Statistical Literary Analysis

Statistical Literary Analysis

One method of approaching text in a computational way is to compute the relative probabilities that a word will follow a previous word, or that a word will follow a group of words. This often reveals important stylistic information about the piece. For example, it can show whether two texts have the same author, or whether a given text (such as the Bible) was a collaborative effort. This project will consist of reviewing previous approaches to statistical literary analysis, writing a general program to perform this task, and then applying the program to a text or group of texts with the hope of revealing new insights about these work(s).