Perfectly to a Tee: Understanding User Perceptions of Personalized LLM-Enhanced Narrative Interventions
Authors:
- Ananya BhattacharjeeABAnanya Bhattacharjee
- Sarah Yi XuSXSarah Yi Xu
- Pranav RaoPRPranav Rao
- Yuchen ZengYZYuchen Zeng
- Jonah MeyerhoffJMJonah Meyerhoff
- Syed Ishtiaque AhmedSyed Ishtiaque Ahmed
- David C. MohrDMDavid C. Mohr
- Michael LiutMLMichael Liut
- Alex MariakakisAMAlex Mariakakis
- Rachel KornfieldRKRachel Kornfield
- Joseph Jay WilliamsJWJoseph Jay Williams
Open Access
- 4 July 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- Vol. 2025, 1387-1416
Abstract
Stories about overcoming personal struggles can effectively illustrate the application of psychological theories in real life, yet they may fail to resonate with individuals’ experiences. In this work, we employ large language models (LLMs) to create tailored narratives that acknowledge and address unique challenging thoughts and situations faced by individuals. Our study, involving 346 young adults across two settings, demonstrates that personalized LLM-enhanced stories were perceived to be better than human-written ones in conveying key takeaways, promoting reflection, and reducing belief in negative thoughts. These stories were not only seen as more relatable but also similarly authentic to human-written ones, highlighting the potential of LLMs in helping young adults manage their struggles. The findings of this work provide crucial design considerations for future narrative-based digital mental health interventions, such as the need to maintain relatability without veering into implausibility and refining the wording and tone of AI-enhanced content.Keywords
All Related Versions
Funding Information
- National Institute of Mental Health (K01MH125172, R34MH124960)
- Office of Naval Research (N00014-18-1-2755, N00014-21-1-2576)
- National Science Foundation (2209819)
This publication has 98 references indexed in Scilit:
- A comparison of ChatGPT-generated articles with human-written articlesSkeletal Radiology, 2023
- Supporting students with empathy: the association between empathy and coping strategies in pre-clinical medical studentsCurrent Psychology, 2023
- Understanding the user experience of customer service chatbots: An experimental study of chatbot interaction designInternational Journal of Human-Computer Studies, 2022
- An overview of the features of chatbots in mental health: A scoping reviewInternational Journal of Medical Informatics, 2019
- Not the story you want? Assessing the fit of a conceptual framework characterising mental health recovery narrativesSocial Psychiatry and Psychiatric Epidemiology, 2019
- Using Health Chatbots for Behavior Change: A Mapping StudyJournal of Medical Systems, 2019
- Cognitive Restructuring2013
- Mindfulness‐based Narrative Therapy for Depression in Cancer PatientsClinical Psychology & Psychotherapy, 2013
- Dynamic personalization in conversational recommender systemsInformation Systems and e-Business Management, 2013
- Modelling Dynamic Personalization in Web Applications2003