—While the number of foreign tourists visiting
Japan is increasing in recent years, online hotel reservation
systems are widely used for travel planning. Hotel reservation
service sites provide accommodation information both of the
features and the recommended points to the potential users. The
hotel reservation services users usually refer the other users’
reviews in their decision-making. It is useful information for the
accommodation service improvement, whereas the replies of
users’ reviews are at their will. Most of the reviews are not
classified appropriately for users’ purposes that make it hard to
reach the appropriate information in reservation. To solve this
problem, this paper provides a method to analyse user reviews
in order to capture the characteristic expressions according to
their purposes and examines some methods to present beneficial
information at the time of hotel service improvement.
Moreover, the characteristics of user comments are
distinguished for every hotel. Differences between the
expressions and the evaluations each hotel is found from the
results of the analysis.
—Evaluation extraction, hotel, reservation, text
mining, user review.
Koichi Tsujii is with the Graduate School of Systems and Information
Engineering, The University of TSUKUBA, Tokyo, CO 112-0012 Japan and
with Nippon Travel Agency Co., Ltd, Tokyo, CO 105-8606 Japan (e-mail:
Masakazu Takahashi is with the Graduate School of Innovation and
Technology Management, Yamaguchi University, Yamaguchi, CO
755-8611 Japan (e-mail: firstname.lastname@example.org).
Yoshikatsu Fujita is with the Teikyo University, Tokyo, CO 192-0395
Japan (e-mail: email@example.com).
Kazuhiko Tsuda is with the Graduate School of Business Sciences, The
University of TSUKUBA, Tokyo, CO 112-0012 Japan (e-mail:
Cite: Koichi Tsujii, Masakazu Takahashi, Yoshikatsu Fujita, and Kazuhiko Tsuda, "Extraction of Accommodation Evaluation by Foreign Tourists with Text Mining," International Journal of Trade, Economics and Finance vol.5, no.2, pp. 130-135, 2014.