Recommendations drive significant amount of viewership: YouTube

New Delhi, October 20

YouTube on Wednesday said recommendations drive a significant amount of the overall viewership on the platform and the video streaming company is focussed on minimising the chances of viewers seeing “problematic content”.

YouTube Vice President Engineering Cristos Goodrow said YouTube has built out ‘Recommendations’ on the simple principle of helping people find the videos they want to watch and that will give them value.

Viewers find these recommendations at work in two places — the “homepage” that appears when one first opens YouTube, displaying a mixture of personalised recommendations, subscriptions, and the latest news and information and secondly, in the “Up Next” panel that appears when one is watching a video.

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

Goodrow also emphasised that viewers have controls to manage what and how much they want to share to get a personalised experience on YouTube, and viewers who do not want personalised recommendations can choose to delete watch history.

“Today, Recommendations drive a significant amount of the overall viewership on YouTube, even more than channel subscriptions or search. And, we are thinking about it in a responsible way. Our goal is to help connect viewers to high-quality information by minimizing the chances of them seeing problematic content,” Goodrow said.

He added that YouTube’s goal is to have views of borderline content from recommendations below 0.5 per cent of overall views on YouTube.

Goodrow said people also visit YouTube for News and Information, and its recommendations are built keeping all kinds of audiences in mind.

Through the years, YouTube has used recommendations to reduce low-quality content from being widely viewed, built out classifiers to identify and prevent racy/violent videos from being recommended, started to demote sensationalist content, removed any video that showed minors in risky situations, and further expanded the way the recommendation system is used to reduce problematic misinformation and borderline content, he noted. —PTI