Taxonomy and Evaluation of Markers for Computational Stylistics

摘要

Currently, stylistic analysis of natural language texts is achieved through a wide variety of techniques containing many different algorithms, feature sets and collection methods. Most machine-learning methods rely on feature extraction to model the text and perform classification. But what are the best features for making style based distinctions? While many researchers have developed particular collections of style features -called style markers - no definitive list exists. In this paper we present an organized collection of such style markers with performance data on a diverse set of texts. We show that for each training document, one or more markers exist that can distinguish it from others, providing a basis for a weighted, combined set of markers that outperform any of the individual ones. We examine and categorize 502 style markers, both individually and as a set, and evaluate their performance on several English language text collections.