大屠杀口述史情感分层诊断
本文在107,305段话、579,013句的大屠杀口述史语料上评估三种预训练Transformer情感分类器，提出基于一致性的ABC分层法来划分模型输出稳定性，报告了两两一致率、Cohen/Fleiss κ和混淆矩阵，并用T5情绪分类器比较各层次的情绪分布。结果显示模型总体一致性偏低到中等，分歧主要出现在中性边界判断，提出了在敏感史料中审慎解读情感模型输出的操作性框架。
原文内容
arXiv:2603.28913v1 Announce Type: new
Abstract: Polarity detection becomes substantially more challenging under domain shift, particularly in heterogeneous, long-form narratives with complex discourse structure, such as Holocaust oral histories. This paper presents a corpus-scale diagnostic study of off-the-shelf sentiment classifiers on long-form Holocaust oral histories, using three pretrained transformer-based polarity classifiers on a corpus of 107,305 utterances and 579,013 sentences. After assembling model outputs, we introduce an agreement-based stability taxonomy (ABC) to stratify inter-model output stability. We report pairwise percent agreement, Cohen kappa, Fleiss kappa, and row-normalized confusion matrices to localize systematic disagreement. As an auxiliary descriptive signal, a T5-based emotion classifier is applied to stratified samples from each agreement stratum to compare emotion distributions across strata. The combination of multi-model label triangulation and the
Abstract: Polarity detection becomes substantially more challenging under domain shift, particularly in heterogeneous, long-form narratives with complex discourse structure, such as Holocaust oral histories. This paper presents a corpus-scale diagnostic study of off-the-shelf sentiment classifiers on long-form Holocaust oral histories, using three pretrained transformer-based polarity classifiers on a corpus of 107,305 utterances and 579,013 sentences. After assembling model outputs, we introduce an agreement-based stability taxonomy (ABC) to stratify inter-model output stability. We report pairwise percent agreement, Cohen kappa, Fleiss kappa, and row-normalized confusion matrices to localize systematic disagreement. As an auxiliary descriptive signal, a T5-based emotion classifier is applied to stratified samples from each agreement stratum to compare emotion distributions across strata. The combination of multi-model label triangulation and the