Recommendation Systems and Filter Bubbles
How recommendation systems work: YouTube, Netflix, and shop websites track what you click and find patterns; filter bubbles; the difference between helpful suggestions and manipulation
What a learner can do afterwards
- Explain how YouTube or Netflix decides what to suggest next
- Describe what a 'filter bubble' is (only seeing things similar to what you already like)
- Give one benefit and one risk of recommendation systems
The lesson
Have you noticed that after you watch one video, apps like YouTube keep showing you videos just like it? Every click, watch, and skip gets remembered. The app looks for patterns in what you do, then guesses what you might want next.
Mia watches cooking videos every day after school. She never searches for cooking videos, but Netflix keeps suggesting more of them. Netflix noticed her pattern and used it to pick new shows for her.
But there is a catch. If you only ever see videos and shows like the ones you already watched, you stop seeing anything different. This is called a filter bubble. You are inside a bubble where everything looks similar, and other things get pushed out of sight.
Recommendations can be helpful. They save you time hunting for things you like, whether it is videos, shows, or things at a shop website. But it is worth searching for something new once in a while, so your filter bubble does not get too small.
Apps use your clicks to spot patterns and suggest similar things, but only seeing similar things can trap you in a filter bubble.
Watch it
Where it sits
This opens up
Where this leads
Jobs that lean on this skill. Follow one to see everything it is built on.
8 questions wait behind this lesson, each with its answer explained. Every answer feeds the sky: stars light as they are learned, and dim when it is time to come back.