A Text Mining Workflow Tool
Overview
Provides a text mining and natural language processing workflow for documents. Includes preprocessing via 'quanteda', lexical analysis (term frequency-inverse document frequency, log-odds ratios, lexical diversity) via 'tidytext', topic modeling via 'stm' and the 'BERTopic' approach, semantic similarity and document clustering on transformer representations, an interactive 'Shiny' interface with 'ggplot2' visualization, optional 'spaCy' preprocessing, and local 'sentence-transformers' or web-based ('OpenAI', 'Gemini') model providers for retrieval-augmented generation, as described in Shin et al. (2026) doi:10.1177/07319487251412879.
- Coded output tells a declined unit from a failed call.
- Confidence outside 0 to 1 is dropped, not clamped.
- Inter-coder agreement reports the unit count each statistic used.
- Coded assignments export as CSV or Excel.
- Added
estimate_topic_effects()for STM prevalence effects. - Fixed neural-classifier sentiment scoring.
- Prevented the hosted app from crashing on large datasets.
From NEWS.md in the release
Install
Health
- OK13 OK2026-08-05
- NOTE11 OK, 1 NOTE2026-08-01
- OK7 OK2026-07-28
Documentation
- Help pages
- 228 (87 internal)includes a package overview page
- Examples that run
- 54%42 run in a plain check (39 of them under a condition) · 36 only when donttest examples are enabled (R CMD check --as-cran)
- Exported functions with examples
- 50%
- Documented parameters
- 100%
- Return-value docs
- 100%
- Help pages citing references
- 1%
- Accessibility HTML
- AI Integration HTML
- Getting Started HTML
- Installation HTML
- Lexical Analysis HTML
- Multimodal Analysis HTML
- Preprocessing HTML
- Python Environment HTML
- Qualitative Coding HTML
- Security HTML
Show 2 moreHide 2 vignettes
- Semantic Analysis HTML
- Topic Modeling HTML
Downloads
Repository
Stars over time
Commits over time
8 development-tooling and community-health practices detected across 5 families in the upstream repository
Checks run against github.com/mshin77/textanalysisr on 2026-10-18.
The R CMD check workflow runs on Linux, macOS and Windows, and on R-devel
GitHub Pages site last deployed 2026-10-18
pkgdown site last built 2026-08-19, before release 0.1.5 (2026-09-13)
Show all practicesHide 1 practice
Dependencies
Installing TextAnalysisR adds 82 packages (45 with compiled code, 74 MB of source tarballs). Heaviest: stringi 11 MB, ggplot2 6.0 MB, bslib 5.6 MB.
Code & Tests
Datasets
People & History
Pick two releases to compare their code metrics.
- 0.1.5Latest2026-09-13 · current release · diff ↗ ·
added 17 exports
add_memo, align_categories, apply_codes, assign_noise, cluster_embedding_topics, code_agreement, code_retest, detect_language, detect_language_llm, estimate_topic_effects, get_memos, log_round, merge_codes, round_summary, split_texts, uncoded_units, validate_categories - 0.1.42026-07-27
- RR 4.6.0 released · 2026-04-24
Package metadata
- First published
- 2026-07-27
- Total releases
- 2 / 1 yrs
- License
- GPL (>= 3) OSI
- Minimum R
- ≥ 4.0
- Bundled data
- 595 KB / 4 files
- Download size
- 2.9 MB
Cite
Cite this package
Run in R for the authors' entry:
citation("TextAnalysisR")The package provides a citation file, so citation() returns the authors' own entry.
Cite the R Observatory
For a number measured here: a download total, a coverage figure, an archival date.
From data release v2026-10-22, which the citation names so these numbers can be found later. More on citing and the projects behind them.