Approaches to visualizing big text data at the stage of collection and pre-processing

Abstract

This paper describes the text data analysis in the course of management decision making. We examine in detail the process of collection of text data for further analysis and the use of imaging to increase the efficiency of human resources during collection and data pre-processing. A modification of the algorithm for creating an “n-gram cloud” visualization is proposed, which makes visualization accessible to people with visual impairments. Also, a method of visualization of n-gram vector representation models (word embedding) is proposed. On the basis of the conducted research, a part of a software package was implemented, which is responsible for creating interactive visualizations in a browser and interoperating with them.