How does importance of topics and characters change over the course of a narrative? Who is gaining prominence and who vanishes? Jeff Clark tries to answer these question with automatic text analysis and a StreamGraph visualization.
Jeff has adapted the StreamGraph code to work with arbitrary text documents. The document is split up into 25 equal sized segments and the word counts are done within each segment. These segments are used in place of time along the horizontal axis of the StreamGraph.
It seems that the visualization does a good job at showing the development over a narrative as Cory Doctorow himself points out:
This works amazingly well — I’ve never seen an automated text analysis that was so revealing of the emotional and plot elements of a book!