Н. А. Моисеева In the context of scientific and technological progress, the level of scientific journal is a key element of the modern national system for assessing research performance. Categorizing scientific journals is one of the primary tasks of bibliometrics, and the constant growth in the volume of data on publications and journals requires credible analysis of the alignment between declared and observed categorization patterns. The purpose of this article is to test the application of Exploratory Data Analysis (EDA) to study the distribution of scientific journals across the “White List” levels and to identify statistical patterns linking a journal's level to its indexing in scientometric databases (DB). The research subject is open data on scientific journals on the “White List”. The study employs statistical approach to analyzing publication data, implemented in the Google Collaboratory digital environment using Python programming language libraries for EDA (Pandas, Matplotlib, Seaborn). The results enabled a quantitative analysis of the alignment between empirical data and the “White List” journal categorization rules, revealing differences in indexing patterns across different journal levels. The practical significance lies in integrating EDA digital technologies into the bibliometric toolkit, opening opportunities for verifying categorization systems and advancing bibliometric methods amid the digitalization of science.
Научная статья 
исследовательский анализ данных