9P-D-5 自己組織化マップを用いたWeb記事の可読性予測手法の提案と評価(D会場 大学院生・学部学生 奨励賞セッション)

抄録

In this article, we introduce a proposal and evaluation of prediction method for readability of web articles based on Self-Organizing Maps (SOM). We focused on font-size among web contents for web readability. Then we considered a threshold of readability for the specific age groups with the method of pairwise comparison of Scheffe. In addition, we measured the time for reading aloud and predicted the readability of Web articles by SOM. As the result, we confirmed that in a certain range, this prediction method was effective because the agreement rate is 90%.