Authorship Verification in Arabic using Function Words: A Controversial Case Study of Imam Ali's Book Peak of Eloquence

Abstract

This paper addresses the viability of two multivariate methods (Principal Components Analysis and Cluster Analysis) in verifying the disputed authorship of a famous Arabic religious book called (Nahjul-Balagha/ Peak of Eloquence). This book occupies an exceptional position in the history of the huge debates held between the two basic Islamic sectors: Sunni'e and Shia. Therefore, it represents a serious challenge to the viability of the multivariate techniques in resolving certain types of historical and sectarian conflicts and controversies. Furthermore, verifying the authorship of this book could be a good opportunity to find out whether there are certain quantitative techniques of attribution that hold for different languages such as English and Arabic. Function words have been targeted in this paper as possible indicators of the author's identity. Accordingly, a set of Arabic function words would be tested using WordSmith Tools (version 5). It turned out that the multivariate techniques are most likely robust for addressing the type of issues raised about Nahjul-Balagha. Besides, it appeared that the statistical patterns of function word usages are quite sensitive to genre in Arabic.

Keywords: authorship attribution, authorship verification, stylometrics, computational stylistics.