Home Business amount Recommendations generate a significant number of views: YouTube

Recommendations generate a significant number of views: YouTube



YouTube said Wednesday that the recommendations are generating a significant share of the platform’s overall audience and that the video streaming company is focused on minimizing the chances that viewers will see “problematic content.”

YouTube vice president of engineering Cristos Goodrow said YouTube has come up with “recommendations” on the simple premise of helping people find the videos they want to watch that will make them valuable.

Viewers find these recommendations at work in two places: the ‘home page’ that appears when you first open YouTube, displaying a mix of personalized recommendations, subscriptions and the latest news and information, and second, in the “To be continued” panel that appears when watching a video.

He noted that the success of YouTube’s recommendations depends on accurately predicting which videos the viewer wants to watch, based on their own interests and preferences, and not on who they are connected with, as it may be. be the case with social media platforms.

Goodrow also pointed out that viewers have controls to manage what they want to share and how much they want to share to get a personalized experience on YouTube, and viewers who don’t want personalized recommendations can choose to delete the viewing history. .

“Recommendations today generate a significant portion of the overall YouTube audience, even more than channel subscriptions or search. And we think about it responsibly. Our goal is to help viewers access high quality information while minimizing the chances of them seeing problematic content, ”said Goodrow.

He added that YouTube’s goal is to have limit content views from recommendations below 0.5% of overall YouTube views.

Goodrow said people also visit YouTube for news and information, and its recommendations are designed with all kinds of audiences in mind.

Over the years, YouTube has used recommendations to reduce the delivery of low-quality content, created classifiers to identify and prevent racy / violent videos from being recommended, began downgrading sensationalistic content, removed any video showing offensive content. minors in risky situations, and has further expanded how the referral system is used to reduce problematic misinformation and borderline content, he noted.

(This story was not edited by Devdiscourse staff and is auto-generated from a syndicated feed.)



Please enter your comment!
Please enter your name here