Predicting perceived ethnicity with data on personal names in Russia

Abstract

In this paper, we develop a machine learning classifier that predicts perceived ethnicity from data on personal names for major ethnic groups populating Russia. We collect data from VK, the largest Russian social media website. Ethnicity was coded from languages spoken by users and their geographical location, with the data manually cleaned by crowd workers. The classifier shows the accuracy of 0.82 for a scheme with 24 ethnic groups and 0.92 for 15 aggregated ethnic groups. It can be used for research on ethnicity and ethnic relations in Russia, with the data sets that have personal names but not ethnicity.