Application of Machine Learning for Document Classification and Processing in Adaptive Information Systems

Abstract

This article discusses the approach to the use of machine learning for the classification and processing of documents in adaptive information systems. The main tasks on the application of machine learning methods in adaptive information systems are considered. A classification of documents based on the facet approach and presented in the set theory notation is developed. An approach for pre-processing documents for their subsequent analysis using machine learning methods is presented. Experimental studies were carried out, during which the accuracy of document classification was improved and the training time of the neural network was reduced. The results obtained will be used in further studies of the application of machine learning methods for processing, classification and routing of documents.