Text mining of tourism preference in a multilingual site

There is a huge demand on multilingual tourism information of Japan because of the increasing number of tourists from foreign countries. Most of them may expect typical and stereotyped culture, nature, and modern society of Japan. However, people from different backgrounds, cultures, and languages might expect different aspects of Japan, as well. In this paper, we analyze these kinds of differences as the cultural tourism preference for Japan. We propose a machine-learning-based method to figure out the cultural tourism preference of people of different countries based on comparing the access logs to a multilingual tourism information site in different languages. We focus our discussion on the pages accessed in Thai and Vietnamese languages. Our research result shows that for Thai tourists the characteristic features are the famous places in an area and local specialties, but Vietnamese tourists pay much more attention to facilities and location of hotels. This difference was not observable by naive extraction of keywords and their visualization. This result has been used as a guide to the further creation of content in the tourism information site.