On the Use of Supervised Learning Method for Authorship Attribution

In this paper we investigate the use of a supervised learning method for the authorship attribution that is for the identification of the author of a text. We suggest a new, simple and efficient method, which is merely based on counting the number of repetitions of each alphabetic letter in the text, instead of using the traditional classification properties; such as the contents of the text and style of the author; which falls into four feature categories: lexical, syntactic, structural, and content-specific. Furthermore, we apply a spherical classification method. We apply the proposed technique to the work of two Italian writers, Dante Alighieri and Brunetto Latini. With almost high reliability, the spherical classifier proved its ability to discriminate between the selected authors. Finally the results are compared with those obtained by means of a standard Support Vector Machine classifier.