Word Analysis of the 2nd Presidential Debate


After the first Presidential debate, I published a post which briefly analyzed the words used by each candidate. Now that the second debate is over, I’m going to do a similar analysis. Like the previous post, my goal is to understand which topics were addressed most frequently and how this contrasted between the two, how much each spoke overall, and how much time each candidate spent talking about their opponent. At times, I’ll also compare the data to my analysis of the first debate.


Like the first debate, I obtained the transcript from the Washington Post, then used a tool from WriteWords.orgto parse out each word and its frequency of use. Once I had the frequencies of each word, I did some cleanup, filtering out pronouns, prepositions, conjunctions, and other types of common words, and removing any words which were used less than six times.

Observations
From the data, we can make a few observations:
  • CNN analyzed the amount of speaking time each candidate received and the result were pretty even with Trump speaking for 40 minutes and 10 seconds and Clinton speaking for 39 minutes and 5 seconds.


  • However, Trump spoke more overall words than Clinton, using a total of 7,334 words compared to Clinton’s 6,272, a difference of about 17%. This, however, is a much smaller difference than the first debate, in which Trump spoke over 35% more words than Clinton.
  • Trump spoke a total of 1,131 unique words, while Clinton spoke 1,261, an 11.5% difference.
  • Like the first debate, both candidates spent a lot of time speaking about their opponent. Trump’s # 3 word was “Hillary” (26 occurrences) and Clinton’s #2 word was “Donald” (32 occurrences). In a departure from the first debate, Trump chose to use Secretary Clinton’s first name only (Clinton used this tactic in both debates).
  • Not surprisingly, since this was a debate and the candidates were being asked similar questions, there is a lot of overlap in each candidate’s most commonly used words, particularly “People” and “Country”.

Here are each candidate’s top 10 most used words.




  • In the first debate, both candidates focused heavily on the economy and jobs, but this debate saw a shift in focus. Trump’s focus was on foreign policy (ISIS, Syria, Russia) and he made frequent criticisms (disaster). Hillary, on the other hand, chose to focus on healthcare and insurance (insurance, health, care).


Word Cloud
Finally, like the first debate, I thought that word clouds would be a good way to visualize this data set, so I created the following word clouds for each candidate.





And, just for fun, here’s a word cloud for the moderators, Martha Raddatz and Anderson Cooper. Their top words, not surprisingly, were the candidates’ names—they said “Secretary” 45 times, “Clinton” 41 times, “Mr.” 38 times, and “Trump” 40 times.



If you have any questions or comments, please let me know. And, if you’d like to interact with the visualization, feel free to check it out on my Tableau Public page: https://public.tableau.com/profile/ken.flerlage#!/vizhome/Second2016PresidentialDebate/Top10Words

Ken Flerlage, October 10, 2016

2 comments:

  1. is possible to see the words inside of a specific shape? for example i want to show the words cloud, but inside of an imagine of the state of Iowa, because i wnat to analisis the speech in this state. thanks

    ReplyDelete
    Replies
    1. That would be very difficult in Tableau, unfortunately. It would require you to use some sort of outside tool for sure.

      Delete

Powered by Blogger.