Simple Sentiment Analysis Using Deep Learning

Sentiment Analysis via deep learning and gradient boosting models with a lot of the underlying hassle taken care of to make the process as simple as possible. In addition to out-performing traditional, lexicon-based sentiment analysis (see <>), it also allows the user to create embedding vectors for text which can be used in other analyses. GPU acceleration is supported on Windows and Linux.

Version: 0.1.1
Depends: R (≥ 4.0.0)
Imports: data.table (≥ 1.12.8), jsonlite, reticulate (≥ 1.16), roperators (≥ 1.2.0), stats, tensorflow (≥ 2.2.0), tfhub (≥ 0.8.0), utils, xgboost
Suggests: rmarkdown, knitr, magrittr, microbenchmark, prettydoc, rappdirs, rstudioapi, text2vec (≥ 0.6)
Published: 2022-03-19
DOI: 10.32614/
Author: Ben Wiseman [cre, aut, ccp], Steven Nydick ORCID iD [aut], Tristan Wisner [aut], Fiona Lodge [ctb], Yu-Ann Wang [ctb], Veronica Ge [art], Korn Ferry Institute [fnd]
Maintainer: Ben Wiseman <benjamin.h.wiseman at>
License: MIT + file LICENSE
NeedsCompilation: no
Materials: README NEWS
In views: NaturalLanguageProcessing
CRAN checks: results


Reference manual:


Package source: sentiment.ai_0.1.1.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): sentiment.ai_0.1.1.tgz, r-oldrel (arm64): sentiment.ai_0.1.1.tgz, r-release (x86_64): sentiment.ai_0.1.1.tgz, r-oldrel (x86_64): sentiment.ai_0.1.1.tgz
Old sources: archive


Please use the canonical form to link to this page.