Metraipolis › archive › dc_d08c574d3afa
Distilling Literary Sentiment from LLM Annotations into an Ordinal BERT Model — arXiv:2611.02985
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02985
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:23:47.764Z
- SHA-256 of the archived text
6c323eda2bf29990364764482f9e5f08c5d42883eb74ce9e85232838e6bdffbe- Stable URL of this page
https://metraipolis.com/documento/dc_d08c574d3afa
How to cite
Distilling Literary Sentiment from LLM Annotations into an Ordinal BERT Model — arXiv:2611.02985 — arXiv (en), https://arxiv.org/abs/2611.02985 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d08c574d3afa (Metraipolis archive dc_d08c574d3afa, sha256 6c323eda2bf29990364764482f9e5f08c5d42883eb74ce9e85232838e6bdffbe)
BibTeX
@misc{dcd08c574d3afa,
title = {Distilling Literary Sentiment from LLM Annotations into an Ordinal BERT Model — arXiv:2611.02985},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02985},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d08c574d3afa; sha256 6c323eda2bf29990364764482f9e5f08c5d42883eb74ce9e85232838e6bdffbe},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02985. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The scarcity of human-annotated literary corpora limits the development of domain-specific sentiment analysis models. This study investigates whether LLM-generated annotations can supervise smaller models for literary sentiment analysis. We fine-tune five BERT models using ordinal regression on 10,889 literary sentences annotated by Gemma 4 31B on a ten-point sentiment scale. The models are evaluated against 1,923 human-annotated sentences from Hemingway's "The Old Man and the Sea", alongside the teacher model and conventional baselines. BERT-large achieves a Kendall's $\tau$ of 0.589, approaching the teacher's 0.604. Although a constant-neutral predictor achieves the lowest overall mean absolute error (MAE), BERT-base outperforms the teacher on non-neutral sentences, achieving an MAE of 0.726 versus 1.116. These findings demonstrate the potential of LLM-generated supervision for developing smaller literary sentiment models, while highlighting the limitations of aggregate error metrics on predominantly neutral datasets. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.02985 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T18:10:07.985Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).