@inproceedings{jaff-2026-consensus,
    title = "From Consensus to Split Decisions: {ABC}-Stratified Sentiment in Holocaust Oral Histories",
    author = "Jaff, Daban Q.",
    editor = "Anuradha, Isuri  and
      Wynne, Martin",
    booktitle = "Proceedings of The Second Workshop on Holocaust Testimonies as Language Resources ({HTR}es)",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/revision-previews/2026.htres-2.4/",
    doi = "10.63317/2t969u9fy4gf",
    pages = "29--36",
    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 Holocaust oral histories, using three pretrained transformer-based polarity classifiers over a corpus comprising 107,304 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{'}s {\ensuremath{\kappa}}, Fleiss' {\ensuremath{\kappa}}, and row-normalized confusion matrices to localize systematic disagreement. As an external convergent descriptive signal, we apply a T5-based emotion classifier to stratified samples from each agreement stratum to compare emotion distributions across strata. The combination of multi-model label triangulation and the ABC taxonomy provides a cautious, interpretable framework for characterizing where and how sentiment models diverge in sensitive historical narratives. Inter-model agreement is low to moderate overall and is driven primarily by boundary decisions around neutrality."
}