The heart of tech is coming to the heart of the Mediterranean. Join TNW in València this March 🇪🇸

This article was published on August 11, 2011

Twitter to get real time and “predictive” with spam control

Twitter to get real time and “predictive” with spam control

Spam is a huge problem on Twitter. Some days you can’t mention the word “iPad” or use a hashtag without getting flooded with unhelpful and obviously fake spam Tweets from robot-driven accounts. Many of those accounts are obviously spammers as well, with 0 followers to their names.

Well, rest assured that Twitter understands spam is a problem and is working on it. Twitter CEO Dick Costolo Tweeted this response to a complaint by Peter Kafka about spam on Twitter:

Yep, we’re working on it. We are trying to migrate from “reactive” to “realtime” to “predictive” on that front.

Now, a reactive role is pretty easy to define. Currently Twitter users can report spam accounts right on by choosing the “Report spam” option on an account’s profile.

Once the account hits a certain threshold of complaints, it is suspended or removed, thereby killing off one spammer. Twitter is known to do this in batches, with a ‘spam purge’ of thousands of reported accounts resulting in a loss of somewhere between a few and several hundred spam accounts disappearing from users followers.

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.

But the really interesting bit is the “predictive” part. Perhaps a database of spam phrases and accounts that Twitter uses to identify spammers and deletethem automatically? A better way to vet users as actual humans before letting them sign up for accounts in the first place? A method for tying trends in with an internal spam search routine that monitors hot topics for spam and uses spikes in Twitter traffic to weed out the fake accounts?

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.

PeekYou CEO Michael Hussey estimates that only 35% of the average Twitter users followers are actually real people Update: Hussey has been in touch to clarify that “real people” on twitter is in fact between 30% to 60% and defined as accounts with “real names, locations etc.” This means that if Twitter deleted all of the spam accounts on Twitter today, it could leave it with 40%-70% fewer registered users. With Facebook already past the 800 million user mark, it would leave Twitter trailing some margin, based on the estimate of 200 million current Twitter users.

But we know from Costolo’s recent talk to Fortune that the number of accounts on Twitter isn’t a primary concern to him, it’s total visitors that matters because many users don’t even have accounts and use Twitter primarily as a news source.

Twitter even states on its about page that you don’t have to Tweet to get things out of Twitter. “You can contribute, or just listen in and retrieve up to the second information. Some people never tweet, they simply use Twitter as a way to get the latest information on their interests.”

What do you think? Is Twitter spam a big problem for you, and if so, what do you think would be the best way to fight it?

We’ve reached out to Twitter for further comment about their efforts to fight spam but they have not replied as of this posting.