Assessment of the possibility of using social network data in urban research

Abstract

Widespread digitalization leads to the acceleration of socioeconomic processes, which requires faster decision-making. Official statistics is the basis for managing the socio-economic development of a city or region. However, it has a number of limitations related to the timing of publication of information and details. At the same time, new data sources have been emerging in recent years. This study determines the possibility of using open data of the VKontakte social network in socioeconomic research using the example of Russian million-plus cities. The main research methods were statistical, descriptive, and comparative analysis. The information base of the study was made up of depersonalized data of the VKontakte social network users, as well as statistical data. It is revealed that on the basis of depersonalized data from VKontakte, it is possible to characterize the gender and age composition of city residents, which is comparable with Rosstat data, to identify and evaluate labor migration. It is concluded that the data from the social network can be used to obtain analytical information in situations where there is no official statistics available. The data have high geographical detail and can act as an additional source of operational big data on the composition of the population and the quality of its life.