File photo of Jack Dorsey, co-founder and chief executive officer of Twitter, as he attends the annual Allen & Company Sun Valley Conference, July 6, 2016 in Sun Valley, Idaho. Every July, some of the world’s most wealthy and powerful businesspeople from the media, finance, technology and political spheres converge at the Sun Valley Resort for the exclusive weeklong conference. (Drew Angerer/Getty Images)
@Siliconeer #Siliconeer @Twitter #Twitter #Tech –Twitter has started using a trendy type of artificial intelligence to figure out which tweets to show on the timeline of its over 300 million monthly active users.
The popular micro-blogging site is evaluating and scoring thousands of tweets per second to determine what is worth recommending on timelines, taking into consideration an increasing number of factors, including whether tweets contain images or videos, the number of retweets and likes, and your previous interactions with other account holders, Twitter software engineers Nicolas Koumchatzky and Anton Andryeyev wrote in a blog post, CNBC news reported.
Tech giants like Facebook, Google and Microsoft among others have previously attempted to improve various products using deep learning, a trendy type of artificial intelligence (AI), the report said, May 9.
The San Francisco-headquartered company, for its 313 million monthly active users, has brought on talented people of this area through acquisitions of companies such as Magic Pony, and it has open-sourced some of its deep learning software. But the company has not been especially transparent about its progress.
A year ago Twitter introduced a so-called algorithmic timeline that ranked tweets based on relevance instead of them being in reverse chronological order, the report said.
The feature is on by default, and users can opt out to revert to the classic timeline style, but Twitter has also introduced various widgets near the top of users’ reverse- chronological timelines to show off tweets that it thinks users might like or might have missed, it said.
Before putting the deep learning system into production recently, Twitter was using less computationally intensive machine learning methods such as decision trees and logistical regression, Koumchatzky and Andryeyev wrote.