San Francisco, June 27: To address the problem of increasing spam accounts and trolls on its platform, Twitter has introduced tough policies that will soon see some users losing fake followers globally.

In May, Twitter identified and challenged more than 9.9 million potentially "spammy" or automated accounts per week -- up from 6.4 million in December and 3.2 million in September 2017.

Twitter said late Tuesday that it will take further action to challenge a large number of suspected spam accounts globally.

As a result of these improvements, some people may notice their own account metrics change more regularly. 

"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," Twitter said in a blog post.

Some people may see their follower counts drop but this does not mean they did anything wrong, the company said.

To make it harder to register spam accounts, Twitter will now require new accounts to confirm either an email address or phone number when they sign up to the platform. 

"This is an important change to defend against people who try to take advantage of our openness," Twitter said in a blog post.

"Due to technology and process improvements during the past year, we are now removing 214 per cent more accounts for violating our spam policies on a year-on-year basis," it added.

Twitter saw a drop in the average number of spam reports -- from an average of approximately 25,000 per day in March, to approximately 17,000 per day in May.

"We've also seen a 10 per cent drop in spam reports from search as a result of our recent changes. These decreases in reports received means people are encountering less spam in their timeline, search, and across the Twitter product," the company said.

Twitter currently has 330 million user accounts.

"We're also moving rapidly to curb spam and abuse originating via Twitter's APIs. In Q1 2018, we suspended more than 142,000 applications in violation of our rules -- collectively responsible for more than 130 million low-quality, spammy tweets," the blog post said.

To reduce the visibility of suspicious accounts in Tweet and account metrics, the company said it has started updating account metrics in near-real time.

"For example, the number of followers an account has, or the number of likes or Retweets a Tweet receives, will be correctly updated when we take action on accounts," it added.

Twitter is also automating some processes where it sees suspicious account activity, like exceptionally high-volume tweeting with the same hashtag, or using the same @handle without a reply from the account a user has mentioned.

Twitter said it will continue to invest in leveraging Machine Learning (ML) technology and partnerships with third parties.

Let the Truth be known. If you read VB and like VB, please be a VB Supporter and Help us deliver the Truth to one and all.



Thiruvananthapuram (PTI): The body of a 37-year-old nurse from Kerala who died in the Ahmedabad flight disaster was brought back to her home state on Tuesday morning.

Ranjitha, a native of Pathanamthitta district, was working in the UK when the incident occurred. Her mortal remains were identified through a DNA test.

Her body arrived at the international airport in Thiruvananthapuram around 7 am.

Kerala ministers V Sivankutty and G R Anil were among the officials who paid their last respects.

Senior political leaders, including CPI(M) general secretary M A Baby and Congress veteran Thiruvanchoor Radhakrishnan, also offered tributes.

The coffin was later taken to her village, where it will be kept at a school in Pullad for the public to pay their respects.

Her brother and a close relative accompanied the body on its final journey.

Cremation is expected to take place on the premises of her family home later in the evening.

Ranjitha, a mother of two, was remembered as a dedicated nurse who had worked outside the state for several years to support her family.