Wrote Python scripts to parse Seinfeld tv scripts from Seinology.com.
Hierarchically organized raw data , including episode and scene numbers, number of words sequentially, and duration of speech by different character, into structured python lists, series->season->episode->scene.
Would like to return to this project and conduct temporal network analysis and topological data analysis to determine the evolution of the social network of characters throughout the course of the sitcom.
H/t https://github.com/colinpollock/seinfeld-scripts
MORE INFORMATION AVAILABLE UPON REQUEST.