Development of a chatbot for depression: adolescent perceptions and recommendations

Abstract

Background: Chatbots are a relatively new technology that has shown promising outcomes for mental health symptoms in adults; however, few studies have been done with adolescents or reported adolescent user experiences and recommendations for chatbot development. Methods: Twenty three participants ages 13-18 (M age = 14.96) engaged in user testing of a chatbot developed to psychoeducate adolescents on depression, teach behavioral activation, and change negative thoughts. Thematic analysis was conducted of participants' responses to user experience questions, impressions, and recommendations. Results: Over half (56.5%) of the sample completed the full intervention and provided user experience feedback online. The average NPS score was 6.04 (SD = 2.18), and 64.3% (n = 9) said they would use the chatbot in the future. Of all user experience responses, 54.5% were positive. The most common impressions were related to symptom improvement (61.1%) and availability (52.8%) The most frequent recommendations were related to solving technical problems (66%). Conclusions: Chatbots for mental health are acceptable to some adolescents, a population that tends to be reluctant to engage with traditional mental health services. Most participants reported positive experiences with the chatbot, believing that it could help with symptom improvement and is highly available. Adolescents highlighted some technical and stylistic problems that developers should consider. More pilot and user testing is needed to develop mental health chatbots that are appealing and relevant to adolescents. Key practitioner message• Chatbots are a relatively new technology; however, few studies have been done with adolescents.• Most adolescents perceived the chatbot positively and believed that it could help with symptom improvement and that it is highly available. • Chatbots for mental health are acceptable to some adolescents, a population that tends to be reluctant to engage with traditional mental health services.

Use of automated conversational agents in improving young population mental health: a scoping review

“…Of the 25 studies, 19 were recently published (between 2020 and 2023) 8 – 10 , 12 , 26 – 40 . Studies were conducted predominantly in the US ( n = 12) 11 , 12 , 27 , 28 , 33 , 34 , 38 , 41 – 45 , followed by Europe ( n = 5) 10 , 26 , 29 , 32 , 35 , Asia ( n = 4) 9 , 31 , 36 , 39 , New Zealand ( n = 2) 37 , 40 , and Australia ( n = 1) 30 .…”

“…Only 3 of the CA were the focus of more than one study – Paro 11 , 41 , 45 , Nao 8 , 38 , and Woebot 12 , 42 . These automated CAs were predominantly disembodied chatbots ( n = 15) 10 , 26 , 28 – 32 , 35 – 37 , 40 , 42 – 44 , followed by robots ( n = 7) 8 , 9 , 33 , 34 , 38 , 41 , 45 . Automated CAs with a virtual representation were the focus in 2 studies 11 , 27 .…”

“…Regarding the dialog system underlying the process of conversation, almost half of automated CAs ( n = 12) employed natural language processing and machine learning to carry on an interaction 8 , 9 , 12 , 27 , 30 , 31 , 34 , 38 , 39 , 41 , 43 , 45 . Predefined dialog or interactions assembled, and matched to the user input in a dynamic manner was used in 10 studies 10 , 11 , 26 , 28 , 29 , 32 , 33 , 35 , 40 , 44 , while 3 used a mixed dialog system 36 , 37 , 42 . These agents communicated through text ( n = 13) 10 , 12 , 26 , 28 – 30 , 32 , 35 , 37 , 40 , 42 – 44 , speech ( n = 2) 8 , 38 , and non-verbal cues ( n = 4) 9 , 34 , 41 , 45 , while multiple modalities communication was employed by 5 studies 11 , 31 , 33 , 36 , 39 .…”

“…Predefined dialog or interactions assembled, and matched to the user input in a dynamic manner was used in 10 studies 10 , 11 , 26 , 28 , 29 , 32 , 33 , 35 , 40 , 44 , while 3 used a mixed dialog system 36 , 37 , 42 . These agents communicated through text ( n = 13) 10 , 12 , 26 , 28 – 30 , 32 , 35 , 37 , 40 , 42 – 44 , speech ( n = 2) 8 , 38 , and non-verbal cues ( n = 4) 9 , 34 , 41 , 45 , while multiple modalities communication was employed by 5 studies 11 , 31 , 33 , 36 , 39 . For one study no information was provided on modality of communication 27 .…”

“…Anxiety was the most frequent targeted emotional component of mental health by automated CAs ( n = 12) 8 , 10 , 12 , 27 , 33 , 35 , 37 , 38 , 41 – 43 , 45 . Depression was the second most targeted emotional component ( n = 8) 12 , 28 , 31 , 35 , 36 , 38 , 42 , 43 , followed by psychological well-being ( n = 5) 26 , 29 , 30 , 33 , 44 , general distress ( n = 5) 9 , 10 , 34 , 39 , 40 , and mood ( n = 2) 33 , 41 . One intervention had as target mental health problems as a broad construct 32 .…”