Twitter Still Can't Keep Up With Its Flood of Junk Accounts, Study Finds (wired.com)

According to a new 16-month study of 1.5 billion tweets, researchers write that Twitter still isn't keeping up with the flood of automated accounts designed to spread spam, inflate follower counts, and game trending topics. Wired reports: In a 16-month study of 1.5 billion tweets, Zubair Shafiq, a computer science professor at the University of Iowa, and his graduate student Shehroze Farooqi identified more than 167,000 apps using Twitter's API to automate bot accounts that spread tens of millions of tweets pushing spam, links to malware, and astroturfing campaigns. They write that more than 60 percent of the time, Twitter waited for those apps to send more than 100 tweets before identifying them as abusive; the researchers' own detection method had flagged the vast majority of the malicious apps after just a handful of tweets. For about 40 percent of the apps the pair checked, Twitter seemed to take more than a month longer than the study's method to spot an app's abusive tweeting. That lag time, they estimate, allows abusive apps to cumulatively churn out tens of millions of tweets per month before they're banned.

The researchers say they've been sharing their results with Twitter for more than a year but that the company hasn't asked for further details of their method or data. When WIRED reached out to Twitter, the company expressed appreciation for the study's goals but objected to its findings, arguing that the Iowa researchers lacked the full picture of how it's fighting abusive accounts. "Research based solely on publicly available information about accounts and tweets on Twitter often cannot paint an accurate or complete picture of the steps we take to enforce our developer policies," a spokesperson wrote.

Comments

Can't?

[Areyoukiddingme]

Won't. Twitter knows. Twitter is carefully ignoring them for a precisely calibrated length of time designed to hide just how few actual unique humans use Twitter.

"Research based solely on publicly available information about accounts and tweets on Twitter often cannot paint an accurate or complete picture of the steps we take to enforce our developer policies," a spokesperson wrote.

Also, they're getting paid. Publicly available information does not include how much they're getting paid for allowing those accounts. So the spokesperson spoke the technical truth. The best kind of truth.

What is the motivation? Cheap credibility!

[shanen]

Question: What is the underlying motivation for creating fake Twitter accounts?

Answer: Cheap credibility. A fresh sock puppet looks just about the same as any other identity on Twitter.

Yes, there's a slight advantage to the accounts with the little blue checked circle, but not much considering the sock puppets can use similar names and there will be plenty of fools who overlook the circle that isn't there.

The generalized solution approach is to reduce the value of the fake accounts. One way to do that would involve MEPR (Multidimensional Earned Public Reputation) as a way to render most identities much less visible until AFTER they earned some more credibility. One of the dimensions should be age, by the way. If the fake accounts start at 0 on all dimensions, but the visibility threshold is just slightly above 0, then they have disappeared (except to each other or to people who want to change the defaults to play with them).

MEPR should be an opt-in metric, of course, though even that is kind of complicated. The degree of participation should be controllable, but essentially you should be able to earn visibility by being a nice person and lose it for being a troll. It might even motivate some people to be nicer to become more visible, eh?

Anyway, enough time spent for now, so I bid you the usual ADSAuPR, atAJG.