Twitter hints at predictive approach to spam

Micro-blogging site Twitter hinted Thursday at getting predictive against fake and spam tweets, following a complaint from an irate user. Twitter CEO Dick Costolo said they are trying to evolve their response from "reactive" to "realtime" and eventually to "predictive" in weeding out spam. "Yep, we're working on it. We are trying to migrate from 'reactive' to 'realtime' to 'predictive' on that front," he said in a tweet. He was replying to a tweet from user Peter Kafka, who complained they have to manually remove or filter spam from their accounts. "But since we're praising Twitter w/one hand - why do I have to filter out spam from accounts w/0 followers? Can't you guys handle?" Kafka had said. A separate article on tech site TheNextWeb said many fake spam Tweets come from robot-driven accounts, many of which have zero followers to their names. "Costolo’s Tweet seems to imply that they’re moving toward 'realtime,' which could be a method for identifying and dealing with spam accounts in a quicker manner. Perhaps some sort of better automated system for identifying spam accounts in real-time and suspending them," it said. But it said the "predictive" approach is the "really interesting bit." "Twitter isn’t telling at the moment but any improvements that Twitter can make to the way spam is currently handled would be welcome, because it’s becoming a bigger issue as the network’s user base grows and the potential for spammers to trick people into clicking links grows along with it," it said. — TJD, GMA News