Can Artificial Intelligence Help Fight Against Online Dating Scams?

Blinded by love, the online dating environment has seen most users fall prey to online scams, what is the role of artificial intelligence to this effect?

The Horrors of Online Dating Scams in Recent Years

Over the years, millions of people have turned to online dating with the hopes of finding love, unfortunately exposing them to the horrible schemes of fraudsters who come with the promise of love only to swindle them out of money.

According to recent research by the University of Warwick, most dating scams follow a predictable pattern. A fraudster creates a fake profile, makes a love connection with or offers free sex to an unsuspecting prey, and as soon as the victim falls in love with them, they proceed to make monetary or gift demands. In 2017, over 3000 online daters lost a collective sum of $14,600 and more to roam-cons, and most are often too embarrassed to make a report to the authorities.

Up until in recent times, no substantial efforts have been made to improve the state of current online dating/ matching algorithms to detect such fake accounts, but now, AI has come up with the promise of such, thus aiding law enforcement agencies to target these horrendous scammers.

The Role of Artificial Intelligence in Curbing Online Dating Scams

According to a February 2019 publication by the Engineering and Physical Sciences Research Council, dating apps and websites could soon use computing algorithms that ‘think’ like humans to pinpoint fake profiles designed to con victims. The most recent algorithm was developed by the University of Warwick and funded by the Engineering and Physical Sciences Research Council (EPSRC) and the Economic and Social Research Council (ESRC). Its primary task is to understudy the essential characteristics of a fake profile and apply that knowledge in detecting similar accounts on a given dating app.

However, the technology isn’t near perfect yet as shown by a recent demonstration of competency (see https://en-sg.datinginsider.net). In a recent trial operation, the algorithm produced a very low false-positive rate of around 1 percent. Hence, there a need to tighten the loose ends in future versions. While briefing on the importance of such technology, University of Warwick’s Prof. Sorell said: “Online dating fraud is a very common, often unreported crime that causes huge distress and embarrassment for victims as well as financial loss. Hence, Using AI techniques to help reveal suspicious activity could be a game-changer that makes detection and prevention quicker, easier and more effective, ensuring that people can use dating sites with much more confidence in future.”