Validate ALI against PAQ-24
A study proposal to check whether ALI (built from transcripts) tracks PAQ-24 in the ways we’d expect, and whether ALI is stable when nothing changes and responsive when something does. ALI is a measurement tool (process/construct marker), not a symptom outcome measure.
What we want to learn
- Does ALI track PAQ-24? Do people with higher PAQ-24 scores also show the expected transcript patterns in ALI (overall and by facet)?
- Is it stable? If someone’s situation hasn’t meaningfully changed, does ALI look reasonably consistent across nearby sessions?
- Do humans agree with the labels? If a trained coder reviews the same excerpts, do they generally agree with ALI’s facet tags?
- Does it move when change should happen? During an intervention that should improve emotion awareness, does ALI shift in the expected direction?
What data we need
- Participants: therapy clients with multiple recorded sessions (so we can look at within-person patterns over time).
- PAQ-24: baseline plus follow-ups aligned to sessions.
- Optional benchmark (performance-based): LEAS (Levels of Emotional Awareness Scale) as a complementary measure of emotional awareness (not self-report). See Lane & Smith (2021).
- Transcripts: speaker turns + timestamps, with clear consent, governance, and redaction workflows.
How we’ll check it
- Facet mapping: does “DIF-like” language line up most with PAQ DIF (and similarly for DDF/EOT)?
- Generalization checks: does it hold across sites, therapists, and populations without changing the marker definitions?
- Human coding: define a coding guide + adjudication rules for a subset of excerpts, then compare to ALI labels.
Who we’re looking for
- US-based academic researchers who can run IRB-approved validation studies with therapy-session transcripts and PAQ-24.
- Emotion / language / clinical measurement labs interested in transparent, evidence-linked approaches to construct validation.
- Graduate students / postdocs who want a clear, publishable validation project with a defined coding protocol.
We prefer US-based partners because HIPAA compliance and data export logistics are usually simpler, but we’re open to conversations and collaboration with researchers outside the US as well.
Ethics, consent, and workflow
This study uses therapy-session transcripts. Any publishable validation should include clear participant consent, data minimization, and an IRB determination appropriate to your site. The goal is to keep ALI auditable (evidence-linked) while minimizing sensitive exposure through governance and redaction.
For governance details, see our Privacy & Compliance guide.