Every day a new page, post or video pop up with millions of like. Many of them are genuine but numerous of them are fake. The likes, comments everything is fake about those posts and pages.
So when the problem was clear that a lot of likes and comments on Facebook are not obtained through honest means, research was conducted on how to solve this.
A team of researchers worked on its solution that included Fareed Zaffar of LUMS, Shehroze Farooqi and Zubair Shafiq from The University of Iowa, and Nektarios Leontiadis from Facebook. These youngsters found that almost 1 million fake accounts generated 100 million fake likes and comments on Facebook.
The deduction by the team was this “a thriving ecosystem of large-scale reputation manipulation services on Facebook that leverage the principle of collusion. Collusion networks collect OAuth access tokens from colluding members and abuse them to provide fake likes or comments to their members.”
“Collusion networks” are not easy to detect because they are accounts that form a group to benefit each other by liking and commenting on one another’s posts. The post becomes popular while the content of the post is quite mediocre. The accounts that conduct such activity cannot be easily tracked as they mix up real and fake activity on the account.
This kind of scam is quite common on social media sites like Facebook and Twitter. They have millions of fake accounts and in order to control such scams, the sites should be able to detect which accounts are real and which are not. The research that has been conducted on this issue was published last Wednesday and it will be part of the Association for Computing Machinery Internet Measurement Conference on November 1, 2017.