Categorization Behavior -or- How I Learned to Stop Worrying and Love the Long Tail » Tag Distribution when there are many categories
Figure 1: Expected vs. Uniform Distributions of Pages to Categories
Figure is a chart showing two data series. One is a uniform distribution for 500 pages divided by 100 categories. It is a horizontal line at 5. The other series is the long-tail distribution we expect to see, where the most popular category has 100 items in it and the curve drops sharply from there.


