Basically, for supervised mining you need what we call "labelled" data, that is, you need a history of values for the variable you want to predict.

Let's use post rewards as an example. Imagine you want to create a model to predict your post rewards based on a set of variable such as post length, topic, day of the week you posted it and any other atribute you may want to include.

That is a typical supervised mining problem. In this case you will need a dataset with all your posts and the rewards you got on each of them. Then you can train a model to predict the rewards of your future posts.