YouTube on Wednesday reiterated the importance of having a ‘recommendation system’ in place. The video streaming platform said that the consumption of borderline content through its recommendation is significantly below 1 per cent.

Borderline content refers to violent content which is right on the line of violating community guidelines. The company added that it began demoting borderline content in 2019, which led to 70 per cent decrease in watch time of non-subscribed borderline content in the US.

‘YouTube is very focussed on creators’

Launched in 2008, YouTube’s recommendation system was created to rank videos based on their popularity. Users today get to see this system at work on their homepage which displays a mixture of personalised recommendations, subscriptions, the latest news and information; and the ‘Up next’ panel which shows related content to the video you are viewing.

The company said it does not connect with viewers through social network and instead relies on the accuracy of the predictions of its recommendation engine. Users also get to choose and manage whether they want personalised recommendations by deleting watch history.

High-quality information

Cristos Goodrow, VP Engineering, YouTube, said, “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 minimising the chances of them seeing problematic content. Our goal is to have views of borderline content from recommendations below 0.5% of overall views on YouTube.”

YouTube adds new ways to improve searching on the platform

“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,” the company said in a statement.

comment COMMENT NOW