A research agenda I'd love to see (or pursue, if I magically had the time and resources) is a bridge between social science (especially international relations) modeling and narrative generation.
-
Show this thread
-
A lot of generative models produce numeric outputs, and even agent-based models generally offer their agents a limited set of actions.
1 reply 0 retweets 3 likesShow this thread -
In my experience, grafting narrative onto many existing models and methods (both computationally and manually/qualitatively) produces results that are fairly unsatisfying.
1 reply 0 retweets 2 likesShow this thread -
But narrative (or at least a sequence of discrete events) is generally how historic / future paths and processes are thought of.
1 reply 0 retweets 3 likesShow this thread -
This is obviously less vital for theory-testing, but I think there's a place in the ecosystem for rigorous models and methods that generate a human-readable narrative / history as a first-class feature.
2 replies 0 retweets 4 likesShow this thread
For my dissertation, I was building a system of BDD style tests for agents tht tried to kill two birds with one stone. I wanted it for testing and explication. It was very useful (but on backburner because of my ticking clock.)
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.