get_keywords: Get Keywords

In activetext/activeR: a semi-supervised active learning algorithm for text classification.

Get Keywords

Description

Gets keywords to feed to 'active_EM()', depending on on scheme type.

Usage

get_keywords(
  docs,
  dfm,
  num_keywords = 10,
  scheme = c("max_eta_raw", "max_eta_ratio"),
  verbose = TRUE
)

Arguments

docs	Documents table, same as for 'active_EM()'.
dfm	Quanteda document-feature matrix matching 'docs'.
num_keywords	Number of keywords selected for each class.
scheme	Keyword selection scheme. "max_eta_raw" finds selects based on maximum eta values for positive and negative classes. "max_eta_ratio" selects based on ratio between eta values for positive and negative classes.
verbose	If 'TRUE', prints out keywords to console.

Value

List of length 2. First element is vector of keywords for negative class, second element is vector of keywords for positive class.

activetext/activeR documentation built on May 31, 2024, 10:21 a.m.