A Proposed Cultural Difference Detection Method Using Data from Japanese and Chinese Wikipedia

Multilingual communications often have the potential to cause misunderstanding, because even when people use the same word, they may not understand each other's culture. To prevent such misunderstandings, people should factor cultural differences into modern communications. However, it is difficult to judge such differences without knowledge of other cultures. We therefore propose a cultural difference detection method using Wikipedia as a database of multilingual knowledge. Data analysis revealed feature in the text and category, and others of the articles on Wikipedia. Accordingly, our proposed method incorporates these features. Based on our findings, we present a proposed method that can accurately detect various cultural differences. We found that the following features of an article are important for detecting cultural differences: (1) An article is not explained from a global viewpoint. (2) An article about Japan is mentioned by the Japanese version of Wikipedia. (3) An article that presents a positive view of China is not mentioned by the Chinese version of Wikipedia. (4) An article in each language version of Wikipedia has not mentioned each country.