Process & analyse data
Hands-on tutorials and tools for processing and analysing large collections of language data.
Analysing language data at scale
Being able to analyse large amounts of language data opens up vast possibilities for researchers across disciplines. Language data may also need to be cleaned and processed in other ways to suit your research purposes. We are making tools for text analysis available, alongside our collaborators including Language Technology and Data Analysis Laboratory (LADAL), Sydney Corpus Lab, Sydney Informatics Hub (SIH), QUT Digital Observatory and the Melbourne Data Analytics Platform. Test out tools for processing and analysing data and access analysis and reuse training and tutorials for a diverse range of skill levels.
FEATURED RESOURCE
LDaCA Wordflow
LDaCA Wordflow is a code-free text analytics tool that makes it easier for researchers to explore and analyse text without needing programming skills. Users can build flexible workflows by combining tools for frequency analysis, concordancing, trends, topic modelling and quotation analysis, with results from one tool feeding into the next.
LDaCA Wordflow was developed by the Sydney Informatics Hub and Sydney Corpus Lab
LADAL
The Language Technology and Data Analysis Laboratory (LADAL) is an open-access learning and research platform that helps researchers build skills in working with language data. It provides more than 60 step-by-step tutorials, structured courses and browser-based tools covering data science, statistics, visualisation, text analytics and computational research methods, with resources designed for everyone from complete beginners to experienced researchers.
ANALYTICAL TOOLS & NOTEBOOKS
Explore available tools for language research and work.
No tools available.
GUIDES
FIELD GUIDE
Introduction to Text Analysis
An introduction to working with text as data. Covers key text analysis concepts and the workflow from preparing and analysing text through to documenting and packaging research outputs for reuse.
TECHNOLOGIES GUIDE
Text Analytics
A LADAL tutorial introducing text analysis in R and a range of text analytics methods. Some familiarity with R and RStudio is required, so we recommend being comfortable with the material covered in the R Basics section before getting started.
ON THE BLOG
Analyse image collections with the Image Dataset Explorer
Learn more about how Research Analytics Lead Sam Hames and University of Queensland student Jasper Chong developed the Image Dataset Explorer, a tool for making sense of large image collections. Their work revealed insights that can also be applied to working with text.
Team member tip: There's no substitute for looking closely at the data
Research Analytics Lead Sam Hames shares some advice for making sure that the data you’re working with suits your purposes.
Putting data to work — 2
Learn more about the challenges of working with an unwieldy data source — the Australian Federal Hansard — from Simon Musgrave. In the blog post, Simon unpacks approaches to issues of access and scale allowing for the effective use of this data source.
ADDITIONAL RESOURCES
COLLABORATORS
Interested in contributing to LDaCA?
Do you have data, expertise or resources you'd like to share? We'd love to hear from you.
Interested in contributing to LDaCA?
Do you have data, expertise or resources you'd like to share? We'd love to hear from you.