Goal

Test whether adding session-linked, personalized psychoeducation reduces alexithymia symptoms compared to usual care.

What we’re testing

• AI-summarized session topics with emotions: short summaries linked to supporting excerpts, highlighting themes and emotions.
• Dynamic emotion wheel: helps clients find more specific words for what they’re feeling.
• Emotion annotation: guided practice labeling emotions in real excerpts from the session.
• Emotion analytics: simple, interpretable trends over time (e.g., emotion vocabulary and themes).

How we’d run the study

• Simple trial: eligible clients are assigned to therapy-as-usual vs therapy + personalized psychoeducation tools.
• Stepped rollout (optional): phase the tools in over time to see which ones add value (without changing the core therapy session).
• Within-person design (optional): compare the same client before vs after tool access, with repeated symptom measurement.

What we’ll measure

• Primary outcome: PAQ-24 at baseline, end-of-study, and follow-up.
• Engagement (simple): whether clients actually use the tools (views, annotations, time spent).
• Mechanism signals (optional): changes in emotion vocabulary richness and consistency of labeling over time.
• Optional benchmark (performance-based): LEAS (Levels of Emotional Awareness Scale) as a complementary measure of emotional awareness (not self-report). See Lane & Smith (2021).

We treat language-derived signals (e.g., vocabulary richness) as process / mechanism markers. Clinical outcome claims should be anchored to validated outcome measures (here: PAQ-24).

Increased emotion vocabulary does not automatically imply increased emotional understanding; we treat this as a testable hypothesis and validate it against the benchmark measures in the study.

Who we’re looking for

• US-based academic researchers (or clinical research groups) who can run IRB-approved studies with therapy-session text.
• Emotion research labs and applied clinical labs interested in alexithymia, emotion awareness, and skills-based psychoeducation.
• Graduate students / postdocs looking for a tractable, publishable intervention study with clear endpoints.
• Therapists, clinics, and training programs who want to evaluate session-linked psychoeducation tools in real workflows.

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 data handling

This type of intervention is built around real therapy sessions and sensitive text. Any publishable study should include clear participant consent language and an IRB determination appropriate to your site and protocol. The tool should enforce participant-level consent for saving analysis outputs, and support transcript edits/redactions.

For research governance details, see our Privacy & Compliance guide.