Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Who We Are, Where We Are: Mental Health at the Intersection of Person, Situation, and Large Language Models

Nikita Soni, August Håkan Nilsson, Syeda Mahwish, Vasudha Varadarajan, H. Andrew Schwartz, Ryan L. Boyd

Abstract

Mental health is not a fixed trait but a dynamic process shaped by the interplay between individual dispositions and situational contexts. Building on interactionist and constructionist psychological theories, we develop interpretable models to predict well-being and identify adaptive and maladaptive self-states in longitudinal social media data. Our approach integrates person-level psychological traits (e.g., resilience, cognitive distortions, implicit motives) with language-inferred situational features derived from the Situational 8 DIAMONDS framework. We compare these theory-grounded features to embeddings from a psychometrically-informed language model that captures temporal and individual-specific patterns. Results show that our principled, theory-driven features provide competitive performance while offering greater interpretability. Qualitative analyses further highlight the psychological coherence of features most predictive of well-being. These findings underscore the value of integrating computational modeling with psychological theory to assess dynamic mental states in contextually sensitive and human-understandable ways.

Who We Are, Where We Are: Mental Health at the Intersection of Person, Situation, and Large Language Models

Abstract

Mental health is not a fixed trait but a dynamic process shaped by the interplay between individual dispositions and situational contexts. Building on interactionist and constructionist psychological theories, we develop interpretable models to predict well-being and identify adaptive and maladaptive self-states in longitudinal social media data. Our approach integrates person-level psychological traits (e.g., resilience, cognitive distortions, implicit motives) with language-inferred situational features derived from the Situational 8 DIAMONDS framework. We compare these theory-grounded features to embeddings from a psychometrically-informed language model that captures temporal and individual-specific patterns. Results show that our principled, theory-driven features provide competitive performance while offering greater interpretability. Qualitative analyses further highlight the psychological coherence of features most predictive of well-being. These findings underscore the value of integrating computational modeling with psychological theory to assess dynamic mental states in contextually sensitive and human-understandable ways.
Paper Structure (27 sections, 5 figures, 7 tables)

This paper contains 27 sections, 5 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Background
  3. A Principled Baseline: Integration of Person-Level Traits and Situational Context
  4. Psychological Characteristics of the Situation
  5. Person-Level Traits (PLT)
  6. Human Language Modeling: HaRT for Person-Contextual Embeddings
  7. Data & Tasks
  8. Dataset.
  9. Shared Tasks.
  10. Methods
  11. Situational 8 DIAMONDS (S8D).
  12. Person-Level Traits (PLT).
  13. Person-Contextual Embeddings: HaRT.
  14. Results & Discussion
  15. Well-being Scores.
  16. ...and 12 more sections

Figures (5)

  • Figure 1: Distribution of probabilities to predict adaptive state for a given sentence. On the top is using HaRTWB-FT + PLT features, and the bottom is using PLT features in Logistic Regression models.
  • Figure 2: Qualitative analysis of features in our principled baseline consisting of psychological characteristics of the situation and person-level traits. Left: Pearson correlation coefficients; Right: Ridge regression beta coefficients for predicting well-being with the S8D and PLT features.
  • Figure A1: Distribution of probabilities to predict maladaptive state for a given sentence. On the top is using HaRTWB-FT + PLT features, and the bottom is using PLT features in Logistic Regression models.
  • Figure A2: Distribution of probabilities to predicting adaptive state for a given sentence. On the top is using HaRTWB-FT + ReLM + Distadaptive features, and the bottom is using ReLM + Distadaptive features in Logistic Regression models.
  • Figure A3: Distribution of probabilities to predicting maladaptive state for a given sentence. On the top is using HaRTWB-FT + ReLM + Distmaladaptive features, and the bottom is using ReLM + Distmaladaptive features in Logistic Regression models.