Skip to main content

Text & Corpus Tools

text-analysis
corpus-linguistics
topic-models
digital-humanities
Point-and-click and desktop tools for text analysis, concordances, topic modeling, and handwritten-text recognition, for researchers working without R.
Published

2 November 2026

This guide covers tools for analysing collections of text without writing R code: browser and desktop programs for word frequencies and concordances, topic modeling, very large digital libraries, and turning handwritten archives into searchable text. Begin with the three picks under Start here. If you work in R, the R Text Analysis guide is the place to go.

Start here

  • Voyant Tools — Browser-based environment for reading and analysing texts you paste or upload, with word clouds, frequency trends, and keywords in context.
  • AntConc — Laurence Anthony’s freeware concordance program for searching a corpus, with documentation and older releases on the same page.
  • Text Mining Tools and Methods (University of Illinois Library) — Library guide introducing text mining methods and the tools available for each.

Concordance and corpus tools

  • CasualConc — Concordance program that runs natively on macOS.
  • KH Coder — Desktop software for quantitative content analysis and text mining.
  • Tools for Corpus Linguistics — Searchable directory of tools for building and analysing corpora, sorted by tag.
  • Voyant Server — Desktop edition of Voyant Tools that runs locally on your machine for private corpora and offline analysis.

Topic modeling without R

Large collections and archives

  • HathiTrust Bookworm — HathiTrust Research Center app for charting word use across the HathiTrust digital library; it replaced the retired HTRC Analytics portal.
  • Transkribus — AI platform that turns scans of handwritten documents into searchable text; it has free and paid tiers.

Learning computational social science

  • SICSS Learning Materials — Videos and code from the Summer Institutes in Computational Social Science, including sessions on text as data and research ethics.