Objective quantification of mood states using large language models

2025-02-13

AI Summary

Traditional mental health assessments rely on subjective, label-dependent clinical scales, lacking objective, unobtrusive, and multidimensional quantification of depressive symptoms. Method: We employed the Mistral-7B-OpenOrca large language model (LLM) to encode open-ended depression questionnaire responses, integrating LLM-derived hidden-layer representations with psychometric factor analysis to identify clinically interpretable depressive subspaces; ridge regression was then used to map these latent states to clinical constructs (e.g., somatic-affective distress, suicide severity). Contribution/Results: We propose a novel LLM latent-space-driven paradigm for emotion dimensionality modeling; uncover clinically meaningful depressive subspaces; and demonstrate—without labeled training data—that LLM-based predictions correlate strongly with gold-standard scale scores (r = 0.52–0.84), validating its feasibility and efficacy as an objective, multidimensional tool for affective quantification.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

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

Abstract

Emotional states influence human behaviour and cognition, leading to diverse thought trajectories. Similarly, Large Language Models (LLMs) showcase an excellent level of response consistency across wide-ranging contexts (prompts). We leverage these parallels to establish a framework for quantifying mental states. Our approach utilises self-report questionnaires that reliably assess these states due to their inherent sensitivity to patterns of co-occurring responses. Specifically, we recruited a large sample of participants (N=422) to investigate how well an LLM (Mistral-7B-OpenOrca) quantifies a heterogenous set of depressive mood states measured with participants' open-ended responses to a depression questionnaire. We show LLM responses to held-out multiple-choice questions, given participants' open-ended answers, correlate strongly (r: 0.52-0.84) with true questionnaire scores, demonstrating LLM's generalisation from mood representations. We explore a link between these representations and factor analysis. Using ridge regression, we find depression-related subspaces within LLM hidden states. We show these subspaces to be predictive of participants'"Depression"and"Somatic&Emotional Distress"factor scores, as well as suicidality severity. Overall, LLMs can provide quantitative measures of mental states. The reliability of these hinges upon how informative the questions we ask participants are. Used correctly, this approach could supplement mental state assessment in a variety of settings.

Problem

• Quantify mood states using LLMs
• Assess depression via open-ended responses
• Predict mental health with LLM subspaces

Innovation

• LLMs quantify mental states
• Ridge regression identifies depression
• Factor analysis enhances mood representations