Woebot chatbot for substance use
An 8-week fully automated Woebot SUD program showed pre–post drops in substance use, cravings, depression, and anxiety in a single-group study.
Source
A Therapeutic Relational Agent for Reducing Problematic Substance Use (Woebot): Development and Usability Study
Study at a glance
- Design
- Human experiment — Single-group 8-week pre–post usability/feasibility evaluation (no control)
- N
- N=101 · 101 enrolled; 51 completed the post-treatment survey
- Population
- Adults initiating a therapeutic chatbot for problematic substance use
- Outcome
- Past-month use occasions, AUDIT-C/DAST-10, cravings, PHQ-8, GAD-7 over 8 weeks
Structured fields used in claim comparison tables when every cited study has a complete layer.
Inspect source passages
Woebot chatbot for substance use
These passages occur verbatim in the stored paper text. They support the points listed below; they do not verify every statement in the explanation.
101 participants formed the analytic sample
The analytic sample consisted of 101 participants who ultimately registered with W-SUDs and initiated use.
48.5% reported lifetime GAD
Most (73/101, 72.3%) reported a lifetime psychiatric diagnosis, most commonly generalized anxiety disorder (49/101, 48.5%) and unipolar depression (45/101, 44.6%), with 47.5% (48/101) reporting multiple lifetime psychiatric diagnoses; few (6/101, 5.9%) reported a SUD diagnosis, 43.6% (44/101) were currently taking psychiatric medication, and 25.7% (26/101) were currently in therapy.
What they did
101 adults who started Woebot for substance use (W-SUDs) completed an 8-week single-group pre–post evaluation of use occasions, AUDIT-C/DAST-10, cravings, confidence, PHQ-8, GAD-7, and pain.
What they found
Past-month use occasions, AUDIT-C, DAST-10, PHQ-8, and GAD-7 improved (all P<.05). In-app craving ratings fell roughly by half by weeks 8–9. Engagement averaged about 15.7 use days over 8 weeks. Authors call the approach feasible and acceptable but note the need for controlled efficacy trials.
The limits
What it doesn't show
Without a control group, pandemic-era substance-use shifts and regression to the mean can explain change. Few participants had diagnosed SUD, and posttreatment completers were a subset of enrollees.
Key terms
- Woebot / W-SUDs
- Text conversational agent adapted for substance-use treatment.
- Conversational agent
- Automated chatbot delivering therapeutic check-ins and skills.
- AUDIT-C
- Brief alcohol screening/severity measure.
- DAST-10
- Drug Abuse Screening Test score for drug-use problems.
- PHQ-8
- Eight-item depression symptom scale used here.
- Single-group pre–post design
- Everyone receives the intervention; change is within-person over time.
Flashcards
0 of 11 answers reviewed
Research intelligence for this paper
See its role on concept claims, tensions it is part of, placement history, and related discoveries.
Quiz yourself
What delivery modality was tested?
Common questions
How many started W-SUDs?
Analytic sample of 101 participants.
What mood scales were used?
PHQ-8 for depression and GAD-7 for anxiety.
Did cravings change?
Yes—ratings were about half of week-1 levels by weeks 8–9.
Was there a control arm?
No; it was a single-group pre–post study.
More on mHealth