Metraipolis › archive › dc_edfcd3f6ef3e
GCUL: Ambiguity Identification in Text Emotion Classification via Cluster-Guided Learning — arXiv:2609.29327
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29327
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T05:26:31.883Z
- SHA-256 of the archived text
1755144f24bdca0c74149af08368e4430bb5227f28ec98bf5d3c7b60d06d503d- Stable URL of this page
https://metraipolis.com/documento/dc_edfcd3f6ef3e
How to cite
GCUL: Ambiguity Identification in Text Emotion Classification via Cluster-Guided Learning — arXiv:2609.29327 — arXiv (en), https://arxiv.org/abs/2609.29327 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edfcd3f6ef3e (Metraipolis archive dc_edfcd3f6ef3e, sha256 1755144f24bdca0c74149af08368e4430bb5227f28ec98bf5d3c7b60d06d503d)
BibTeX
@misc{dcedfcd3f6ef3e,
title = {GCUL: Ambiguity Identification in Text Emotion Classification via Cluster-Guided Learning — arXiv:2609.29327},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29327},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edfcd3f6ef3e; sha256 1755144f24bdca0c74149af08368e4430bb5227f28ec98bf5d3c7b60d06d503d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29327. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Selective classification enables a model to abstain from predictions on uncertain instances, but existing approaches typically reject them through confidence scores, predefined coverage constraints or instance-level distance measures. These approaches may overlook the collective geometric structure of difficult samples in learned representation spaces. We propose Guided Clustering-based Uncertain Learning (GCUL), a geometric-guided selective classification framework that identifies misclassified and ambiguous instances as a potential confusion attractor in the representation space. GCUL uses a three-phase procedure to initialize, cluster, and explicitly relabel this uncertain region, allowing the rejection boundary to emerge from the underlying representation geometry rather than from a prescribed rejection rate. We further derive a selectivity score and a geometric sufficient condition that characterizes when rejection can provide positive operational utility, enabling pre-deployment feasibility assessment. GCUL improves DistilBERT accuracy from 89.37 percent to 94.98 percent with less than 9 percent rejection. Beyond accuracy, our selectivity score correctly pre-detects the only dataset (GoEmotion) where all baselines fail, and controlled simulations yield 6.1 percent Type-I and 0 percent Type-II errors, validating the sufficient condition's conservatism. These results suggest that collective representation geometry provides a useful alternative perspective for selective prediction. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.LG). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.29327 — 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 2026-10-08T04:50:39.658Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).