Have you ever been catfished or trolled by a fake account on Facebook? Or maybe you’re even guilty doing this?
Well, the social media giant is putting an end to this. It has deleted more than 6.5 billion fake accounts in 2019 using a programme designed to sniff out frauds.
The programme is called Deep Entity Classification’ (DEC), a computer program equipped with machine-learning capabilities that analyzes user accounts for potential fakes.
The programme works by monitoring the activity of a potentially fraudulent user.
It analyzes the number of other accounts the fake account is connected to, as well as whatever groups and pages they may have liked or followed.
It then maps out similar data for each person in the account’s friends list. And then evaluate their daily activity for potential evidence of fraud, such as sending the same link to a promotional sale on sunglasses to hundreds or thousands of people.
The overall idea is to not just evaluate individual accounts, but look at how they interact with their presumptive friends, and in-turn consider how those friends interact with their own groups.
Facebook currently has over 2.89 billion monthly users, and it estimates that five per cent of this are fakes.