associate {lsa} | R Documentation |
Find close terms in a textmatrix
Description
Returns those terms above a threshold close to the input term, sorted in descending order of their closeness. Alternatively, all terms and their closeness value can be returned sorted descending.
Usage
associate(textmatrix, term, measure = "cosine", threshold = 0.7)
Arguments
textmatrix |
A document-term matrix. |
term |
The stimulus 'word'. |
measure |
The closeness measure to choose (Pearson, Spearman, Cosine) |
threshold |
Terms being closer than this threshold are going to be returned. |
Details
Internally, a complete term-to-term similarity table is calculated, denoting the closeness (calculated with the specified measure) in its cells. All terms being close above this specified threshold are returned, sorted by their closeness value. Select a threshold of 0 to get all terms.
Value
termlist |
A named vector of closeness values (terms as labels, sorted in descending order). |
Author(s)
Fridolin Wild f.wild@open.ac.uk
See Also
Examples
# create some files
td = tempfile()
dir.create(td)
write( c("dog", "cat", "mouse"), file=paste(td, "D1", sep="/"))
write( c("hamster", "mouse", "sushi"), file=paste(td, "D2", sep="/"))
write( c("dog", "monster", "monster"), file=paste(td, "D3", sep="/"))
write( c("dog", "mouse", "dog"), file=paste(td, "D4", sep="/"))
# create matrices
myMatrix = textmatrix(td, minWordLength=1)
myLSAspace = lsa(myMatrix, dims=dimcalc_share())
myNewMatrix = as.textmatrix(myLSAspace)
# calc associations for mouse
associate(myNewMatrix, "mouse")
# clean up
unlink(td, recursive=TRUE)