they feel uncomfortable when they are lying,” said Hancock. “So they tend to use terms like ‘sad’, ‘angry’, ‘unhappy’ and ‘stressed out’.”

Another telltale sign of a fib is the overuse of “sense terms”, such as “see”, “feel” and “touch”, which Hancock believes are employed to build up an elaborate and evocative account of a scenario that may never have happened.

Finally, liars tend to use fewer “causal phrases” to minimise the chances of being caught out.

So, for example, a person conducting an illicit affair is less likely to say they were unable to get home early last night because they were with someone else. “They will just say, ‘Sorry, I couldn’t meet you’ and be deliberately vague,” said Hancock.

Previous research by the University of Central Lancashire has shown that up to one-third of communications at work involve some degree of deception. The most common work-place lie is faking a “sickie”.

Hancock has claimed people lie in a quarter of all social interactions, but he concedes they are far more likely not to tell the truth over the phone than on e-mail — because there is no written record of the exchange.

Several insurance companies are now using lie detectors to spot fraudulent claims and even the Department for Work and Pensions has expressed an interest in voice-stress analysis technology to combat benefit cheats.

Dr Peter Collett, a psychologist who has written a book on lying, is sceptical about Hancock’s claims. “The thing about lying is that a lot of it can be picked up from body language when you talk, it’s got something to do with the timing, the pacing and the actual utterances,” he said. “How can you get software to spot all this? With e-mails you are just left with lexical patterns.”

Explore UK News

• Crime News

• Education News

• Health News

• Science News

• Scotland News

Times Recommends

• Swine flu vaccine for all as drug rushed through
• Artificial sperm and the race to build a baby
• BBC jets out stars to tout for prizes