Word analysis of Korean leaders’ speeches

humaniora

import packages

Screen Shot 2019-07-05 at 10.52.27 AM.png

import text from website

Screen Shot 2019-07-05 at 10.58.25 AM.png

make a list for the data frame

Screen Shot 2019-07-05 at 11.03.28 AM.png

getting into psycholinguistics analysis 

choosing a group of words I applying to both speeches

‘WE’, ‘I’, ‘GREAT’, ‘BEST’, ‘SOCIALIST’, ‘POWER’, ‘MILITARY’, ‘ARMY’, ‘PEOPLE’, ‘PEACE’, ‘DIALOGUE’, ‘HUMAN RIGHTS’, ‘DISCUSSION’, ‘SHOULD’,’MUST’, ‘WORK’, ‘PATRIOTISM’, ‘US’, ‘COMRADES’, ‘DEAR’

 

count the words using regex and str.count

Screen Shot 2019-07-05 at 11.12.27 AM.png

Screen Shot 2019-07-05 at 12.03.49 PM.png

sorting the columns

Screen Shot 2019-07-05 at 11.22.15 AM.png

changing the data frame into machine-friendly reading 

Screen Shot 2019-07-05 at 11.17.27 AM.png

 

coming up with visualization

 

M_allplotJ_allplot

JcountriesMcountries

people_countpeople2_count