Rhobots: 'BERTopic'-Style Topic Modeling Without 'Python'

Implements the 'BERTopic' topic modeling pipeline directly in R: transformer-based sentence embedding, Uniform Manifold Approximation and Projection dimensionality reduction, Hierarchical Density-Based Spatial Clustering of Applications with Noise clustering, and class-based term frequency-inverse document frequency topic extraction - all without any dependency on 'Python', 'conda', or 'reticulate'. Every stage runs in R through 'torch', 'safetensors', 'tok', 'uwot', and 'dbscan'. The package mirrors the accessor API of the original 'Python' package, adds integrated quality metrics and hyperparameter search tools, and introduces part-of-speech filtered and C-value-ranked representation models.

Version: 0.1.10
Depends: R (≥ 4.1.0)
Imports: torch, safetensors, hfhub, tok, jsonlite, uwot, dbscan, Matrix, stats, wordpiece, Rcpp
LinkingTo: Rcpp
Suggests: testthat (≥ 3.0.0), plotly, httr2, gutenbergr, udpipe
Published: 2026-08-08
DOI: 10.32614/CRAN.package.Rhobots (may not be active yet)
Author: J.P.G. van der Pol [aut, cre]
Maintainer: J.P.G. van der Pol <j.p.g.vanderpol at uu.nl>
BugReports: https://github.com/JPvdP/RhoBots/issues
License: MIT + file LICENSE
URL: https://github.com/JPvdP/RhoBots
NeedsCompilation: yes
SystemRequirements: Microsoft Visual C++ Redistributable 2022 (Windows only; required by torch)
Materials: README, NEWS
CRAN checks: Rhobots results

Documentation:

Reference manual: Rhobots.html , Rhobots.pdf

Downloads:

Package source: Rhobots_0.1.10.tar.gz
Windows binaries: r-devel: not available, r-release: not available, r-oldrel: not available
macOS binaries: r-release (arm64): Rhobots_0.1.10.tgz, r-oldrel (arm64): not available, r-release (x86_64): Rhobots_0.1.10.tgz, r-oldrel (x86_64): Rhobots_0.1.10.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=Rhobots to link to this page.