Building a software model to preserve intellectual property and identify the authorship of a text

Abstract

This article describes a software model algorithm that was implemented in order to determine the author of an unknown document based on the previously presented data and also studies the degree of accuracy of each of the measures for determining the authorship of a text. A comparative analysis is carried out based on the dependence of the quality of the identification of the text’s creator on his stylistic affiliation. The problem of determining the authorship of anonymous text in this programming model has been solved using a set of metrics, for each of which the following parameters are required: analysis of text frequency, total number of characters in the text, and dimension of the alphabet. These parameters are required for anonymous text and for the library of famous authors.