Text Mining for Conformity Assessment of the Strategy for the State National Policy and Government Websites

摘要

The article examines the news items on the official websites of the Federal Agency for Nationality Affairs, the State Duma Committee on Nationality Affairs, and the Council for Interethnic Relations for their compliance with the Strategy for the state nationality policy of the Russian Federation for the period up to 2025. The research is mainly based on the method of comparing text documents in natural language processing. The primary parameter for the analysis of the text corpus is the wording of the Strategy. The news features on the websites are checked for their consistency with the trends of the state nationality policy indicated in the document as the most voluminous section of the Strategy. The array of textual data is represented by 397 news items published on the websites in 2019. The comparison of textual data shows that the largest number of matches is found on the news feed of the website of the Council for Interethnic Relations. The focus area with the greater number of matches across all websites is establishing the environment to preserve and enrich the Russian language and the languages of the peoples of the Russian Federation.