Researchers from Israel’s Ben-Gurion University of the Negev and University of Washington, Seattle have developed a method to detect fake accounts on social networks such as Facebook and Twitter.

Fake users, like fake news, create enough headache for social media companies, their genuine users and even policymakers.

“Rooting out fake users has never been of greater importance,” says Dima Kagan, who led the study, citing the recent user privacy scandal involving social media networks.

Kagan is with the Department of Software and Information Systems Engineering at Ben-Gurion University. The new method, according to a study published in the latest issue of Social Network Analysis and Mining , works on the assumption that fake accounts tend to establish “improbable links” to other users in the networks.

The process consisted of two main “iterations” (set of commands that repeat) based on machine-learning algorithms.

The first set of commands built a “link prediction classifier” that accurately estimated whether two particular users were linked, or not. Based on this link, a second set of commands created new meta-features which researchers then used to build a generic classifier that can detect fake profiles on social networks.

Facebook itself has more than 200 million fake accounts, according to reports, and the platform has admitted its helplessness in tracking these fake accounts and removing them, especially in developing markets such India, Indonesia and the Philippines where the share of spurious is meaningfully higher than the developed world. Reports suggest nearly 15 per cent (about 48 million) of Twitter’s active users are automated (fake) accounts. Creating fake users is a booming business across the globe. The researchers tested the algorithm on 10 different social networks and it “performed well” on both simulated and real-world situations. The researchers said the method outperformed other similar tools and could enhance cyber security applications.

Earlier, the researchers from Ben-Gurion University had developed a Social Privacy Protector that social media users could use to evaluate their friends list and identify fake profiles — all in a matter of seconds.