Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Jun 11, 2025
Date Accepted: Oct 24, 2025

The final, peer-reviewed published version of this preprint can be found here:

Exploring Body Image Awareness With a Large Language Model–Based Conversational Agent: Qualitative Study With Young Adults

Zhang X, Zayed A, Rehn Hamrin J, Güneysu A, Kuoppamäki S

Exploring Body Image Awareness With a Large Language Model–Based Conversational Agent: Qualitative Study With Young Adults

J Med Internet Res 2025;27:e78829

DOI: 10.2196/78829

PMID: 41248495

PMCID: 12670058

Exploring Body Image Awareness with an LLM-based Conversational Agent: Qualitative Study with Young Adults

  • Xuan Zhang; 
  • Ahmed Zayed; 
  • Josefin Rehn Hamrin; 
  • Arzu Güneysu; 
  • Sanna Kuoppamäki

ABSTRACT

Background:

Body image plays a crucial role in both physical and mental health, influencing outcomes such as self-esteem, eating behaviors, and psychological well-being. Young adults are particularly vulnerable to body dissatisfaction, defined as negative thoughts or feelings about one’s appearance. While there is growing awareness of the benefits of positive body image, characterized by body appreciation and acceptance—few digital interventions are designed to support it in this population.

Objective:

We designed a text-based conversational AI agent integrating biomedical information on eating disorders and the principles of Cognitive Behavioural Therapy to enable open-domain conversations on body image. The study explores young adults’ strategies in maintaining positive body image without the agent, the characteristics of conversations with the agent regarding the conversational topic and content, and the advantages and drawbacks on having a conversation with the agent for body image related queries.

Methods:

A qualitative study consisting of in-depth interviews with young adults was conducted among 15 young adults (aged 20-30) who used a prototype of the AI agent in their homes for a 1-week period. Data comprises of pre-interviews exploring young adults’ maintenance of body image perception without the AI agent, text-based conversations with an AI agent (n=933 messages), and post-interviews on the self-perceived impact of these conversations to body image perception. Interview transcripts and conversations with the AI agent were analysed through thematic analysis.

Results:

Young adults’ body image perception was connected to self-acceptance and confidence and valuing body functionality. Participants used several strategies for improving body image perception without the conversation with the AI agent, ranging from social support networks, exercise and physical well-being and positive self-talk. The conversations with the AI agent were categorised into (1) Body image perception, (2) Body image-related eating and behavioral regulation, (3) Body-focused mindfulness and (4) Social conversation with agent. Three themes in perceived advantages and drawbacks of conversations with the agent were identified (1) Facilitating body image awareness and self-reflection, (2) Availability of conversational support and (3) Discontinuities in user engagement.

Conclusions:

Young adults’ body image perception is closely linked to self-acceptance and self-appreciation. In this context, AI-agent was perceived as an available, accessible, and non-judgemental conversational support in raising awareness on body image perception, which offered possibilities for self-reflection and self-compassion. However, adverse effects may occur in relation to overwhelming messages and declined interest towards maintaining the conversation over time.


 Citation

Please cite as:

Zhang X, Zayed A, Rehn Hamrin J, Güneysu A, Kuoppamäki S

Exploring Body Image Awareness With a Large Language Model–Based Conversational Agent: Qualitative Study With Young Adults

J Med Internet Res 2025;27:e78829

DOI: 10.2196/78829

PMID: 41248495

PMCID: 12670058

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.