Chatbot-Delivered Interventions on Psychological Health Among Young People: A Systematic Review and Meta-Analysis

Abstract

Background: There exists a notable disparity in meeting the psychological health needs of young people through available services and resources. Chatbots, enabling synchronous interactions between humans and digital devices, hold promise as a technology to assist in filling the treatment gap. This study aims to systematically evaluate the effectiveness, feasibility, and acceptability of chatbot-delivered interventions for young people's psychological health. Methods: We systematically searched 11 databases and search engines covering the publication period from January 2014 to September 2024 to identify eligible interventional studies. Meta-analyses and subgroup analyses were performed on randomized controlled trials to investigate the effectiveness of chatbot-delivered interventions and potential influencing factors. Narrative syntheses were conducted to summarize the feasibility and acceptability of these interventions in all the included studies. Results: We identified 29 eligible interventional studies, of which 13 were randomized controlled trials. The meta-analysis indicated that chatbot-delivered interventions significantly reduced psychological distress, but did not have a significant effect on psychological well-being. The treatment effects observed were influenced by factors including sample type, delivery platform, interaction mode, and response generation approach. Overall, this systematic review demonstrates that chatbot-delivered interventions were feasible and acceptable. Conclusions: Chatbot-delivered interventions have the potential to supplement existing mental health services provided by healthcare professionals.