LoginSign Up
← Back to all sparks
T

tall

ANALYTICS
Velocity0.0

R package tall by massimoaria — release notes from GitHub.

github.com/massimoaria/tall ↗

A Shiny text-mining GUI grows into a full NLP workbench at 1.0.0

text-analysisnlpshinytopic-modelingcpp-backendllm-integration
◆Current state
tall is a graphical text-analysis environment that wraps a dependency-parsing NLP pipeline in a Shiny interface, aimed at researchers who want corpus analysis without writing R. The 1.0.0 release consolidates a year of module additions into a broad analysis surface: SVO triplet extraction, document-level syntactic complexity, NRC-lexicon emotion analysis, noun-phrase extraction and correlated/structural topic models. Performance-sensitive paths are pushed into C++ backends rather than R.
◆Where it's heading
The arc is consistent: each release bolts another named analysis method onto the Documents section, each with its own Run/Export/Report UI, and moves the hot loop into C++. The second thread is the embedded Gemini assistant, introduced in 0.3.0 and by 1.0.0 wired into every switch point of the new modules. Reporting plumbing — Add to Report, image and Excel export — has been retrofitted across older modules to match.
◆Prediction
Expect the next releases to continue the pattern of adding one or two named analysis methods with matching export and AI hooks, and to extend the C++ rewrite to modules that have not yet been converted.

◆Recent moves

  1. 4mo ago

    tall 1.0.0 adds SVO, emotion and syntactic-complexity analysis

    ⚡ SPARK

    The 1.0.0 milestone lands four new analysis families at once — SVO triplets, syntactic complexity, NRC emotion analysis and noun-phrase extraction — plus CTM and STM topic models, each with a C++ backend and a matching export/report UI. It is the point where the incremental module-per-release arc becomes a broad workbench.

    View source ↗
  2. 6mo ago

    Report and image export retrofitted across Overview and Keyness

    Add to Report and Export Images buttons reach the Overview, Keyness and KWIC Network modules, closing the gap between older modules and the export plumbing newer ones shipped with. Table layout is tidied across several modules alongside fixes to Split and Import.

    View source ↗
  3. 8mo ago

    tall 0.5.1

    A maintenance release: retired Gemini 1.5 and 2.0 model options, an API key check fix and a synonym-merging fix. The model removal is housekeeping against upstream deprecation rather than a change in what the assistant does.

    View source ↗
  4. 8mo ago

    Supervised classification module and a 200x C++ rewrite

    The largest release before 1.0.0: a full supervised classification interface with DTM and embedding workflows, two-corpus Keyness comparison, and Morrone's IS index for multi-word detection. The txt_recode and applyRake rewrites in C++ are reported at roughly 200x, and ui.R/server.R are split into per-module files — the refactor that made the 1.0.0 module burst practical.

    View source ↗
  5. 1y ago

    TALL AI assistant introduced

    A one-line release note introducing the in-app assistant, TALL AI. The entry carries little detail on its own, but later releases show it becoming a standing fixture — by 1.0.0 it is wired into every switch point of each new analysis module.

    View source ↗