Development of Software System for the Selection of Important Legal News from the Information Flow

The work is a description of the developed software and the results of empirical analysis of machine learning methods in relation to the Russian-language text data of a legal nature. The paper deals with the main approaches to the pre-processing of texts, feature extraction, and classification. The result is a software system that includes a database and a WEB-interface, the main purpose of which is to visualize the results of the model. A way to display information about the news in a text view, allowing the user to check the result of the developed SOFTWARE and change it if necessary. The software implementation is a client-server application in which the client part contains interactive user interaction functions. The visualization is static. The server part contains data aggregation functions and their analysis. The volume of this work is 53 pages including 14 pictures and 4 tables.