A very nice feature to have would be to run topic modeling (say, your run-of-the-mill LDA) on the comments, and then colormap the nodes as to preserve the distances in the comment topic vector. This way you'd be able to see threadjacking, etc.
Wow, that's a great idea for next steps. This is the direction I'd love to take this work- getting into the comments and running an analysis. The comments range in size and some can have subtle humor- I wonder how that would affect the LDA.
A very nice feature to have would be to run topic modeling (say, your run-of-the-mill LDA) on the comments, and then colormap the nodes as to preserve the distances in the comment topic vector. This way you'd be able to see threadjacking, etc.