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

TL;DR

This paper develops interpretable models combining psychological traits and language features from social media to predict mental well-being, emphasizing the importance of theory-driven approaches for understanding mental health dynamics.

Contribution

It introduces a novel integration of psychological theories with language models to improve interpretability and prediction of mental health states from social media data.

Findings

Theory-grounded features outperform pure embeddings in interpretability.

Psychological coherence of predictive features validated qualitatively.

Models effectively capture dynamic mental health states in context.

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.