I downloaded the Topic Modeling Tool and put in the corpus that I created for Lab 3.

The first thing that I saw was this list/bug chunk of words or topics, I guess they would be called.


Screen Shot 2016-03-01 at 2.49.44 PM

In this block of words, some of them include: read, book, boy, boys, England,  life, thing, things, wife, woman, man, people, work, etc. So some of these words go together and make sense but then there are some outliers like meningitis.


Here is one more souvenir from my experiment with the Topic Modeling Tool:

Screen Shot 2016-03-01 at 2.56.17 PM

This is almost the same as the one before, though I am not entirely sure how the blocks are different from each other. This block has some of the same words as the one before such as: read, things, book, idiot, people, years, etc. But there are also some new words that pop up in this one too such as: english, give, doctor, etc. However, for the most part, the two share a lot of the same words.