Package: sentometrics 1.0.0

Samuel Borms

sentometrics: An Integrated Framework for Textual Sentiment Time Series Aggregation and Prediction

Optimized prediction based on textual sentiment, accounting for the intrinsic challenge that sentiment can be computed and pooled across texts and time in various ways. See Ardia et al. (2021) <doi:10.18637/jss.v099.i02>.

Authors:Samuel Borms [aut, cre], David Ardia [aut], Keven Bluteau [aut], Kris Boudt [aut], Jeroen Van Pelt [ctb], Andres Algaba [ctb]

sentometrics_1.0.0.tar.gz
sentometrics_1.0.0.zip(r-4.5)sentometrics_1.0.0.zip(r-4.4)sentometrics_1.0.0.zip(r-4.3)
sentometrics_1.0.0.tgz(r-4.4-x86_64)sentometrics_1.0.0.tgz(r-4.4-arm64)sentometrics_1.0.0.tgz(r-4.3-x86_64)sentometrics_1.0.0.tgz(r-4.3-arm64)
sentometrics_1.0.0.tar.gz(r-4.5-noble)sentometrics_1.0.0.tar.gz(r-4.4-noble)
sentometrics_1.0.0.tgz(r-4.4-emscripten)sentometrics_1.0.0.tgz(r-4.3-emscripten)
sentometrics.pdf |sentometrics.html✨
sentometrics/json (API)
NEWS

# Install 'sentometrics' in R:

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

Bug tracker:https://github.com/sentometricsresearch/sentometrics/issues

Uses libs:

openblas– Optimized BLAS
c++– GNU Standard C++ Library v3
openmp– GCC OpenMP (GOMP) support library

Datasets:

epu - Monthly U.S. Economic Policy Uncertainty index
list_lexicons - Built-in lexicons
list_valence_shifters - Built-in valence word lists
usnews - Texts (not) relevant to the U.S. economy

On CRAN:

nlp prediction sentiment-analysis text-mining time-series

6.08 score 82 stars 49 scripts 559 downloads 24 exports 89 dependencies

Last updated 3 years agofrom:c84611b1bc. Checks:OK: 1 NOTE: 8. Indexed: yes.

Target	Result	Date
Doc / Vignettes	OK	Nov 12 2024
R-4.5-win-x86_64	NOTE	Nov 12 2024
R-4.5-linux-x86_64	NOTE	Nov 12 2024
R-4.4-win-x86_64	NOTE	Nov 12 2024
R-4.4-mac-x86_64	NOTE	Nov 12 2024
R-4.4-mac-aarch64	NOTE	Nov 12 2024
R-4.3-win-x86_64	NOTE	Nov 12 2024
R-4.3-mac-x86_64	NOTE	Nov 12 2024
R-4.3-mac-aarch64	NOTE	Nov 12 2024

Exports:add_features as.sentiment as.sento_corpus attributions compute_sentiment corpus_summarize ctr_agg ctr_model get_dates get_dimensions get_hows get_loss_data measures_fill measures_update nmeasures peakdates peakdocs sento_corpus sento_lexicons sento_measures sento_model weights_almon weights_beta weights_exponential

Dependencies:caret class cli clock codetools colorspace cpp11 data.table diagram digest dplyr e1071 fansi farver fastmatch foreach future future.apply generics ggplot2 glmnet globals glue gower gtable hardhat ipred isoband ISOcodes ISOweek iterators jsonlite KernSmooth labeling lattice lava lifecycle listenv lubridate magrittr MASS Matrix mgcv ModelMetrics munsell nlme nnet numDeriv parallelly pillar pkgconfig plyr pROC prodlim progressr proxy purrr quanteda R6 RColorBrewer Rcpp RcppArmadillo RcppEigen RcppParallel RcppRoll recipes reshape2 rlang rpart scales shape SnowballC SQUAREM stopwords stringi stringr survival tibble tidyr tidyselect timechange timeDate tzdb utf8 vctrs viridisLite withr xml2 yaml

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
sentometrics: An Integrated Framework for Textual Sentiment Time Series Aggregation and Prediction	sentometrics-package sentometrics
Add feature columns to a (sento_)corpus object	add_features
Aggregate textual sentiment across sentences, documents and time	aggregate.sentiment
Aggregate sentiment measures	aggregate.sento_measures
Get the sentiment measures	as.data.table.sento_measures
Convert a sentiment table to a sentiment object	as.sentiment
Convert a quanteda or tm corpus object into a sento_corpus object	as.sento_corpus
Retrieve top-down model sentiment attributions	attributions
Compute textual sentiment across features and lexicons	compute_sentiment
Summarize the sento_corpus object	corpus_summarize
Set up control for aggregation into sentiment measures	ctr_agg
Set up control for sentiment-based sparse regression modeling	ctr_model
Differencing of sentiment measures	diff.sento_measures
Monthly U.S. Economic Policy Uncertainty index	epu
Get the dates of the sentiment measures/time series	get_dates
Get the dimensions of the sentiment measures	get_dimensions
Options supported to perform aggregation into sentiment measures	get_hows
Retrieve loss data from a selection of models	get_loss_data
Built-in lexicons	list_lexicons
Built-in valence word lists	list_valence_shifters
Add and fill missing dates to sentiment measures	measures_fill
Update sentiment measures	measures_update
Merge sentiment objects horizontally and/or vertically	merge.sentiment
Get number of sentiment measures	nmeasures
Get number of observations in the sentiment measures	nobs.sento_measures
Extract dates related to sentiment time series peaks	peakdates
Extract documents related to sentiment peaks	peakdocs
Plot prediction attributions at specified level	plot.attributions
Plot sentiment measures	plot.sento_measures
Plot iterative predictions versus realized values	plot.sento_modelIter
Make predictions from a sento_model object	predict.sento_model
Scaling and centering of sentiment measures	scale.sento_measures
Create a sento_corpus object	sento_corpus
Set up lexicons (and valence word list) for use in sentiment analysis	sento_lexicons
One-way road towards a sento_measures object	sento_measures
Optimized and automated sentiment-based sparse regression	sento_model
Subset sentiment measures	subset.sento_measures
Texts (not) relevant to the U.S. economy	usnews
Compute Almon polynomials	weights_almon
Compute Beta weighting curves	weights_beta
Compute exponential weighting curves	weights_exponential