Classifying ethnicity by large scale surname data and its application

Abstract

The characteristics of social members have diversified thanks to the ease and freedom of movement of humans. In this study, we intended to analyze social phenomena by focusing on ethnicity among the characteristics of society members. To this end, large-scale surname data and machine learning methods were used to establish a surname-ethnicity classifier. We also present an application case for analyzing the spatial network of ethnicity using a built classifier.