Here are a couple images from Modeling Narrative Discourse, a PhD thesis by David K. Elson. I was looking at this because I thought it might have some clues about how to represent narratives, which is something I'm interested in vis à vis my computer programming work. And it does seem to have some nice clues about that! It also has some interesting results that I've skimmed about representing literary social networks, which seem at least a bit related to what we were talking about vis à vis scholarly social networks. A few pictures and a short quote are probably worth just over 2000 words.
The notion of extracting social networks from literary texts offers a wealth of possible collaborations between computer scientists and literary experts. Studies about the nineteenth-century British novel, for instance, are often concerned with the nature of the community that surrounds the protagonist. Some theorists have suggested a relationship between the size of a community and the amount of dialogue that occurs, positing that “face to face time” diminishes as the number of characters in the novel grows. [...] We did not find this to be the case. Rather, we found a weak but positive correlation (r=.16) between the number of quotes in a novel and the number of characters (normalizing the quote count for text length). There was a stronger positive correlation (r=.50) between the number of unique speakers (those characters who speak at least once) and the normalized number of quotes, suggesting that larger networks have more conversations than smaller ones. (pp. 10-11, 38-39)
 |
| Figure 2.1 "Automatically extracted conversation network for Jane Austen’s Mansfield Park." |
Comments
Post a Comment