Team MKC at CLPsych 2026: Capturing and Characterizing Mental Health Changes through Social Media Timeline Dynamics

2026-06-30

AI Summary

This work proposes a unified large language model (LLM)-based computational framework to address the scarcity of professional resources in early detection and continuous monitoring of mental health disorders. By leveraging users’ longitudinal social media texts, the framework enables scalable analysis through an integrated approach that combines post-level fine-grained psychological state assessment with user-level dynamic modeling of mental health trajectories. Experimental results on the CLPsych shared task demonstrate that the method accurately captures and dynamically characterizes individual mental health pathways over time, significantly enhancing capabilities for early warning and ongoing monitoring.

Abstract

Recent advances in Large Language Models (LLMs) have motivated their adoption across a wide range of domains, including Artificial Intelligence (AI) for mental health. Given the growing prevalence of mental health disorders worldwide and the limited accessibility of professional care, there is an increasing demand for scalable computational approaches that can assist in early detection and continuous monitoring of psychological well-being. In this area, ongoing efforts have focused on curating domain-specific datasets and leveraging them to develop LLMs capable of supporting holistic mental health analysis. In line with this direction, we propose an LLM-based pipeline for comprehensive mental health analysis over sequentially ordered user posts, as part of the CLPsych shared task. Our pipeline offers a unified framework that jointly enables post-level assessment and user-level temporal modeling.

Problem

• mental health
• social media
• temporal modeling
• early detection
• timeline dynamics

Innovation

• Large Language Models
• mental health analysis
• temporal modeling
• social media timeline
• user-level dynamics