University of California, Riverside researchers have developed MyPageKeeper, an application for detecting spam and malware posts on Facebook users' walls, which they say is highly accurate, fast, and efficient.
The researchers also have introduced the term "socware" to describe a combination of social malware, encompassing all criminal and parasitic behavior on online social networks. The researchers found that MyPageKeeper flagged 97 percent of socware during a four-month testing phase that involved more than 40 million posts from 12,000 MyPageKeeper users. The researchers also found that it took just 0.0046 seconds to classify a post.
"This is really the perfect recipe for socware detection to be viable at scale: High accuracy, fast, and cheap," says Riverside professor Harsha V. Madhyastha.
The app works by continuously scanning the walls and news feeds of subscribed users, identifying socware posts and alerting the users. The researchers say the app's primary novelty is that it factors in the social context of the post, which includes the words in the post and the number of likes and comments it received. They also note that users are unlikely to like or comment on socware posts because they add little value.
From UCR Today
View Full Article
Abstracts Copyright © 2012 Information Inc., Bethesda, Maryland, USA
No entries found