# Pointwise mutual information for tag generation in Twitter

I came across the following link. https://stackoverflow.com/questions/2764116/tag-generation-from-a-small-text-content-such-as-tweets

The question is about how do we assign tag to tweets automatically, the answer suggest using pointwise mutual information, however, my question is if how can we achieve it?

If we have 1000 unique tweets and 100 unique tags, the probability of hashtag $x$ appear in tweet $y$ $p(x,y) = 1$, $p(x) = 1/1000$ and $p(y) = 1/1000$ will always stay, right?