Scientific Texts Classification by Speciality with Machine Learning Methods

Abstract

This article investigates the problem of experimental study classification problem of scientific text materials by utilizing the methods of Machine Learning and Deep Learning. The experimental study based on text classification method which proposed preprocessing and specificity of scientific text materials by using the ML algorithms to improve accuracy and speed of text classification was conducted. The analysis of indexation and classification methods by specialties was conducted for a set of scientific text materials. The evaluation and comparison of ML algorithms’ quality was considered, and the results of dissertational works’ classification by machine learning methods within the framework of the existing training set of scientific materials were obtained.