Analysis of the developed quantitative method for automatic attribution of scientific and technical text content written in Ukrainian

Abstract

A formal approach was proposed to implement text content attribution. The study was conducted with Ukrainian scientific and technical texts. The results of application of the designed algorithms of automatic attribution of the text content based on the NLP and stylemetry methods were analyzed. Prospects and features of application of stylemetry information technologies for attribution of the text content were considered. Quantitative content analysis of scientific and technical text content takes advantage of content monitoring and text content analysis based on NLP, Web-Mining and stylemetry methods to identify the multitude of authors whose talking style is similar to that of the analyzed text fragment. This narrows the range of search for further use in the stylemetry methods to determine the degree of belonging of the analyzed text to a particular author. Decomposition of the attribution method was carried out based on analysis of such talking coefficients as lexical diversity, degree (measure) of syntactic complexity, talking coherence, indexes of exclusivity and concentration of the text. At the same time, author's style parameters such as the number of words in a certain text, the total number of words of this text, the number of sentences, the number of prepositions, the number of conjunctions, the number of words with occurrence frequency 1, the number of words with occurrence frequency 10 or more were analyzed. Further experimental study requires testing of the proposed method in identifying keywords of texts of other categories: scientific humanitarian, artistic, journalistic, etc.