Stylogenetics: Clustering-based stylistic analysis of literary corpora

Current advances in shallow parsing allow us to use results from this field in stylogenetic research, so that a new methodology for the automatic analysis of literary texts can be developed. The main pillars of this methodology which is borrowed from topic detection research are (i) using more complex features than the simple lexical features suggested by traditional approaches, (ii) using authors or groups of authors as a prediction class, and (iii) using clustering methods to indicate the differences and similarities between authors (i.e. stylogenetics). On the basis of the stylistic genome of authors, we try to cluster them into closely related and meaningful groups. We report on experiments with a literary corpus of five million words consisting of representative samples of female and male authors. Combinations of syntactic, token-based and lexical features constitute a profile that characterizes the style of an author. The stylogenetics methodology opens up new perspectives for literary analysis, enabling and necessitating close cooperation between literary scholars and computational linguists.