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

2025-12-08

AI Summary

Current LLM-based mental health support systems often adopt a one-size-fits-all design, failing to accommodate heterogeneous psychological needs and value priorities across user groups. Method: Drawing on large-scale user discussions from six social platforms, we developed a joint analytical pipeline integrating sentiment, opinion, and value-laden discourse analysis, grounded in Value Sensitive Design (VSD) principles. We propose a condition-specific LLM design framework that differentiates requirements by neurodiversity status, high-risk psychiatric conditions, and other clinically relevant subgroups—emphasizing core values including privacy, autonomy, and identity affirmation. Results: Empirical findings reveal consistently positive affective responses among neurodiverse users, whereas individuals with high-risk mental disorders exhibit significantly elevated negative sentiment—validating the necessity of both clinical condition alignment and value embedding. This work contributes a theoretically grounded, empirically validated framework for developing ethically robust, personalized mental health dialogue systems.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Analyzes public sentiment on LLM chatbots for mental health support across conditions.
• Investigates condition-specific user experiences and values like autonomy and privacy.
• Proposes tailored, value-sensitive LLM designs over generic chatbot approaches.

Innovation

• Crowdsourcing user posts from social media platforms
• Using LLM-assisted pipeline with Value-Sensitive Design
• Mapping sentiments, conditions, perspectives, and values