Supplementary code and data for the paper `From stage to page: language independent bootstrap measures of distinctiveness in fictional speech`

The repository provides full data and processing / analysis pipeline for the paper 'From stage to page: language independent bootstrap measures of distinctiveness in fictional speech'

Rendered notebooks are also available through Github:

1) Preparation, energy distance and exploration (main)

2) Keyword curves & formal modeling

- `00_dracor_get_data.R`. Script uses DraCor dedicated API to get texts spoken by characters

- `01_distinctiveness_energy.ipynb` does the heavy lifting of data wrangling, cleaning and preprocessing, plus implements energy distance bootstrapping and does exploratory analysis

- `02_logodds_curves.R` calculates keyword curves for characters

- `03_analysis_and_models.R` explores keyword curves and does Bayesian models