Analyzing G20 Countries' Wikipedia Texts on LGBT

Abstract

In order to promote LGBT participation and acceptance in society, we need to develop indicators to compare the current status of each society. This study clarifies the differences in LGBT awareness in the language space of each country by analyzing the differences in perceptions of LGBT among the G20 countries that appear in Wikipedia articles.This paper uses a natural language processing model (BERT) to vectorize Wikipedia articles in each country's language and then uses dimensionality compression, clustering, and other processing to clarify the characteristics of LGBT awareness in each language space. We also find a correlation between LGBT awareness and the Gender Gap Index in each language space.