Emotional Reactions and Likelihood of Response to Questions Designed for a Mental Health Chatbot Among Adolescents: Experimental Study

Abstract

Background Psychological distress increases across adolescence and has been associated with several important health outcomes with consequences that can extend into adulthood. One type of technological innovation that may serve as a unique intervention for youth experiencing psychological distress is the conversational agent, otherwise known as a chatbot. Further research is needed on the factors that may make mental health chatbots destined for adolescents more appealing and increase the likelihood that adolescents will use them. Objective The aim of this study was to assess adolescents’ emotional reactions and likelihood of responding to questions that could be posed by a mental health chatbot. Understanding adolescent preferences and factors that could increase adolescents’ likelihood of responding to chatbot questions could assist in future mental health chatbot design destined for youth. Methods We recruited 19 adolescents aged 14 to 17 years to participate in a study with a 2×2×3 within-subjects factorial design. Each participant was sequentially presented with 96 chatbot questions for a duration of 8 seconds per question. Following each presentation, participants were asked to indicate how likely they were to respond to the question, as well as their perceived affective reaction to the question. Demographic data were collected, and an informal debriefing was conducted with each participant. Results Participants were an average of 15.3 years old (SD 1.00) and mostly female (11/19, 58%). Logistic regressions showed that the presence of GIFs predicted perceived emotional valence (β=–.40, P<.001), such that questions without GIFs were associated with a negative perceived emotional valence. Question type predicted emotional valence, such that yes/no questions (β=–.23, P=.03) and open-ended questions (β=–.26, P=.01) were associated with a negative perceived emotional valence compared to multiple response choice questions. Question type also predicted the likelihood of response, such that yes/no questions were associated with a lower likelihood of response compared to multiple response choice questions (β=–.24, P=.03) and a higher likelihood of response compared to open-ended questions (β=.54, P<.001). Conclusions The findings of this study add to the rapidly growing field of teen-computer interaction and contribute to our understanding of adolescent user experience in their interactions with a mental health chatbot. The insights gained from this study may be of assistance to developers and designers of mental health chatbots.

Pharmacogenomic Clinical Decision Support: A Review, How‐to Guide, and Future Vision

“…Somewhat removed from typical workflows, we can find CDS tools, such as chatbots or technological conversation agents. 32 , 33 These are automated systems that patients or clinicians may engage with through a “conversation.” Through these conversations, the tool can gather data and be utilized as a screening system or provide educational content to the user. 34 …”

Chatbots to Support Mental Wellbeing of People Living in Rural Areas: Can User Groups Contribute to Co-design?

“…While many popular mental health chatbots exist, few studies have reported on how user groups can contribute to co-design as it is important to consider the user needs when designing content and features for this application. A few recent studies have involved young people in the design process to co-develop mental health and wellbeing chatbots targeted at under 18 s (Audrey et al, 2021 ; Grové, 2021 ). Another study by Easton et al reported on co-designing content for a health chatbot by involving patients with lived experiences (Easton et al, 2019 ).…”

The Role of AI Chatbots in Mental Health Related Public Services in a (Post)Pandemic World: A Review and Future Research Agenda

“…Confidentiality and data protection [33], [39], [82] Regulatory compliance [33], [39], [83], [82] Localization [51], [83] Trust and transparency [84][85][86] Purposeful and goaloriented designs Personalization and choices [32], [36], [76], [83] Ease of access [54], [58], [87] Participation, engagement, and collaborative design [36], [48], [85][86]…”

“…The use of AI technology in public services is a controversial topic, which necessitates careful consideration of the issues of trust, fairness, and transparency, which should aim to gain citizens' confidence and trust towards the user interface, the technology platform, and the purpose [78], [84][85][86]. Additionally, ethical designs of mental health chatbots require them to be sensitive towards sub-cultural differences and localization aspects, for example, multi-lingual conversational ability [51], [83].…”

“…Personalization and accommodation of users' choices are vital elements driving continued use and engagement for mental health chatbots. Easy and convenient access through Smartphone-based apps and voice-activated agents with selfmonitoring and visual content appeals can promote the uptake of mental health coaching and well-being chatbots, particularly among young people and adolescents [49], [54], [58], [62], [83], [87]. Dosovitsky et al [40] suggest that the designs of mental health chatbots should strike a careful balance between the length and sequence of the modules and complexity levels to sustain users' interest and engagement.…”