Talking to an AI mirror : designing self-clone chatbots for enhanced engagement in digital mental health support

As mental health support becomes increasingly digitized, chatbots have emerged as promising tools for immediate, cost-effective remedies. These conversational agents have the potential to deliver valuable therapeutic impact, but low user engagement remains a critical barrier hindering their efficacy. Existing therapeutic approaches have leveraged clients’ internal dialogues (e.g., journaling, talking to an empty chair) to enhance engagement through accountable, self-sourced support. Inspired by these, we aimed to design, implement, and evaluate novel AI-driven self-clone chatbots replicating users’ support strategies and conversational patterns to improve therapeutic engagement through externalized meaningful self-conversation. To ensure the therapeutic safety and effectiveness of self-clone chatbots, we analyzed insights from 16 expert interviews with mental health professionals to identify key design considerations that informed our final chatbot principles. Validated through a controlled experiment (N=180), significantly higher emotional and cognitive engagement was demonstrated with self-clone chatbots than a chatbot with a generic counselor persona. This finding was consistent in a follow-up study with a subgroup of participants (N=66) conducted after a 10-week period to mitigate any novelty effects. Our findings highlight self-clone believability as a mediator and emphasize the balance required in maintaining convincing self-representation while creating positive interactions. This work contributes to AI-based mental health interventions by introducing and evaluating self-clones as a promising approach to increasing the efficacy of conversational agents while offering insights into their design and exploring implications for their application in mental health care.