Four separate analyses are run as part of the project, on four different data sets:
- English ratings (this also includes the etymology stuff)
- Indo-European based on Google Translations
- Hungarian ratings
- Cross-linguistic data (excluding all Indo-European languages + Hungarian)
Raw data files are in raw_data, arranged by analysis. Final data files are in final_data. Data processing scripts are in data_processing. The model folder might be unnecessary โ I think I started saving some models, but then didn't really do it in the end. The analysis is all in rough_r_master_analysis.Rmd.