@inproceedings{naskar-conway-2026-hierarchical,
    title = "Hierarchical Multi-Stage Modeling of Adaptive and Maladaptive Self-States in Social Media Timelines",
    author = "Naskar, Abir  and
      Conway, Mike",
    editor = "Zirikly, Aya  and
      Bar, Kfir  and
      MacAvaney, Sean  and
      Ireland, Molly  and
      Ophir, Yaakov  and
      Atzil-Slonim, Dana  and
      Varadarajan, Vasudha  and
      Bedrick, Steven  and
      Desmet, Bart",
    booktitle = "Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology ({CLP}sych 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.clpsych-1.37/",
    pages = "472--481",
    ISBN = "979-8-89176-421-7",
    abstract = "We address the CLPsych 2026 Shared Task on modeling psychological self-states from longitudinal social media data. We propose (i) a hierarchical multi-stage framework that integrates a multi-task transformer encoder and (ii) a four stage instruction-tuned large language model finetuning pipeline for subelement classification, presence estimation, and evidence extraction. Our approach incorporates element-conditioned label masking and cross-stage encoder transfer, enabling structured prediction aligned with the ABCD psychological framework. Experiments show improvements over the baseline on the development setup, with RoBERTa achieving an 8.3{\textbackslash}{\%} gain in macro-F1 and improved RMSE, while a fine-tuned Qwen3 model attains the best overall performance. These results demonstrate the effectiveness of combining hierarchical multi-task learning with structured generation for interpretable mental health analysis."
}