Comparative study for Stylometric analysis techniques for authorship attribution

A text is a meaningful source of information. Capturing the right patterns in written text gives metrics to measure and infer to what extent this text belongs or is relevant to a specific author. This research aims to introduce a new feature that goes more in deep in the language structure. The feature introduced is based on an attempt to differentiate stylistic changes among authors according to the different sentence structure each author uses. The study showed the effect of introducing this new feature to machine learning models to enhance their performance. It was found that the prediction of authors was enhanced by adding sentence structure as an additional feature as the f1_scores increased by 0.3% and when normalizing the data and adding the feature it increased by 5%.

I. Introduction

Stylometry is study of an author’s or a text’s linguistic identity by means of extracting quantitative variations and specific patterns of language use. Stylometry is field of interest in natural language processing (NLP), it is divided into five subtasks which are: Authorship attribution, Authorship verification, Authorship profiling, Stylochronometry, Adversarial stylometry. The dominant sub-tasks are the first three as stylometry is often used to attribute authors to disputed documents. Stylometric studies have several applications ranging from detecting the true author of Shakespeare’s plays [1] to forensic linguistics [2]–[4]. Recent works have applied stylometric techniques in the field of art and music [5],[6] which proved that detecting stylistic change could be applied to different fields to attribute the work to its owner.