2018 年 7 巻 2 号 p. 209-214
This paper explains text mining and it’s practical uses according to three types and stages of data science: 1) VISUALIZATION , 2) ANALYSIS, 3) Predictive analytics (MODELING).VISUALIZATION is visualization of the characteristics of the data, and these include: web analysis, co-occurrence tables, and (reference) frequency analysis. ANALYSIS uses statistical techniques for the results of text mining. Predictive analytics (Modeling) uses a variety of techniques from machine learning to make predictions about the future. There exists author discrimination by decision tree and neural network, and Text classification by modeling method.