[ad_1]
Law enforcement agencies in Spain have adopted an artificial intelligence (AI) system capable of detecting false crimes and theft.
Researchers from Cardiff University and Charles III University of Madrid have come up with the AI system, dubbed VeriPol, which uses automatic text analysis and analysis. machine learning to identify misrepresentations.
According to computer scientists, VeriPol is able to identify false flight reports "with an accuracy of over 80%."
Although filing false statements is often considered a criminal offense, when it comes to robbery, a claim may be made to insurance providers to fraudulently benefit from a policy.
Budgets and law enforcement personnel are often solicited and so it can be difficult to prove that a suspicious statement is false – and to find both the time and the resources needed.
CNET: A portrait manufactured by Christie's auctioned AI for $ 432,500
The artificial intelligence tool is capable of analyzing written statements to recognize features generally associated with misrepresentations, such as the type of allegedly stolen objects, descriptions of alleged perpetrators and "details" of an incident, said the team.
Themes that often indicated a false report focused on stolen objects rather than the incident itself; a lack of detail that suggests that the journalist is not really using his memory; limited details about the aggressor, the lack of witnesses and the lack of contact with law enforcement – or a health professional – immediately after.
High-end technology items such as iPhones and Samsung smartphones were often associated with false reports, while jewelry and bikes were often linked to legitimate cases of theft.
VeriPol uses what is called natural language processing, an element of machine learning technologies that helps artificial systems understand and interpret the natural use of human language. Algorithms are used to decode this language and VeriPol's understanding is based on historical police reports that have been introduced into the system.
TechRepublic: Top 5: What to Know About AI
The researchers believe that the tool could help police support staff to choose the best ways to use resources and determine when more in-depth investigation is needed. In addition, VeriPol can deter members of the general public from filing false returns, saving agencies time and money.
See also: Meeting with Norman, the world's first "psychopathic" AI
VeriPol has been deployed in the police forces in Spain. A lawsuit launched by the Spanish National Police has used VeriPol to examine more than 1,000 police reports, in which the tool could detect a false report eight times out of 10.
"Our study gave us a fascinating insight into how people lie to police and a tool that can be used to deter people from doing so in the future," said Dr. Camacho-Collados, co – author of the study. "In the end, we hope that by showing that automatic detection is possible, it will deter people from lying to the police in the first place."
The study was published in the academic journal Knowledge-Based Systems.
Previous and related coverage
Source link
