Tools
Interactive browser-based tools for text analysis — no installation required
Each tool is a self-contained Jupyter notebook that runs in your browser — no installation of R or any other software is required. Simply click a launch button below, wait for the environment to load (this may take a minute or two), and start working with your own texts.
ARDC BinderHub
Hosted by the Australian Research Data Commons. More generous computing resources. Requires authentication through an Australian or New Zealand research organisation covered by the AAF or Tuakiri.
mybinder.org
Free and open — no account or institutional login required. Suitable for users outside Australia/New Zealand or without AAF/Tuakiri access. May have lower resource limits.
All Tools at a Glance
Concordancing
KWIC displays for words or phrases
Collocations
Association measures and collocation statistics
Keywords
Over- and under-represented words vs. reference corpus
POS Tagging
Part-of-speech tags for 60+ languages
Corpus Cleaning
Remove or replace words, tags, and patterns
Network Analysis
Generate and visualise network graphs
Topic Modelling
Discover topics across text collections using LDA
Sentiment Analysis
Polarity scoring and eight basic emotion categories
Concordancing
Concordancing Tool
Extract KWIC displays and download the results as a table
The Concordancing Tool creates Keyword-in-Context (KWIC) displays of words or phrases across a single text or collection of texts, and allows you to download the resulting table. Use it to examine how a chosen word or phrase is used in context, to compare usage across texts, or to build evidence for a discourse analysis.
→ Learn more: Concordancing TutorialCollocations
Collocation Tool
Calculate association measures and download the results
The Collocation Tool calculates association measures (collocation statistics) based on your text input and allows you to download the resulting table. Association measures quantify which words are statistically more likely to occur near each other — helping you identify significant phraseological patterns, multi-word expressions, and lexical tendencies in your texts.
→ Learn more: Collocation and N-gram Analysis TutorialKeywords
Keyword Tool
Identify vocabulary distinctive to your texts relative to a reference corpus
The Keyword Tool calculates keyness measures describing how words are over- or under-represented in your texts compared to a reference corpus. This is useful for identifying vocabulary that is distinctive to a particular text, author, genre, or time period — and for contrastive corpus analysis more generally.
→ Learn more: Keyness and Keyword Analysis TutorialPart-of-Speech Tagging
POS Tagging Tool
Add part-of-speech tags to texts in 60+ languages
The POS Tagging Tool adds part-of-speech tags to your texts in more than 60 languages, and allows you to download the tagged output. POS tagging can isolate specific word classes (e.g. all nouns across a corpus), disambiguate words that can function as more than one part of speech, or serve as a pre-processing step for more advanced grammatical analysis.
→ Learn more: Analysing Learner Language TutorialCorpus Text Cleaning
Corpus Cleaning Tool
Remove and replace words, tags, and patterns across your texts
The Corpus Cleaning Tool allows you to remove and replace words, tags, and other elements from uploaded text data, and to download the cleaned texts. Use it to strip repetitive structures — such as XML or HTML markup, speaker labels, document headers, or boilerplate text — that might otherwise distort a subsequent analysis.
→ Learn more: String Processing TutorialNetwork Analysis
Network Analysis Tool
Generate and visualise network graphs from structured edge-list data
The Network Analysis Tool generates and downloads network graphs from your data. Unlike the other tools, this one requires structured data describing edges (connections) and their weights rather than plain text files. Network analysis can visualise and quantify relationships between words, characters, authors, speakers, or any other entities that can be meaningfully connected.
→ Learn more: Network Analysis TutorialTopic Modelling
Topic Modelling Tool
Discover thematic structure in text collections using LDA
The Topic Modelling Tool generates custom topic models using unsupervised and supervised Latent Dirichlet Allocation (LDA), and downloads the results as an Excel spreadsheet. Topic modelling supports distant reading approaches — exploring thematic content across a large collection of texts without reading every document individually.
→ Learn more: Topic Modelling TutorialSentiment Analysis
Sentiment Analysis Tool
Score texts for polarity and eight basic emotion categories
The Sentiment Analysis Tool performs word-level sentiment scoring to estimate whether texts lean positive or negative, and downloads the results as an Excel spreadsheet. It can also examine eight basic emotional associations — anger, fear, anticipation, trust, surprise, sadness, joy, and disgust — of the words in your texts, providing a richer picture of emotional tone across a corpus.
→ Learn more: Sentiment Analysis TutorialReporting Errors
Something not working?
If a tool fails to launch or behaves unexpectedly, please email Martin at m.schweinberger@uq.edu.au. When reporting an error, please include the tool name, which launch option you used (ARDC BinderHub or mybinder.org), and a brief description of what happened. We will investigate and resolve issues as quickly as we can — thank you for letting us know.