Role-Guided Annotation and Prototype-Aligned Representation Learning for Historical Literature Sentiment Classification

Hongfei Du, Jiacheng Shi, Jacobo Myerston, Sidi Lu, Gang Zhou, Ashley Gao


Abstract
Sentiment analysis of historical literature provides valuable insights for humanities research, yet remains challenging due to scarce annotations and limited generalization of models trained on modern texts. Prior work has primarily focused on two directions: using sentiment lexicons or leveraging large language models (LLMs) for annotation. However, lexicons are often unavailable for historical texts due to limited linguistic resources, and LLM-generated labels often reflect modern sentiment norms and fail to capture the implicit, ironic, or morally nuanced expressions typical of historical literature, resulting in noisy supervision. To address these issues, we introduce a role-guided annotation strategy that prompts LLMs to simulate historically situated perspectives when labeling sentiment. Furthermore, we design a prototype-aligned framework that learns sentiment prototypes from high-resource data and aligns them with low-resource representations via symmetric contrastive loss, improving robustness to noisy labels. Experiments across multiple historical literature datasets show that our method outperforms state-of-the-art baselines, demonstrating its effectiveness.
Anthology ID:
2025.findings-emnlp.201
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3756–3768
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.201/
DOI:
Bibkey:
Cite (ACL):
Hongfei Du, Jiacheng Shi, Jacobo Myerston, Sidi Lu, Gang Zhou, and Ashley Gao. 2025. Role-Guided Annotation and Prototype-Aligned Representation Learning for Historical Literature Sentiment Classification. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 3756–3768, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Role-Guided Annotation and Prototype-Aligned Representation Learning for Historical Literature Sentiment Classification (Du et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.201.pdf
Checklist:
 2025.findings-emnlp.201.checklist.pdf