New Computational-Linguistic Authorial-Attribution Method Applied to "Shakespeare" & Other Texts

The data in this GitHub repository is made publicly available to support the conclusions described in a series of articles that re-attributed 266 English-language texts from between 1570s and 1640s.
DALLAS - July 26, 2020 - PRLog -- The data was derived by using an entirely new 27-test computational-linguistics authorial-attribution method that was designed for this study. The 27 tests measure punctuation, word groups, emotional categories, lexical and linguistic density, passive voice and the top-6 words and letters.

The initial goal was solving the mystery of who wrote "William Shakespeare's" works if, as records indicate, Shakespeare was illiterate and could not have written them himself. The findings indicated that these texts were all written by a Ghostwriting Workshop with six members: Richard Verstegan, Josuah Sylvester, Gabriel Harvey, Benjamin Jonson, William Byrd and William Percy. Past computational-linguistics studies of the "Shakespeare" canon have mistakenly assumed all "Shakespeare"-attributed texts were actually written solely by the one man called William Shakespeare. This bias has skewed their results, so that most texts of uncertain "Shakespearean" authorship have changed bylines as studies derived variously skewed results. The articles in this attribution study explain the literary and biographical analysis that went into choosing these particular six ghostwriters, as well as the method employed, structural patterns, the historical background and various other elements that build this case. The data alone also speaks for itself. The findings are particularly blatant in the visualizations of the matches between the texts in each linguistic-group in the included diagrams. Two of these articles have been preliminarily accepted and are forthcoming: 1. Anna Faktorovich, "A New Computational-Linguistics Authorial-Attribution Method Described and Applied to Solving the 'William Shakespeare' Mystery", Studia Metrica et Poetica (December 2020). 2. Anna Faktorovich, "Manipulation of Audience-Size by 'Shakespeare' and Henslowe: Nonexistent Plays and the Murderous Lenders", was accepted for publication in 2021 by Critical Survey. This study was preceded by another book-length study with a modified multi-test computational-linguistics attribution method that was applied to the canon surrounding "Daniel Defoe's" texts, and one of these essays called "Publishers and Hack Writers: Signs of Collaborative Writing in the 'Defoe' Canon" is forthcoming in the Fall 2020 issue of the Journal of Information Ethics. The ideas that were employed in these studies were first developed for Anna Faktorovich's book called Gender Bias in Mystery and Romance Novel Publishing: Mimicking Femininity and Masculinity (Atlanta: Anaphora Literary Press, 2015). Comments and questions are warmly invited. Access the data files on GitHub at

Anna Faktorovich
Email:*** Email Verified
Tags:Computational Linguistics
Location:Dallas - Texas - United States
Account Email Address Verified     Account Phone Number Verified     Disclaimer     Report Abuse
Anaphora Literary Press PRs
Trending News
Most Viewed
Top Daily News

Like PRLog?
Click to Share