LLM-Assisted Thematic Analysis Pipeline (Different Minds Lab)

Researcher-led Python pipeline for inductive thematic analysis of interview transcripts, with code extraction, code checking, theme generation and theme checking.

L2Research workflow Source Repository-documented Outcome Not empirically evaluated here

Evidence & verification

Source level

Repository-documented
Grounded in a maintainer repository/README. Availability, stars and forks do not establish research benefit or correctness.

Outcome verification

Not empirically evaluated here
A documented resource or intended workflow, not a demonstrated academic outcome. No empirical benefit is established by its inclusion.

Sources checked

2026-10-17 (UTC)

Repository-described capabilities, not independently demonstrated effectiveness.

Source-checked does not mean independently reproduced. See the Method page for how these labels are assigned.

Sources (1)

Research applicability

Researcher-led Python pipeline for inductive thematic analysis of interview transcripts, with code extraction, code checking, theme generation and theme checking.

Getting started

Read the data/privacy section, configure a de-identified pilot and run the four numbered scripts in order, checking outputs against original transcripts before progressing. These are documentation-based editorial adoption suggestions, not an exercised workflow.

Maintenance

README status is Complete / Exploring a New Direction; future support not independently verified.

License

License not independently audited.

Workflow & human oversight

Human oversight at every stage is the documented intended workflow, not a claim that this editorial review or every pipeline run received human review.

Workflow level is not an evidence score; higher is not better evidence.

Approach

Four scripts call OpenAI with stage-specific prompts, produce structured JSON and log prompts/responses; familiarization and final theme definition/reporting remain manual.

Limitations

Raw interviews are not released; derived de-identified outputs are documented. No runtime or time-saving claims reproduced, and conference presentation and lab affiliation are repository-reported. Model verification does not replace researcher judgment; sending participant text to an external API requires ethics/privacy review.

Reproducibility

Primary repository documentation checked live. No installation, software execution, security audit, or outcome replication performed.

Adoption requirements

Python virtual environment, requirements.txt, an OpenAI API key in the documented API_KEY setting, and appropriately consented transcripts.

Comments

No comments yet.

Add a comment

Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.