Resumen
This study was conducted to present the possibilities of modern approaches to extracting information from text corpus. The purpose of this study is to provide answers to the following business questions using a scientific approach to the analysis of the text: What important areas of research have developed over the past year? What is new in oil and gas technologies?The authors have successfully applied the technology of topic modeling to solve the problem. The focus of the research was quality of the topic model. This paper investigates the behaviors of metrics Perplexity Score and Sparsity Scores for matrices T and F in the regularization of the topic model.The application of additive regularization allowed dividing the topics into main and noise, which significantly improved the interpretability of the topics.