A Novel Method That Identifies The Hidden Properties Of A Person’s Name In Kanji Or Hanzi

Abstract

Most Japanese persons’ Kanji names have similar characters with ’Hanzi’. For example, ’吉田悠人’ and ’欧阳沛南’ are two persons’ names. ’吉田悠人’ is a Kanji name, ’欧阳沛南’ is a Hanzi name. It is a challenge for a computer to identify the name origins between ’Hanzi’ and ’Kanji’ of a person’s name. In addition, we found that there are limited existing methods to identify more than one hidden property of people’s names at one time. In this paper, we aim to build a method that can identify the hidden properties of Hanzi names and Kanji names. Our novel method can point out the origin, the surname and the given name of a person’s name. The evaluation result shows that our method is better than an existing system ’TextBlob’ on predicting the origins of people’s names. The accuracy of our proposed method is 86.87%.