• If you are citizen of an European Union member nation, you may not use this service unless you are at least 16 years old.

  • Social distancing? Try a better way to work remotely on your online files. Dokkio, a new product from PBworks, can help your team find, organize, and collaborate on your Drive, Gmail, Dropbox, Box, and Slack files. Sign up for free.


Lindsay Blackie - Topic Modeling

Page history last edited by Lindsay Blackie 5 years, 1 month ago

So when I started looking at Topic Modeling, I decided to look at The Moonstone by Wilkie Collins as this book is longer and more complex than many of the other novels I have been looking at, so I thought it would provide the most interesting results. 


The first time I ran it through the topic modeling took, I got this list of results.

This list seems more random and doesn't tell me very much, even as someone who has read the book. This could be due to the length of the novel itself, so there is a high likelihood of potential iterations. The second time I decided to increase the number of potential topics and increase the iteration number to 500 and decreased the number of words shown to 5 to see how that would change the list. 

This list I found to be a lot more interesting. It's a little less overwhelming than the 10 word list, although it is maybe less precise. But I do find it interesting that very few personal names made it into this list, and the one person who is mentioned twice is actually a more minor character who dies earlier on, but who's death plays a pivotal role in the resolution of the novel. With further refinement, this could be increasingly accurate. 


Comments (0)

You don't have permission to comment on this page.