This workshop introduces you to a modern, scalable, and iterative approach to qualitative data analysis (QDA) using AI and other contemporary computational tools. We will work through the full set of QDA fundamentals: organizing data, de-identifying sensitive text, constructing a data set, indexing text segments, coding, memoing, analyzing, retrieving, and representing results. Designed for those with little to no background in QDA software or coding, this course will equip participants from any field with the skills to improve and streamline their analytical process.

Demonstrations and exercises feature an interactive data set, integrating the offline language-model tools in ATLAS.ti, as well as free open-source resources that run in a browser or Python environment. Each session combines short explanations with hands-on practice as we build a sample data set and walk-through common procedures. You will learn to:

• Chart the full workflow of qualitative data analysis, identifying contemporary tools and strategies for each task.
• Use ATLAS.ti 25 to compile and code diverse data types—interviews, ethnographic fieldnotes, focus-group transcripts, open-ended survey questions, PDFs, images, audio, and video—then analyze results inside ATLAS.ti or export them for other software.
• Use automation and deep-readings of data to index, code, and write memos to develop confidence in findings and produce research.
• Use first-pass indexing with regular-expression search, named-entity recognition, and synonym suggestions to ‘chunk’ data, while maintaining the depth of original data.
• Build or refine codebooks and dictionaries for targeted indexing, with help from large-language-model output (does not require sharing data!).
• Create interactive visuals in ATLAS.ti.
• Export coded segments and use free browser-based Python tools to create data visualizations and validation checks.
• Organize comparative analysis across groups, cases, or time points.
• Automate de-identification before any public sharing of data.
• Consider the promise—and cautions—of AI for qualitative work, including bias, misclassification, and responsible deployment.
• Manage multi-researcher projects, track coder agreement, and integrate CAQDA results into mixed-methods studies.

Throughout the seminar we will introduce free and open-source utilities that complement ATLAS.ti for file management, project comparison, and other common tasks.