previous post: «Tags with MySQL fulltext»
Once upon a time I asked a question on the del.icio.us mailing list if Joshua could give me some stats of his bookmark webservice.
He didn’t. And so I thought I’d do some extrapolation to gain some stats.
And eventually you help me thinking so we together could have some collaborative stats.
Exactly one year ago, on 18.5.2004, Joshua told us: “There’s about 400k posts and 200k links.”
Now, let’s see: According to a pilot study there are about 90000 delicious users. On their graph I assume that those 70 people have an average of 800 bookmaks. If there are 90000 Users, say 10000 are using del.icio.us on this regular basis, then we have 9 million posts. That makes sense, I suppose.
Let’s say each bookmark has got 2 posts (taken the bookmark/post ratio stayed the same as in 2004), that would make a total of 4.5 million bookmarks.
Lets take the most popular tag on del.icio.us right now: design.
Since 7.5., there has been 10000 posts that are tagged with “design”, 20000 since 25.4 and 30000 since 12.4. Down to a month that makes about 24000 posts.
Lets say del.ico.us is already running 1 year at this rate, then we’d have 288000 posts tagged with “design”. That is: 3.2% of all posts on del.icio.us are tagged with the most popular tag “design”.
My most used tag is “resource”. It occurs in 58 out of my 686 bookmarks. That makes an 8.4% occurrence. On the graph you see the distribution of my bookmarks-per-tag ratio, I’ve got 529 distinctive tags.
As I am still doing my performance tests on different tag schemas and I want to have some real numbers so I can adjust my tests to a realworld example.
If you are interested in stats on del.icio.us, then take a look at Clay Shirys post, he has got some graphs on tags distribution.