Folksonomy combines the best of close- and open-ended systems.

Folksonomy was a term in the early 2000's for systems like Flickr's community tagging system.

I imagine I'm one of the only people on earth who have uttered the term in the last few years.

The general idea is that the system allows any participant to create a tag; there's no top-down structure for the ontology.

This gives a fully open ended system.

But open-ended systems create a chaotic, diffuse baseline.

Folksonomies typically work because the UI adds optional preferential attachment.

That is, users can optionally choose to adopt someone else's idea.

Concretely, this means that when you create a new tag, it first shows you a search result of related tags that already exist, along with how popular they are.

The more popular a tag is, the more you'll be willing to adopt it even if it's not exactly what you had in mind.

Adopting a popular tag will help other people find your content.

This setup combines the best of open and closed systems.

It's a kind of collaborative sifting sort of good or useful ideas in that context.

I imagine embeddings could turbocharge folksonomies if applied well.