Check Whether Tokens Read as Surnames — check_if

For each token, compares its census first-name and last-name frequencies and flags it as a surname when it appears more often in the last-name position.

Usage

check_if_surname(x)

Arguments

x: A character vector of name tokens.

Value

A logical vector, one element per token, TRUE where the token is more likely a surname than a given name.

Examples

check_if_surname(c("MICHAEL", "LIVINGSTON"))
#> [1] FALSE  TRUE