Feature Extraction of English Books on Tourism Using Data Mining
According to the White Paper on Tourism for 2020, 20.08 million Japanese individuals travelled overseas before the start of COVID-19, while 31.88 million foreigners visited Japan for sightseeing in 2019. It may be stated that it was a sightseeing period. Tourism expertise has become increasingly crucial, and reading resources in English has become essential. Several English works on tourism are examined in this research, and their metrical linguistics are compared to journalism. In summary, a C++ software is used to explore the frequency characteristics of character and word appearance. These characteristics are approximated using an exponential function. To determine the difficulty level and K-characteristic of each content, the percentage of Japanese junior high school necessary vocabulary and American basic vocabulary is computed. As a result, it’s clear that English resources for tourism follow the same character-appearance pattern as literary texts. In addition, tourism materials have high K-characteristic values, and older publications with a higher speciality are more difficult to read than journalism. Furthermore, the book with the most recent publication year has features that are similar to those of journalism as a whole.
Author (S) Details
Faculty of Engineering, Sanjo City University, Niigata, Japan.
Faculty of Production Systems Engineering and Sciences, Komatsu University, Ishikawa, Japan.
Nihonkai International Exchange Center, Ishikawa, Japan.
View Book :- https://stm.bookpi.org/IEAM-V12/article/view/2076