Package: LSX 1.4.2

LSX: Semi-Supervised Algorithm for Document Scaling

A word embeddings-based semi-supervised model for document scaling Watanabe (2020) <doi:10.1080/19312458.2020.1832976>. LSS allows users to analyze large and complex corpora on arbitrary dimensions with seed words exploiting efficiency of word embeddings (SVD, Glove). It can generate word vectors on a users-provided corpus or incorporate a pre-trained word vectors.

Authors:Kohei Watanabe [aut, cre, cph]

LSX_1.4.2.tar.gz
LSX_1.4.2.zip(r-4.5)LSX_1.4.2.zip(r-4.4)LSX_1.4.2.zip(r-4.3)
LSX_1.4.2.tgz(r-4.4-any)LSX_1.4.2.tgz(r-4.3-any)
LSX_1.4.2.tar.gz(r-4.5-noble)LSX_1.4.2.tar.gz(r-4.4-noble)
LSX_1.4.2.tgz(r-4.4-emscripten)LSX_1.4.2.tgz(r-4.3-emscripten)
LSX.pdf |LSX.html✨
LSX/json (API)
NEWS

# Install 'LSX' in R:

install.packages('LSX', repos = c('https://koheiw.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/koheiw/lsx/issues

Pkgdown site:https://koheiw.github.io

Datasets:

data_dictionary_ideology - Seed words for analysis of left-right political ideology
data_dictionary_sentiment - Seed words for analysis of positive-negative sentiment
data_textmodel_lss_russianprotests - A fitted LSS model on street protest in Russia

On CRAN:

lsa quanteda sentiment-analysis text-analysis

6.23 score 55 stars 14 scripts 455 downloads 2 mentions 18 exports 50 dependencies

Last updated 24 days agofrom:551c1264f7. Checks:3 OK, 4 NOTE. Indexed: yes.

Target	Result	Latest binary
Doc / Vignettes	OK	Jan 09 2025
R-4.5-win	OK	Jan 09 2025
R-4.5-linux	OK	Jan 09 2025
R-4.4-win	NOTE	Jan 09 2025
R-4.4-mac	NOTE	Jan 09 2025
R-4.3-win	NOTE	Jan 09 2025
R-4.3-mac	NOTE	Jan 09 2025

Exports:as.coefficients_textmodel as.seedwords as.statistics_textmodel as.summary.textmodel as.textmodel_lss bootstrap_lss char_context coefficients.textmodel_lss cohesion diagnosys optimize_lss seedwords smooth_lss textmodel_lss textplot_components textplot_simil textplot_terms textstat_context

Dependencies:cli colorspace digest fansi farver fastmatch ggplot2 ggrepel glue gtable isoband ISOcodes jsonlite labeling lattice lifecycle locfit magrittr MASS Matrix mgcv munsell nlme nsyllable pillar pkgconfig plyr proxyC quanteda quanteda.textstats R6 RColorBrewer Rcpp RcppArmadillo RcppEigen reshape2 rlang RSpectra scales SnowballC stopwords stringi stringr tibble utf8 vctrs viridisLite withr xml2 yaml

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
Convert a list or a dictionary to seed words	as.seedwords
[experimental] Compute polarity scores with different hyper-parameters	bootstrap_lss
Extract model coefficients from a fitted textmodel_lss object	coef.textmodel_lss coefficients.textmodel_lss
Seed words for analysis of left-right political ideology	data_dictionary_ideology
Seed words for analysis of positive-negative sentiment	data_dictionary_sentiment
A fitted LSS model on street protest in Russia	data_textmodel_lss_russianprotests
[experimental] Compute variance ratios with different hyper-parameters	optimize_lss
Prediction method for textmodel_lss	predict.textmodel_lss
Seed words for Latent Semantic Analysis	seedwords
Smooth predicted polarity scores	smooth_lss
Fit a Latent Semantic Scaling model	textmodel_lss textmodel_lss.dfm textmodel_lss.fcm
Plot similarity between seed words	textplot_simil
Plot polarity scores of words	textplot_terms
Identify context words	char_context textstat_context