@inproceedings{zhang-li-2026-beyond,
    title = "Beyond Prompt-Sensitive Emotion Words: Stable Embeddings for Tang Poetry Analysis",
    author = "Zhang, Linyue  and
      Li, Feiyue",
    editor = {Hamilton, Sil  and
      {\"O}hman, Emily  and
      Hicke, Rebecca M. M.  and
      Bizzoni, Yuri  and
      Bax, Axel  and
      Matthews, Jacob A.  and
      H{\"a}m{\"a}l{\"a}inen, Mika},
    booktitle = "Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities",
    month = jul,
    year = "2026",
    address = "San Diego, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.nlp4dh-1.7/",
    pages = "58--68",
    ISBN = "979-8-89176-427-9",
    abstract = "Many Tang-poetry emotion studies still rely on coarse labels (e.g., positive/negative), while recent LLM-based attempts face a practical problem: one-word emotion outputs are highly sensitive to prompt wording. When labels shift with phrasing, historical interpretation becomes hard to reproduce and hard to trust. Focusing on Tang poetry around the An Lushan Rebellion (安史之乱), we propose a fine-grained sentence-level workflow centered on emotion embeddings: we use continuous hidden-state vectors, run automatic clustering, and then consolidate labels for interpretation. On the same 3,198 emotional sentences, one-word outputs show only 50.3{\%} A/B exact agreement, while embedding-based clustering remains stable and well distributed ($H_{norm}=0.989$; $20/20$ active clusters). On 7,195 labeled sentences, a char-based baseline reaches 0.446 micro-F1 and 0.395 macro-F1. This multi-stage label-construction path supports historically grounded findings, including the emotional turning point around 762, and also reveals layered patterns that are less visible in coarse setups. These results suggest that stable representation is a prerequisite for turning computational outputs into credible evidence for humanities interpretation."
}