NTULAW at ROCLING-2025 Shared Task: Domain-Adaptive Modeling of Implicit Emotions in Medical Reflections

Sieh-Chuen Huang, Hsuan-Lei Shao


Abstract
This paper describes the NTULAW team’s participation in the ROCLING 2025 Dimensional Sentiment Analysis (DSA) shared task, which focuses on predicting valence and arousal ratings for Chinese doctors’ self-reflection texts. Unlike previous editions of the DSA task that targeted words, phrases, or educational comments, this year’s dataset consists of domain-specific multi-sentence medical narratives, posing challenges such as low-arousal writing styles, implicit emotion expressions, and discourse complexity. To address the domain shift between general affective resources (Chinese EmoBank) and medical reflections, we designed a multi-scale BERT-based architecture and explored different data selection strategies. Our final system adopted a hybrid submission: using a model trained solely on doctors’ annotations for arousal prediction, and a combined model with Chinese EmoBank for valence prediction. The system achieved stable performance, ranking third among six participating teams. Error analysis shows systematic overestimation of implicit or negated expressions for valence and regression toward mid-range predictions for arousal. We conclude with limitations of relying only on BERT and outline future work involving domain adaptation, discourse-aware modeling, and large language models (LLMs).
Anthology ID:
2025.rocling-main.43
Volume:
Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)
Month:
November
Year:
2025
Address:
National Taiwan University, Taipei City, Taiwan
Editors:
Kai-Wei Chang, Ke-Han Lu, Chih-Kai Yang, Zhi-Rui Tam, Wen-Yu Chang, Chung-Che Wang
Venue:
ROCLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
390–398
Language:
URL:
https://aclanthology.org/2025.rocling-main.43/
DOI:
Bibkey:
Cite (ACL):
Sieh-Chuen Huang and Hsuan-Lei Shao. 2025. NTULAW at ROCLING-2025 Shared Task: Domain-Adaptive Modeling of Implicit Emotions in Medical Reflections. In Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025), pages 390–398, National Taiwan University, Taipei City, Taiwan. Association for Computational Linguistics.
Cite (Informal):
NTULAW at ROCLING-2025 Shared Task: Domain-Adaptive Modeling of Implicit Emotions in Medical Reflections (Huang & Shao, ROCLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.rocling-main.43.pdf