{"id":60883,"date":"2018-05-12T17:05:42","date_gmt":"2018-05-12T15:05:42","guid":{"rendered":"http:\/\/www.reunion68.se\/?p=60883"},"modified":"2018-05-03T09:13:21","modified_gmt":"2018-05-03T07:13:21","slug":"25-05-24","status":"publish","type":"post","link":"https:\/\/www.reunion68.se\/?p=60883","title":{"rendered":"New algorithm identifies fake users on social networks"},"content":{"rendered":"
\"Israel21c\"<\/a>New algorithm identifies fake users on social networks<\/a><\/strong><\/span><\/h5>\n

Abigail Klein Leichman <\/strong><\/span><\/p>\n

\n

Israeli and American researchers develop generic method to detect fake accounts on most types of social networks, including Facebook and Twitter<\/strong>.<\/p>\n

Illustration by NiroWorld\/Shutterstock.com<\/em><\/p>\n

Fraudulent user profiles \u2013 bots \u2013 are a serious and growing concern on social media. By some estimates, as many as 48 million Twitter accounts and 270 million Facebook accounts are phony, designed for nefarious purposes from ruining reputations to influencing shoppers and voters.<\/span><\/p>\n

Now, researchers from Israel\u2019s Ben-Gurion University (BGU) of the Negev and from the University of Washington in Seattle say they have developed a generic method to detect fake accounts on most types of social networks, including Facebook and Twitter.<\/span><\/p>\n

According to their study published in the journal Social Network Analysis and Mining, the new method is based on the assumption that fake accounts tend to establish improbable links to other users in the networks.<\/span><\/p>\n

\u201cWith recent disturbing news about failures to safeguard user privacy, and targeted use of social media by Russia to influence elections, rooting out fake users has never been of greater importance,\u201d said Dima Kagan, lead researcher and a PhD student in BGU\u2019s department of software and information systems engineering.<\/span><\/p>\n

The algorithm consists of two main iterations based on machine-learning algorithms. The first constructs a link prediction classifier that can estimate, with high accuracy, the probability of a link existing between two users. The second iteration generates a new set of meta-features based on the features created by the link prediction classifier.<\/span><\/p>\n

These meta-features are used to construct a generic classifier that can detect fake profiles in a variety of online social networks.<\/span><\/p>\n

\u201cWe tested our algorithm on simulated and real-world data sets on 10 different social networks and it performed well on both,\u201d Kagan reported.<\/span><\/p>\n

\n
\n
\n