Abstract
This paper presents a word difficulty mapping method that utilizes three indicators: Average Number of Times, Word Frequency Score, and Word Difficulty Score, to map the difficulty of words. The effectiveness of this method is demonstrated using the EERIE as a case study. To predict the Average Number of Times, a Refined Simulated Annealing Model, which combines K-Dimension Tree, is employed. Subsequently, word difficulty is mapped using K-Means cluster analysis. The results indicate a strong correlation between the Average Number of Times, Frequency Score of The Word, Difficulty Score of The Word and word difficulty, highlighting the efficacy of the proposed word difficulty mapping method.