Development of a software system for automated extraction of text data from social media

This article describes the process of developing a software system that extracts text information from Telegram channels. The paper analyzes existing methods for extracting information from social media, highlights their disadvantages and advantages. It also describes in detail the architecture and tools used to develop this software system. In conclusion, a description of experiments confirming the operability of this system is given. The information system can be further used for automated formation of a description of the subject area in the form of an OWL ontology composed of extracted text data.