4 min read

In the real world, a person having multiple identities is said to have Dissociative identity disorder (DID); but what about the virtual world? Social media sites such as Facebook, Twitter, and so on have an equal number or even more fake identity profiles than real ones. It has set out on a mission to excise these fake and suspicious profiles from its platform. The committee plans to depreciate 214% more accounts on a yearly basis for violating its spam policies.

Source: Twitter blog

Twitter initiated this drive to improve the authenticity of conversations on the platform. It also aims to ensure users have access to information that is highly credible, relevant, and of a high-quality. Following this, it started off its battle against the fake profiles and has been constantly suspending fake accounts which are inauthentic, spammy or created via malicious automated bots.

Instead of waiting for people to report on these accounts, the company is proactively dodging across problematic accounts and observing their behavior by using machine learning tools. These tools identify spam or automated accounts and automatically take necessary actions.

Some plans Twitter has, to avoid fake account creation, include:

Enabling a read-only mode to reduce visibility of suspicious accounts

It plans to monitor the behaviour of every profile and update its account metrics in near-real time. This will help in knowing the number of followers an account has, or the number of likes or Retweets a Tweet receives, and so on. The account may even be converted into a read-only mode, if found behaving suspiciously. The account will be removed from follower figures and engagement counts until it has passed a challenge of conforming the account with a phone number. A warning is displayed against such read-only accounts to prevent new accounts from following it. Once the account passes the challenge, its footprint is restored.

Improving Twitter’s sign-up process

Twitter will make it all the more difficult for spam accounts to register for an account. The new accounts will also have to confirm either an email address or phone number when they sign up to Twitter. It also plans to working closely with its Trust and Safety Council and other expert NGOs to ensure this change does not affect people working in a high-risk environment where anonymity is necessary. This process would be rolled-out later this year.

Auditing existing accounts for signs of automated sign-up

It is also conducting an audit to secure a number of legacy systems used to create accounts. This process will ensure that every account created on Twitter passes some simple, automatic security checks designed to prevent automated signups. The new protections Twitter has recently developed as a result of this audit have already aided them in preventing more than 50,000 spam sign-ups per day.

Malicious behavior detection systems being expanded

They are also planning to automate some processes where suspicious account activity is detected by the behavior detection systems. Activities such as exceptionally high-volume tweeting using the same hashtag, or the same @username without a reply from the account. These tests vary in intensity, and may simply request the account owner to complete a simple reCAPTCHA process or a password reset request. Complex cases are automatically passed to the team for review.

Twitter has fastened its seat belt and won’t stop until it takes down all the fake accounts from its platform. While this move is bold and commendable for a social network platform given the steep rise in fake news and other allied unsavory consequences of an ever-connected world, Twitter’s investors did not take it well. The company shares fell to around 9.7% on Monday, after it announced that it is suspending more than 1 million accounts a day.

As per a Twitter statement, the account suspension doubled since October last year. Many speculate that this is a response to the congressional pressure the platform has been receiving regarding the alleged Russian fake accounts found on Twitter to interfere with the U.S elections held last year. The number reached around 7 million in May and June, and a similar pace continues in July. Though this move raises serious concerns around their falling user growth rate, this is an important step for the organization to improve the health of their social platform.

Chief Financial Officer, Ned Segal, tweeted, “most accounts we remove are not included in our reported metrics as they have not been active on the platform for 30 days or more, or we catch them at sign up and they are never counted.”

I, for one, ‘like’ Twitter’s decision. Minor inconveniences are a small price to pay for a more honest commune and information sharing.

Read more about this news on The Washington Post’s original coverage.

Read next


A Data science fanatic. Loves to be updated with the tech happenings around the globe. Loves singing and composing songs. Believes in putting the art in smart.


Please enter your comment!
Please enter your name here