Host: The Japanese Society for Artificial Intelligence
Name : The 32nd Annual Conference of the Japanese Society for Artificial Intelligence, 2018
Number : 32
Location : [in Japanese]
Date : June 05, 2018 - June 08, 2018
With the progress of globalization and the overseas expansion of the food industry, the importance of understanding regional differences in food culture is increasing. However, the traditional questionnaire-based study is costly in time and money. In this study, a new method for detecting cultural differences using social media is proposed with an experimental analysis on Japanese and American attitudes toward beverages. We gathered descriptive expressions (adjectives) about beverages with both languages from Twitter, and classified them into thirty meaning-based groups. We compared the co-occurrence frequencies of these groups between Japanese and Americans. The results reveal cross-cultural differences in impression and value standards on beverages. For example, coffee is generally recognized as ‘bitter' and ‘sour' in Japan, while it frequently appears in ‘boring' contexts in the U.S. The proposed method enables a fast specific investigation on regional food culture, which can be applied to the localization strategy of the food industry.