Automated Topic Analysis of the Voynich Manuscript

[Jorge_Stolfi]

Very interesting!

Many years ago I did something vaguely similar, but with clustering in an explicit space rather than the black boxes that I presume are those models you used.

Basically the idea was

1. Pick a list of the N most common words in the manuscript
   
2. Compute their frequencies on each page, as a point in N-space
   
3. Choose three orthogonal axes X,Y,Z in N-space
   
4. Project the points on the planes XY, XZ, YZ, colored by section
   
5. Look at the plots and mumble something
   

Here are some plots, using N = 50 

  You are not allowed to view links. Register or Login to view.
  You are not allowed to view links. Register or Login to view.
  You are not allowed to view links. Register or Login to view.

here each dot is a page, and the lines connect the pages in presumed reading order.  Lines are omitted when there are missing pages in the manuscript, and when the section changes from one page to the next.

There are more details in the You are not allowed to view links. Register or Login to view. . Beware that I haven't looked at this work in 25 years, and the data was the old interlinear transcription which had rather variable quality.

My conclusions: 

1. Each section is fairly homogeneous in this metric, except that herbal-A is very different from herbal-B
   
2. Sections can be almost well-separated in this N-space.
   
3. Yet the difference between herbal-A and herbal-B is comparable to that between other two sections.
   
4. Indeed there seems to be a progressive variation from section to section, with herbal-A at one end, herbal-B at the other end  and the other sections wandering about between the two.
   
5. Within each section the pages vary "randomly" around the section's centroid, without a clear gradient.
   
6. It is not clear whether the pages within each section are really independent, or each page has some tendency to stay close to the adjacent pages.  I would expect the latter to be the case in the Biological section, maybe not in the other sections.
   

All the best, --jorge