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 CLPsych2026 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 (Task2), we train supervised classifiers on features derived from Task1.1 predictions. To summarize the patterns of mood dynamics and their progression over time within a timeline (Task 3.1), we augment in-context example labels predicted by upstream systems (Tasks 1.1, 1.2, and 2), yielding performance gains over zero-shot and unaugmented in-context learning baselines. Our submission ranked first on Task1.1, fourth on Task1.2, fourth on Task2, and third on Task~3.1.footnote{The source code for the experiments is available at https://github.com/amirzia/clpsych26-cuny

Source: arXiv cs.CL | 2026-05-26