"It felt more real": Investigating the User Experience of the MiWaves Personalizing JITAI Pilot Study

TL;DR

Using data from the MiWaves pilot study ($N=122$) focused on emerging adults, this paper presents a structured qualitative-quantitative analysis of user experiences with a RL-powered JITAI for cannabis reduction. An inductive thematic analysis of post-test open-ended responses ($N=105$ completed) alongside engagement metrics reveals three core themes: self-awareness through self-monitoring and My Trends, burden associated with higher-effort message tasks, and partial personalization of message timing. Findings show that self-monitoring and trend visualizations supported reflection and daily integration, while input- and link-exploration tasks increased perceived effort; timing was generally well received, but content personalization was not implemented in this pilot. The work discusses limitations of the pilot design and offers concrete design directions for future iterations, including deeper qualitative methods, flexible scheduling, and content personalization to enhance relevance and reduce burden.

Abstract

Cannabis use among emerging adults is increasing globally, posing significant health risks and creating a need for effective interventions. We present an exploratory analysis of the MiWaves pilot study, a digital intervention aimed at supporting cannabis use reduction among emerging adults (ages 18-25). Our findings indicate the potential of self-monitoring check-ins and trend visualizations in fostering self-awareness and promoting behavioral reflection in participants. MiWaves intervention message timing and frequency were also generally well-received by the participants. The participants' perception of effort were queried on intervention messages with different tasks, and our findings suggest that messages with tasks like exploring links and typing in responses are perceived as requiring more effort as compared to messages with tasks involving reading and acknowledging. Finally, we discuss the findings and limitations from this study and analysis, and their impact on informing future iterations on MiWaves.

Figures (5)

• Figure 1: Screenshots from the MiWaves app. (a) Self-monitoring survey screen -- one of the questions prompting participants to report cannabis use in the past 12 hours, (b) an example of an intervention message providing motivational content to encourage reflection and mindfulness, and (c) the 'My Trends' screen, which displays participants’ self-reported trends in cannabis use, sleep, and exercise over the past week, helping them reflect on their lifestyle habits.
• Figure 2: Overview of the MiWaves pilot study.
• Figure 3: Responses to check-in related questions, which asked the participant about how easy and time-consuming the self-monitoring questions (or check-ins) were, and how comfortable were participants answering personal questions (eg: about their cannabis use, sleep patterns etc.)
• Figure 4: Responses to participant's perception of MiWaves (intervention) message burden -- specifically with respect to the different tasks in intervention messages - namely reading and acknowledging messages, visiting links and typing-in or choosing responses.
• Figure 5: Responses to participant's privacy outlook - i.e. questions asking how comfortable they were with an app collecting data about their location, social media messages, text messages, moving speed, physical activity and sleep.