Authorship and Style Attribution by Statistical Methods of Style Differentiation on the Phonological Level

32Citations
Citations of this article
5Readers
Mendeley users who have this article in their library.
Get full text

Abstract

A novel approach to authorship and style attribution and differentiation on the phonological level has been suggested. Each style is considered a statistical system the elements of which are mean frequencies of groups of consonants chosen as a style attribution and differentiation criterion. Statistical analogues of the phonological subsystems of style systems have been obtained by mathematical statistical methods (the hypothesis, ranking and style distance determination methods). Interrelations of style, language and individual manner of writing factors as well as the style-differentiating capability of eight groups of consonants (labial, forelingual, mediolingual, backlingual, nasal, constrictive, occlusive and sonorant) have been established. The results of the research show that only the three methods combined above allow to fully characterize each style (belles-lettres, colloquial and scientific) under study and establish authorship of a text. The closeness and distance established between the compared styles have been shown in the three models proposed.

Cite

CITATION STYLE

APA

Khomytska, I., & Teslyuk, V. (2019). Authorship and Style Attribution by Statistical Methods of Style Differentiation on the Phonological Level. In Advances in Intelligent Systems and Computing (Vol. 871, pp. 105–118). Springer Verlag. https://doi.org/10.1007/978-3-030-01069-0_8

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free