Regional inflation analysis using social network data

Economy of Regions. 2024. Vol. 20. No. 3. P. 930–946.

Shcherbakov, V., Karpov I.

Inflation is one of the most important macroeconomic indicators that have a great impact on the population of any country and region. Inflation is influenced by range of factors, one of which is inflation expectations. Many central banks all over the World take this factor into consideration while implementing monetary policy within the inflation targeting regime. Nowadays, a lot of people are active users of the Internet, especially social networks. There is a hypothesis that people search, read, and discuss on the Internet those issues that are of particular interest to them. It is logical to assume that the dynamics of prices of consumer goods and services may also be in the focus of users’ discussions. In other words, such discussions may reflect their inflationary expectations. So, this data could be regarded as an alternative source of more rapid information about inflation expectations. This study is devoted to use of unstructured data from Vkontakte to analyze upward and downward inflationary trends (on the example of the Omsk region). To solve this problem, the authors used such state-of-art models as BERT family models. These models demonstrated better results than the benchmarks (e.g., logistic regression, decision tree classifier, etc.). It makes possible to define pro-inflationary and disinflationary types of keywords in different contexts. The obtained results can be useful for a deeper and more operational analysis of regional inflation. The approach tested on the example of the Omsk region can be scaled for other regions of Russia.

Keywords: social networks, inflation, machine learning, BERT, regional inflation expectations, monetary ploicy

Publication based on the results of: Development of network analysis in Russia: adaptation of theoretical and methodological approaches and practical application (2024)