This project uses Markov Chains under the hood in order to generate new stories on the basis of your text. The larger the text file, the better is the grammar of the generated text.
Markov chains, named after Andrey Markov, are mathematical systems that hop from one "state" (a situation or set of values) to another. For example, if you made a Markov chain model of a baby's behavior, you might include "playing," "eating", "sleeping," and "crying" as states, which together with other behaviors could form a 'state space': a list of all possible states. In addition, on top of the state space, a Markov chain tells you the probabilitiy of hopping, or "transitioning," from one state to any other state---e.g., the chance that a baby currently playing will fall asleep in the next five minutes without crying first.
The Markov Chain built on word frequencies alone does not work too well, as it does not consider grammar or semantics. However, it will work well if you provide enough text.
I was bored :)