Application of artificial intelligence systems for stylometric analysis of texts as factor of sustainable development

Abstract

Investment in human capital, along with natural resource management, is an important indicator of sustainable development. One of the areas of such investments is the creation of artificial intelligence systems that allow for the classification of texts. This paper analyzes the use of artificial intelligence systems for stylometric text analysis. On the basis of the algorithm of the convolutional artificial immune system, a system for stylometric analysis of texts was developed and implemented in software. In order to determine the possibility of using this system to determine the authorship of literary works, it was trained and tested. For this, the works of two authors were chosen: Leo Tolstoy and Fyodor Kryukov. This system demonstrated a high quality of text classification and a good speed of work and learning. So, to test the performance of the system, 11 works by Leo Tolstoy and 12 works by Fedor Kryukov were taken that were not used to train the system. All works of these authors were classified correctly. It should be noted that the artificial immune system algorithm can also be successfully used in other tasks requiring text classification.