Comparing frequencies for corpora of different sizes

We cannot easily compare the results of the previous exercise, because the sections of the corpora are of different sizes.

A common solution to this problem is to convert each frequency into a value per million words, or per thousand words. This is called normalizing the frequency scores.

Frequency per million words = ( frequency ÷ text no. words ) x 1,000,000

Now try filling in the "per million" column of the table, and think about the patterns.

Use the computer's calculator if you don't have your own pocket calculator:

[ Start - Programs - Accessories - Calculator ]