Background Mobile apps have shown considerable promise for reducing alcohol consumption among problem drinkers, but like many mobile health apps, they frequently report low utilization, which is an important limitation, as research suggests that effectiveness is related to higher utilization. Interactive chatbots have the ability to provide a conversational interface with users and may be more engaging and result in higher utilization and effectiveness, but there is limited research into this possibility. Objective This study aimed to develop a chatbot alcohol intervention based on an empirically supported app (Step Away) for reducing drinking and to conduct a pilot trial of the 2 interventions. Included participants met the criteria for hazardous drinking and were interested in reducing alcohol consumption. The study assessed utilization patterns and alcohol outcomes across the 2 technology conditions, and a waitlist control group. Methods Participants were recruited using Facebook advertisements. Those who met the criteria for hazardous consumption and expressed an interest in changing their drinking habits were randomly assigned to three conditions: the Step Away app, Step Away chatbot, and waitlist control condition. Participants were assessed on the web using the Alcohol Use Disorders Identification Test, Adapted for Use in the United States, Readiness to Change Questionnaire, Short Inventory of Problems-Revised, and Timeline Followback at baseline and at 12 weeks follow-up. Results A total of 150 participants who completed the baseline and follow-up assessments were included in the final analysis. ANOVA results indicated that participants in the 3 conditions changed their drinking from baseline to follow-up, with large effect sizes noted (ie, η2=0.34 for change in drinks per day across conditions). However, the differences between groups were not significant across the alcohol outcome variables. The only significant difference between conditions was in the readiness to change variable, with the bot group showing the greatest improvement in readiness (F2,147=5.6; P=.004; η2=0.07). The results suggested that the app group used the app for a longer duration (mean 50.71, SD 49.02 days) than the bot group (mean 27.16, SD 30.54 days; P=.02). Use of the interventions was shown to predict reduced drinking in a multiple regression analysis (β=.25, 95% CI 0.00-0.01; P=.04). Conclusions Results indicated that all groups in this study reduced their drinking considerably from baseline to the 12-week follow-up, but no differences were found in the alcohol outcome variables between the groups, possibly because of a combination of small sample size and methodological issues. The app group reported greater use and slightly higher usability scores than the bot group, but the bot group demonstrated improved readiness to change scores over the app group. The strengths and limitations of the app and bot interventions as well as directions for future research are discussed. Trial Registration ClinicalTrials.gov NCT04447794; https://clinicaltrials.gov/ct2/show/NCT04447794

BACKGROUND Research suggests participant engagement is a key mediator of mHealth alcohol interventions’ effectiveness. Understanding the features that promote user engagement is critical to maximizing the effectiveness of mHealth-delivered interventions. OBJECTIVE The purpose of this study was to identify factors related to mHealth alcohol intervention utilization and engagement amongst hazardous-drinking participants who were randomized to use either an app or Artificial Intelligence (AI) chatbot-based intervention for reducing drinking. METHODS We conducted semi-structured interviews with 20 participants who used the app or chatbot for three months, utilizing thematic analysis to identify common facilitators of their continued use as well as factors that diminished engagement. RESULTS Participants of both interventions reported that tracking their drinking, receiving feedback about their drinking, feeling accountable; and daily notifications about high-risk drinking times and reminders to track their drinking promoted continued engagement. Positivity, personalization, gaining insight into their drinking, and daily tips were stronger facilitator themes among bot users, indicating these may be strengths of the AI chatbot-based intervention when compared to a user-directed app. While tracking drinking was a theme among both groups, it was more salient among app users, potentially due to the option to quickly track drinks in the app that was not present with the conversational chatbot. Notification glitches, technology glitches, and difficulty with tracking drinking data were barriers for both users. Lengthy setup processes was a stronger barrier for app users. Repetitiveness of the bot conversation, receipt of non-tailored daily tips, and inability to self-navigate to desired content were reported as barriers by bot users. Participants in both conditions reported that their engagement with a behaviorally focused mHealth intervention was encouraged by tailored feedback about their alcohol use and timely notifications. CONCLUSIONS To maximize engagement with AI interventions, future developers should include tracking to reinforce behavior change self-monitoring, and be mindful of repetitive conversations, lengthy setup, and pathways that limit self-directed navigation. CLINICALTRIAL ClinicalTrials.gov NCT04447794 INTERNATIONAL REGISTERED REPORT RR2-10.2196/33037

No abstract