Summary

This analysis is based on the premise that part of the political divide in this country is not just about “what to do” but is more fundamentally about what the problems that need solving are. This is inspired by articles I read over the summer, such as this one in the National Review which emphasize polling results highlighting disagreement about the most important issues facing the United States.
The discourse and news people hear informs their opinions and priorities. Here I want to look systematically as the words used in both the Republican and Democratic debates. Are we talking past one another? Judge for yourself.

Method

The texts of the presidential debates are downloaded from the UCSB Presidency Project. The transcripts were cut and pasted into Apple Pages, and then stored as unformated .txt files. From that point all processing is done with R.
Text lines are split into candidate names and text. Then the {tm} library is used for convert the text data into a Corpus, which is used for analysis.
Processing includes converting all text to lower case and removing both punctuation and stop words.
The top 40 words are plotted for this initial anlaysis.

Definite difference are observed in the word clouds between candidates.

Republican Debates

Republican Candidates Debate October 28, 2015

Trump

Bush

RUBIO

CRUZ

Republican Candidates Debate November 10, 2015

Trump

Bush

RUBIO

CRUZ

Democratic Debate

Democratic Candidates Debate November 14, 2015

SANDERS

CLINTON

Democratic Candidates Debate October 13, 2015

SANDERS

CLINTON