Text Mining and Visualization

RapidMiner for Text Analytic Fundamentals 13

FIGURE 1.14: Build a token repository: Process I Step C – Process Documents operator.

FIGURE 1.15: Build a token repository: Process I Step C – vector window.

anything that is between docdate” > and < (Figure 1.17). Thus, in this case that text

string would be January 20, 1981. Label the attribute as Inaugural Date.

• Extract Information operator: The president’s name is within <title >Ronald Reagan:

Inaugural Address <\title >. So similar to the previous extraction, use a regular

expression (Figure 1.18)

((?<=title>).

*

?(?=:))

In this case take anything that is between title > and :; retrieving Ronald Re