Kirk vs Spock Linguistics Head-to-Head

Today I harvested the three seasons of Star Trek TOS episode scripts from a friendly website hosting the annotated text.  Then I extracted just the lines spoken by Captain Kirk and just the lines of Mr Spock.

So how does Kirk match up to Spock linguistically?

First of all, the Lingua::EN::Fathom module that computes text readability, says that the mean FOG for the entire series is 6.97. This measure can be roughly interpreted as the 7th grade level.  Kirk speaks at just below the average at 6.41 FOG, and Mr Spock weighs in at 8.53 FOG.  Makes sense.  Also, Kirk has a lot more to say than Spock.  He speaks a whopping 115,119 words compared to Spock’s 62,616.  This also makes sense.

Who says what the most?  A bit of handy word cloud code generates these charts:









I’m sure you can tell who is who!

Since emotional sentiment can be easily plotted with the syuzhet package, what does that tell us?









It appears that Spock actually has a slightly greater emotional range than Kirk!

And what about the actual emotions expressed by each?





To my surprise, each expresses exactly the same emotions but in differing amounts.

What are the top 5, 4-word phrases that are repeated the most for each?  (This is done with the ngram package.)  First is Captain Kirk:

Next up is Mr Spock:

It is obvious from the frequency that Mr Spock repeats himself a lot less often.

Here are the top 5 of Kirk’s repeated 5-word phrases:

And here are Spock’s:


For the hardcore out there, the IF-IDF top 10 looks like this:

Not especially enlightening… But anyway. ;-)

(This last bit was done with code of my making, instead of an R package as above.)