Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cloning the Self for Mental Well-Being: A Framework for Designing Safe and Therapeutic Self-Clone Chatbots

Mehrnoosh Sadat Shirvani, Jackie Crowley, Cher Peng, Jackie Liu, Thomas Chao, Suky Martinez, Laura Brandt, Ig-Jae Kim, Dongwook Yoon

TL;DR

Self-clone chatbots offer a novel route for intra-personal mental-well-being support but raise risks around identity, reinforcement of maladaptive patterns, and user autonomy. The authors adopt an interpretive, design-oriented study with 16 mental-health experts and 6 prospective users to derive a practical three-component framework: therapeutic grounding, design dimensions, and safety/ethics. This framework, informed by empirical insights and established therapeutic modalities (e.g., parts-based therapy, compassion-focused therapy, CBT), guides responsible development of non-clinical self-clone tools and clarifies roles for designers, clinicians, researchers, and policymakers. The work advances an interdisciplinary foundation for AI-mediated self-interaction that is emotionally and ethically attuned, with implications for scalable, user-centered mental health support and governance.

Abstract

As digital tools increasingly mediate mental health care, self-clone chatbots can offer a uniquely novel approach to intra-personal exploration and self-derived support. Trained to replicate users' conversational patterns, self-clones allow users to talk to themselves through their digital replicas. Despite the promises, these systems may carry risks around identity confusion, negative reinforcement, and blurred user agency. Through interviews with 16 mental health professionals and 6 general users, we aim to uncover tensions and design opportunities in this emerging space to guide responsible self-clone design. Our analysis produces a design framework organized around three priorities: (1) defining goals and grounding the approach in existing therapeutic models, (2) design dimensions including the self-clone persona and user-clone relationship dynamics, and (3) considerations for minimizing potential emotional and ethical harms. This framework contributes an interdisciplinary foundation for designing self-clone chatbots as AI-mediated self-interaction tools that are emotionally and ethically attuned in mental health contexts.

Cloning the Self for Mental Well-Being: A Framework for Designing Safe and Therapeutic Self-Clone Chatbots

TL;DR

Self-clone chatbots offer a novel route for intra-personal mental-well-being support but raise risks around identity, reinforcement of maladaptive patterns, and user autonomy. The authors adopt an interpretive, design-oriented study with 16 mental-health experts and 6 prospective users to derive a practical three-component framework: therapeutic grounding, design dimensions, and safety/ethics. This framework, informed by empirical insights and established therapeutic modalities (e.g., parts-based therapy, compassion-focused therapy, CBT), guides responsible development of non-clinical self-clone tools and clarifies roles for designers, clinicians, researchers, and policymakers. The work advances an interdisciplinary foundation for AI-mediated self-interaction that is emotionally and ethically attuned, with implications for scalable, user-centered mental health support and governance.

Abstract

As digital tools increasingly mediate mental health care, self-clone chatbots can offer a uniquely novel approach to intra-personal exploration and self-derived support. Trained to replicate users' conversational patterns, self-clones allow users to talk to themselves through their digital replicas. Despite the promises, these systems may carry risks around identity confusion, negative reinforcement, and blurred user agency. Through interviews with 16 mental health professionals and 6 general users, we aim to uncover tensions and design opportunities in this emerging space to guide responsible self-clone design. Our analysis produces a design framework organized around three priorities: (1) defining goals and grounding the approach in existing therapeutic models, (2) design dimensions including the self-clone persona and user-clone relationship dynamics, and (3) considerations for minimizing potential emotional and ethical harms. This framework contributes an interdisciplinary foundation for designing self-clone chatbots as AI-mediated self-interaction tools that are emotionally and ethically attuned in mental health contexts.
Paper Structure (34 sections, 4 figures, 1 table)

This paper contains 34 sections, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Works
  3. AI Clones and LLM-based Chatbots
  4. Landscape of Mental Health Chatbots
  5. Self-Sourced Mental Well-Being Support
  6. AI Outlook in Mental Health
  7. Method
  8. Participants
  9. Data Collection
  10. Data Analysis
  11. Design Framework
  12. Therapeutic Grounding and User Considerations
  13. Therapeutic Approaches and Theories
  14. Targeted User Groups Considerations
  15. Design Dimensions
  16. ...and 19 more sections

Figures (4)

  • Figure 1: Overview of the key components of the proposed design framework.
  • Figure 2: Concept 1 – Mindshift: A self-clone that helps manage work-related emotions by challenging negative thoughts using personal context.
  • Figure 3: Concept 2 – Future You: A self-clone representing a hopeful future self offering reassurance and perspective based on possible positive outcomes.
  • Figure 4: Concept 3 – Inner Coach: A self-clone acting as a personalized coach, guiding self-improvement through tailored, experience-based support.