On YouTube’s recommendation system
blog.youtube
Survey Responses: To really make sure viewers are satisfied with the content they’re watching, we measure what we call “valued watchtime”—the time spent watching a video that you consider valuable. We measure valued watchtime through user surveys that ask you to rate the video you watched from one t
5 Users
1 Comments
45 Highlights
2 Notes
Summary
- 📈 **Recommendations Matter**: YouTube's recommendation system drives more viewership than channel subscriptions or search.
- 🖱️ **Clicks Indicate Interest**: Clicking on a video suggests you will likely find it satisfying, as viewers typically click on content they want to watch.
- ⏰ **Watchtime Signals Preferences**: The duration and type of videos you watch help personalize recommendations based on your interests.
- ⭐ **User Feedback Counts**: Surveys measuring "valued watchtime" through star ratings help gauge viewer satisfaction with content.
- 🚫 **Demoting Borderline Content**: YouTube has reduced the promotion of borderline content, leading to a 70% drop in watchtime for such videos, with current consumption from recommendations now below 1%.
Top Highlights
- Survey Responses: To really make sure viewers are satisfied with the content they’re watching, we measure what we call “valued watchtime”—the time spent watching a video that you consider valuable. We measure valued watchtime through user surveys that ask you to rate the video you watched from one to five stars, giving us a metric to determine how ...
- Recommendations drive a significant amount of the overall viewership on YouTube, even more than channel subscriptions or search.
- To do this, we start with the knowledge that everyone has unique viewing habits. Our system then compares your viewing habits with those that are similar to you and uses that information to suggest other content you may want to watch.
- Our system then compares your viewing habits with those that are similar to you and uses that information to suggest other content you may want to watch
- Clicks: Clicking on a video provides a strong indication that you will also find it satisfying. After all, you wouldn’t click on something you don’t want to watch.
Tags
ML
AI
Domain
Toughts & Comments
Kazuki
Clicks, views, watchtime, user surveys, shares, likes and dislikes
Ready to highlight and find good content?
Glasp is a social web highlighter that people can highlight and organize quotes and thoughts from the web, and access other like-minded people’s learning.