Part of the HASS and Indigenous Research Data Commons Webinar Series.

This webinar introduces LDaCA Wordflow, a free, open-source app from the Language Data Commons of Australia that brings analysis of large text corpora to anyone, no programming required. The session covers corpus-scale analysis in a point-and-click interface: word frequencies, concordances, trends over time and topic models. You’ll also see this year’s new AI-assisted annotation in action, and the design choices that keep every result traceable to the source text. Your own codebook and hand-coded sample set the standard before a model codes the rest.

The session covers 2 ways to work: in the browser on ARDC infrastructure with nothing to install, or as a desktop app so sensitive data never leaves your machine. You will be able to judge where this could fit in your own research workflow.

Who should attend Researchers in humanities, arts, social sciences and Indigenous studies.

It is of particular interest for:

• Researchers with interview transcripts, survey free text or field notes who want computational help without giving up close reading
• Historians, political scientists, linguists and media scholars working with newspapers, Hansard or social media at a scale beyond manual reading
• GLAM staff and collection custodians who want to see what researchers can do with digitised text
• Researchers and custodians with ethics approval to work with sensitive or access-restricted text, including Indigenous data, who need analysis to stay on their own machine
• Research support staff, librarians and trainers who advise researchers on text analysis tools