Twitter has become surprisingly efficient when it comes to dealing with spam, fake accounts and malicious automation.
Not so long ago it felt like every second follower you gained was a bot but that’s happening less and less thanks to Twitter’s efforts. In May of this year for instance, the micro-blogging site identified and challenged 9.9 million potentially spammy or automated accounts per week. For perspective sake, Twitter was only doing this to 6.4 million accounts per week in December 2017.
The firm’s goal is to preemptively stop spam or automated accounts in their tracks before they can make their way into the greater Twitter community.
“We focus on developing machine learning tools that identify and take action on networks of spammy or automated accounts automatically. This lets us tackle attempts to manipulate conversations on Twitter at scale, across languages and time zones, without relying on reactive reports,” the firm wrote in a blog post.
And machine learning appears to be working. Twitter reports that removal of accounts for violating its spam policies is up 214 percent year-on-year and in addition reports of spam from users is down 10 percent from 25 000 per day in March to 17 000 per day in May.
Buying likes and followers?
With influencers being the marketing platform of choice in 2018 having a strong following is important to brands which is why some folks might be tempted to buy likes, followers, retweets etc.
But Twitter is taking action against this – in a roundabout way.
Accounts suspected of of spamming the social network or sharing malicious content are put into a “read only” state prevent the account from tweeting or engaging with other accounts. The account is then challenged by Twitter via a request for a phone number for instance, if the account passes the challenge normal service is resumed, if it doesn’t well then goodbye spam account.
So how does this impact folks buying followers? Twitter explains, “As a result of these improvements, some people may notice their own account metrics change more regularly. But we think this is an important shift in how we display Tweet and account information to ensure that malicious actors aren’t able to artificially boost an account’s credibility permanently by inflating metrics like the number of followers.”
But Twitter is content with just policing the halls it also wants to make it harder for malicious accounts to enter the door in the first place.
Moving forward, all new accounts will be required to confirm an email address or phone number at signup.
This along with regular audits of existing accounts and a focus on improving machine learning should mean that before long being followed by bots is a thing of the past, hopefully.