estimateCorpusSize: estimateCorpusSize

In DataScienceSalon/predictifyR.3.0: Word Prediction Language Model Evaluation

Description

estimateCorpusSize Estimates corpus size based upon lexical features

Usage

estimateCorpusSize(korpus, sampleSize = 2000, numSamples = 100)

Arguments

korpus	List containing the corpus meta data
sampleSize	Numeric indicating the sampling unit size
numSamples	Numeric indicating the number of samples to analyize

Details

This function takes as its parameters, the korpus meta data and the POS tags selected for this analysis, the returns an estimate of total corpus size based upon the distribution of lexical features per n000-word samples of the text. This analysis is based upon Representativeness in Corpus Design Biber 1993 https://www.researchgate.net/publication/31460364_Representativeness_in_Corpus_Design

Value

corpusSize List cointaining:

• nCorpus sample size estimate

• posAnalysisPOS tag distribution analysis

Author(s)

John James, [e-mail]

See Also

analyzeLexicalFeatures

Other sample size estimate functions: estimateRegisterSize, estimateSampleSize, estimateSamplingUnit

DataScienceSalon/predictifyR.3.0 documentation built on May 23, 2019, 8:25 p.m.