Ranking contemporary American poems

Abstract

In this paper I use computational linguistics to find the differences between poems written by amateurs and poems written by professionals. I identify a number of linguistic variables that are important in distinguishing between the two classes of poems. To a large extent the findings corroborate those of earlier researchers, such as the fact that professional poems have more concrete language than amateur poems. However, I go on to use the identifed characteristics to create an ensemble classifier using the principles of machine learning. The holdout sample classification accuracy of the classifier is 80%. Furthermore, I go on to use the scores generated by the classifier to rank a number of contemporary American poets on a continuum from "amateur" to "professional". This method could be used by publishers to run an initial check on submitted poems to determine their merit.