JMIR Publications

ABSTRACT

Background:

Adolescence is a critical developmental period to prevent and treat the emergence of mental health problems. Smartphones-based conversational agents can deliver psychological driven intervention and support, thus increasing psychological wellbeing over time.

Objective:

The objective of the study was to test the potential of an automated conversational agent named Kai.ai to deliver a self-help program based on ACT tools for adolescents, aimed to increase their wellbeing.

Methods:

Participants were 10,387 adolescents, between the ages of 14-18 years old, who used Kai.ai in on one of the top messaging apps (e.g., iMessage, WhatsApp). Users’ well-being levels were assessed between two and five times using the WHO-5 well-being questionnaire, over their engagement with service.

Results:

Users engaged with the conversational agent an average of 45.39 days (SD = 46.77), in which they have sent a total average of 214.3 messages (SD = 220.24). The average wellbeing score at T1 was 39.09 (SD = 18.15), indicating that, on average, users experienced reduced wellbeing. Multilevel modeling analysis indicated that participants’ wellbeing significantly increased over time (β= 1.62, p < .0001), and reached a clinically acceptable wellbeing average score (above 50).

Conclusions:

Mobile based conversational agents has the potential to deliver engaging and effective way to deliver Acceptance Commitment Therapy (ACT) interventions.