Construction of a Business Confidence Index for Russia Based on the Sentiment Analysis of News Texts from the Internet

Filipp V. Ulyankin – PhD student at the Russian Presidential Academy of National Economy and Public Administration (Moscow, Russia). E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Andrey V. Polbin – Head of Mathematical Modelling of Economic Processes Department of the Russian Presidential Academy of National Economy and Public Administration; Deputy Head of Mathematical Modelling of Economic Processes International Department of the Gaidar Institute, Candidate of Economic Sciences (Moscow, Russia). E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

In this paper, we construct a business confidence index for Russia based on news texts from the Internet. News articles are processed via text analysis methods. We estimate sentiment of text based on special dictionary, assembled by crowdsourcing. Analysis of the index dynamics shows that the Russian business negatively evaluates support measures associated with coronavirus crisis. After a peak in March 2020, when the first announcement of business assistance was made, the index is showing the longest decline in the past three years. Even a new support measures announcement has not returned the index to its previous values.

Key words: text analysis; sentiment analysis; business confidence index; machine learning.