Language Identification for Generating GIS Data Used in Mapping Linguistic Features of the World’s Languages

For the purpose of mapping linguistic features of the world’s languages, it is necessary to identify the languages in Yamamoto-Data and SilGIS-Data. In this paper, firstly we point out the problems in the primary method that uses language name(s) for language identification. Secondly, noticing that the world’s languages are classified and grouped into languages family trees, we propose an improved method for the language classification. Finally, we give our experimental results.