brandonleekramer/diverstidy: Standardize messy text data for geographic, population, and diversity-related research

The diverstidy package provides several functions that help detect patterns in unstandardized text data for analyses of geographies, populations, other forms of diversity. Currently, there is one function for detecting geographies and 17 additional functions that detect terms across the following subdomains of diversity-related research: ancestry, culture, disability, discrimination, diversity, equity, inclusion, linguistic, migration, population, race/ethnicity, religious, sex/gender, sexuality, social class, and US OMB population terms. Although somewhat simple, the intuition behind these functions is to detect the quantity of diversity-related terms show up in a given text entry. There are a number of case studies, but the primary uses of these functions are to examine historical trends in term usage and/or to detect potential biases in text.

install.packages("remotes")
remotes::install_github("brandonleekramer/diverstidy")