Manual
User Manual:
Open the PDF directly: View PDF 
.
Page Count: 4
Package ‘textmatch’
March 25, 2019
Title Toolkit for Matching Textual Data and Evaluating Textual Similarity
Version 0.0.0.9000
Description What the package does (one paragraph).
Depends R (>= 3.5.2)
License What license is it under?
Encoding UTF-8
LazyData true
RoxygenNote 6.1.1.9000
Imports dplyr,
data.table,
quanteda
Suggests knitr,
rmarkdown
VignetteBuilder knitr
Rtopics documented:
get_pair_distances...................................... 1
get_similarity_scores .................................... 2
textmatch .......................................... 2
Index 4
get_pair_distances Similarity and distance computation between documents or features
Description
These functions compute distance matrices from a text representation where each row is a document
and each column is a feature to measure distance over based on treatment indicator Z
Usage
get_pair_distances(dat, Z, include = c("cosine", "jaccard", "euclidean",
"mahalanobis", "propensity"), exclude = NULL, docnames = NULL,
verbose = FALSE)
1
2textmatch
Arguments
ZA logical or binary vector indicating treatment and control for each unit in the
study. TRUE or 1 represents a treatment unit, FALSE of 0 represents a control
unit.
docnames A vector of document names equal in length to the number of documents
xa valid quanteda dfm object
Value
A matrix showing pairwise distances for all potential matches of treatment and control units under
various distance metrics
get_similarity_scores This function calculates an input character vector’s similarity matrix
according to the measures contained in the predictive model.
Description
This function calculates an input character vector’s similarity matrix according to the measures
contained in the predictive model.
Usage
get_similarity_scores(x)
Arguments
xA character vector where each element is a document
Value
A data frame of rows (n * n-1) and columns 16; each column is one of the constituent similarity
measures
textmatch This function runs the main ML model as specified in Mozer et al.
(2018)
Description
This function runs the main ML model as specified in Mozer et al. (2018)
Usage
textmatch(x, outcome = "matrix")
Arguments
xA character vector where each element is a document
textmatch 3
Value
An n by n matrix where n is the length of parameter x. Each entry is a standardized similarity score.
Examples
textmatch(c("I am a dog", "I am a cat", "The rain in Spain falls mainly on the plain."),
outcome = "matrix")
