BullsEye {BullsEyeR}R Documentation

Topic Modelling

Description

BullsEye runs intial preprocessing, removes custom stop words and runs LDA with selected number of topics.

Usage

BullsEye(ds, spvar = 0.99, myStopWords = NULL, tno = 20, seedno = 12345,
  stemvar = 0)

Arguments

ds

a character vector of text documents

spvar

a sparsity variable which defaults to 0.99

myStopWords

a character vector of custom stop words which defaults to NULL

tno

a number of topics to be used to model text using LDA approach which defaults to 20

seedno

seed which defaults to 12345

stemvar

a variable indicating stemming to be performed or not which defaults to '0' meaning no stemming

Value

A dataframe with index of empty rows and topic terms.

See Also

FindTopicsNumber

Examples

## Not run: 
# Run it and see for yourself

## End(Not run)
data.tmp<-read.csv(system.file("ext", "testdata.csv", package="BullsEyeR"))
ds<-as.character(data.tmp$Story[1:2])
stopwords<-c("sallin","hannah","company","number","started","unlike")
BullsEye(ds=ds,spvar=0.99,myStopWords=stopwords,tno=20,seedno=12345,stemvar=0)

[Package BullsEyeR version 0.2.0 Index]