@inproceedings{marker-etal-2026-evaluating,
    title = "Evaluating Document-Tuned Transformer Representations for Person-level Mental Health Assessment",
    author = "Marker, Aaron  and
      Kjell, Oscar  and
      Varadarajan, Vasudha  and
      Schwartz, H. Andrew",
    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-1.14/",
    pages = "178--187",
    ISBN = "979-8-89176-421-7",
    abstract = "Person-level psychological assessment requires aggregating meaning across many messages from the same individual, a task that document-level training objectives were not explicitly designed for. We present a systematic, empirical comparison between architecturally matched traditional (a) base-transformers and (b) document-tuned-transformers (further contrastively fine-tuned at the document-level, sometimes referred to as ``sentence transformers'') under otherwise identical conditions. Comparing layer-wise and overall performance across two longitudinal mental health and psychological datasets, we find document-tuned models demonstrated a consistent improvement over base representations (increase in Pearson r of 13.4{\%}, p=.015). Robustness analyses revealed document-tuned models remained more accurate under perturbations to word deletion, synonym replacement, typo injection, and back translation. Further, hedged language (e.g., `usually') was more characteristic of outcomes in document-tuned embeddings while abundance (e.g., `lot') was more characteristic of base-transformers, suggesting document-tuned models may better capture uncertainty.These results suggest representation choice impacts mental health prediction, document-tuned models often being more adept."
}