Development of the Decision Support System for Scientific Texts Categorization

The work is devoted to the development of the decision support system for scientific articles, abstracts and annotations classification. For this purpose, the study of such machine learning models as artificial neural networks, random forest, logistic regression, and the method of support vectors, taking into account such a feature of scientific texts, as a large number of terms that are characteristic of various categories. The stages of analysis of the provided data set of data, extraction of attributes from texts and development of a desktop application are separately considered. The results of the research are used in the development of a decision support system for the assignment of corresponding codes of the department, SRSTI or abstract journal of the All-Russian Institute of Scientific Research to scientific texts.