LLM Use for Mental Health: Crowdsourcing Users' Sentiment-based Perspectives and Values from Social Discussions

TL;DR

This study analyzes social media discussions to understand how users with different mental health conditions perceive and value LLM chatbots, revealing condition-specific sentiments and guiding more personalized, value-sensitive chatbot designs.

Contribution

It introduces a large-scale, crowdsourced analysis of user sentiments and values regarding LLM chatbots in mental health, grounded in Value-Sensitive Design methodology.

Findings

Neurodivergent users report positive sentiments and support.

High-risk disorder users show more negative sentiments.

User perspectives align with core values like privacy and autonomy.

Abstract

Large language models (LLMs) chatbots like ChatGPT are increasingly used for mental health support. They offer accessible, therapeutic support but also raise concerns about misinformation, over-reliance, and risks in high-stakes contexts of mental health. We crowdsource large-scale users' posts from six major social media platforms to examine how people discuss their interactions with LLM chatbots across different mental health conditions. Through an LLM-assisted pipeline grounded in Value-Sensitive Design (VSD), we mapped the relationships across user-reported sentiments, mental health conditions, perspectives, and values. Our results reveal that the use of LLM chatbots is condition-specific. Users with neurodivergent conditions (e.g., ADHD, ASD) report strong positive sentiments and instrumental or appraisal support, whereas higher-risk disorders (e.g., schizophrenia, bipolar disorder) show more negative sentiments. We further uncover how user perspectives co-occur with underlying values, such as identity, autonomy, and privacy. Finally, we discuss shifting from "one-size-fits-all" chatbot design toward condition-specific, value-sensitive LLM design.