Police get lie detectors to test written statements

The world’s first lie detector test for written statements has been developed by British and Spanish experts to weed out untrue claims, and avoid wasting police time.

The system uses a combination of automatic text analysis and machine learning to scan documents and identify false robbery reports in eight out of 10 cases.

Called VeriPol, it was developed by researchers at Cardiff University and Charles III University in Madrid and is already being used by Spanish police.

The program was fed robbery reports that were known to be false so that it could learn to spot patterns.

It found that false statements tended to be shorter, lacked precise detail, and were more focused on the stolen property — rather than the whole incident.

Information about the attacker was often scant, while there was usually a lack of witnesses and other hard evidence to corroborate the story.

In most cases claimants had not contacted police or a doctor immediately after the incident.

“Our model began to identify false statements where it was reported that incidents happened from behind or where the aggressors were wearing helmets,” said co-author of the study Dr Jose Camacho-Collados, from Cardiff University’s School of Computer Science and Informatics.

“Similarly, other clear indicators of falsehood were descriptions of the type of objects stolen. References to iPhones and Samsung were associated with false claims, whereas bicycles and necklaces were correlated with true reports.”

Researchers hope that it will save police time and money.

The system was trialled in Murcia and Malaga in Spain in June last year. In one week, 25 cases of false robbery reports were detected in Murcia, resulting in the cases being closed, and a further 39 were detected and closed in Malaga.