Image from Wikimedia Commons
YouTube has started relying heavily on machine learning (ML) technology to review & block “violative videos”. It revealed this as part of its announcement on how YouTube was going about enforcing community guidelines.
“….Machines are allowing us to flag content for review at scale, helping us remove millions of violative videos before they are ever viewed. And our investment in machine learning to help speed up removals is paying off across high-risk, low-volume areas (like violent extremism) and in high-volume areas (like spam),” it said in a blog post.
Every quarter now, YouTube will release a quarterly report on how it was enforcing its Community Guidelines. By the end of the year, it plans to refine reporting systems, & add additional data, including data on comments, speed of removal, & policy removal reasons.
Also revealed was the Reporting History dashboard that each YouTube user can individually access to see the status of videos they’ve flagged to us for review.
Highlights from the report — reflecting data from October – December 2017 — show:
- Over 8 million videos were removed from YouTube during these months. The majority of these were mostly spam or people attempting to upload adult Content – & represent a fraction of a percent of YouTube’s total views during this time period.
- 6.7 million were first flagged for review by machines rather than humans
- Of those 6.7 million videos, 76% were removed before they received a single view.
Click here to read up the rest of the post.