Identifying Textual Content Based on Thematic Analysis of Similar Texts in Big Data

Abstract

The system designed for working with artistic texts in English is developed. It provides the opportunity to obtain the necessary information for the user, that is, the ordered data in the format Author - Title on the artwork, which correspond to the thematic query. This software tool operates to identify a plurality of content based on thematic analysis of texts. It is used as an application on a PC. Except for the main function the application does not perform additional actions. It consists of a part that serves as a user interface and a database that is located on the server. The input is an English-language text snippet that is similar to what the user wants to find. Output is a list of the names of works and the names of their authors, sorted by descending similarity.