Feature Extraction of English Books on Environmentology Using Data Mining

A system called “environmentology” has recently been attempted to address environmental issues. In order to study environmentology, reading materials in English is considered to be indispensable. In this paper, several English books on environmentology are investigated and compared to journalism in terms of metrical linguistics. In short, a C++ programme is used to investigate the frequency characteristics of character- and word-appearance. An exponential function is used to approximate these characteristics. In addition, to determine the difficulty level and K-characteristic of each material, the percentage of Japanese junior high school required vocabulary and American basic vocabulary is calculated. As a result, it is clearly demonstrated that English resources for environmentology have a similar tendency to literary writings in terms of character-appearance. Furthermore, the K-characteristic values for the materials on environmentology are high, and some books are more difficult than TIME magazine.