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.

Keep what you just learned

Save these 11 cards to your NoteFren library. Your first review starts right away, and each card links back to the study it came from.

What digital tool was studied?

Woebot, a text-based conversational agent adapted for substance use (W-SUDs).

What study design was used?

Single-group pre–post evaluation of within-subject change.

How large was the analytic sample?

101 participants who registered and initiated W-SUDs.

How long was the treatment window?

8 weeks.

What substance-use outcomes improved?

Past-month use occasions, AUDIT-C, and DAST-10 (overall and among clinical-range cases).

Did depression and anxiety change?

Yes—PHQ-8 and GAD-7 improved (P<.05).

What happened to craving ratings?

By weeks 8–9 they were about half of the week-1 mean.

How common was lifetime GAD in the sample?

48.5% (49/101) reported lifetime generalized anxiety disorder.

What average engagement was reported?

About 15.7 use days over 8 weeks (~2 times/week).

What do authors claim this study is?

First empirical evaluation of an SUD-focused fully automated conversational therapeutic.

What is a major causal limit?

Single-group design cannot separate intervention effects from time/pandemic confounds.