CUNY at CLPsych 2026: A Pipeline Approach to Classification and Summarization of Mental Health Changes
arXiv:2605.24164v1 Announce Type: new Abstract: We describe our submission to the CLPsych~2026 Shared Task on capturing and characterizing mental health changes through social media timeline dynamics. To infer the dominant self-states in posts (Tasks 1.1 and 1.2), we ensemble in-context learning of three open-weight large language models using majority voting. For predicting moments of change in a timeline (Task~2), we train supervised classifiers on features derived from Task~1.1 predictions. To summarize the patterns of mood dynamics and their progression over time within a timeline (Task 3.
The proliferation of sophisticated AI models and increasing availability of social media data are enabling more granular analysis of mental health trends, particularly pertinent as AI capabilities advance rapidly.
This work represents a concrete application of AI agents for complex social understanding, directly addressing evolving societal concerns around mental health and the utility of large language models for nuanced prediction.
The development of pipeline approaches combining multiple LLMs and supervised classifiers for mental health monitoring offers a more robust framework for early detection and intervention strategies previously less accessible.
- · Mental Health Tech Startups
- · Social Media Platforms
- · AI/ML Researchers
- · Public Health Institutions
Improved early detection and classification of mental health changes through automated social media analysis.
Ethical and privacy debates intensify regarding the use of AI for sensitive personal health data derived from public platforms.
The development of AI-driven, real-time intervention systems and personalized therapeutic recommendations based on predicted self-states.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL