JMIR Publications

ABSTRACT

Background:

Our prototype smoking cessation chatbot, “Quin”, provides evidence-based, personalised support delivered via smartphone app to help people quit smoking. We developed Quin using a multi-phase program of co-design research, part of which included focus group evaluation of Quin among stakeholders prior to clinical testing.

Objective:

This study aimed to gather feedback on the user-experience of the Quin prototype from end-users and smoking cessation professionals (SCPs) via a beta testing process to inform ongoing chatbot iterations and refinements.

Methods:

Following active and passive recruitment, we conducted online focus groups with nine SCPs and seven end-users from Queensland, Australia. Participants tested the app for 1-2 weeks prior to focus group discussion and could also log conversation feedback within the app. Focus groups of SCPs were completed first to review breadth and accuracy of information, and feedback was prioritised and implemented as major updates using Agile processes prior to end-user focus groups. We categorised logged in-app feedback using content analysis, and thematically analysed focus group transcripts.

Results:

Six focus groups including nine SCPs (Female n=9) and seven end-users (Female n=2) were completed between August 2022 and June 2023. Four SCPs had previously smoked, and most end-users currently smoked cigarettes on a daily (n=3) or less than daily basis (n=2), and two had quit smoking. The mean duration of focus groups was 58 minutes (Range: 46–74 minutes). We identified 4 major themes from focus group feedback: (1) Conversation design; (2) Functionality; (3) Relationality and anthropomorphism; and (4) Role as a smoking cessation support tool. In response to SCPs feedback, we made two major updates to Quin between cohorts: (1) Improvements to conversation flow; and (2) Addition of ‘Moments of Crisis’ conversation tree. Participant feedback also informed 17 recommendations for future smoking cessation chatbot developments.

Conclusions:

Feedback from end-users and SCPs highlighted the importance of chatbot functionality as this underpinned Quin’s conversation design and relationality. The ready accessibility of accurate cessation information and impartial support which Quin provided was recognised as a key benefit for end-users, the latter of which contributed to a feeling of accountability to the chatbot. Findings will inform the ongoing development of a mature prototype for clinical testing.