@inproceedings{munda-etal-2026-benchmarking,
    title = "Benchmarking {LLM}s for Aspect-Based Sentiment Classification in {S}lovene Historical Periodicals",
    author = "Munda, Tina  and
      Dobrani{\'c}, Filip  and
      {\v{S}}majdek, Uro{\v{s}}  and
      Peji{\'c}, Oliver  and
      Bohak, Ciril  and
      Gorjanc, Vojko  and
      Fi{\v{s}}er, Darja",
    editor = "Montejo-Raez, Arturo  and
      Grisot, Cristina  and
      Blochowiak, Joanna  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Battaner, Elena  and
      Rigau, German",
    booktitle = "Proceedings of Shaping Multilingual, Multimodal {AI} for the Social Sciences and Humanities ({LLM}s4{SSH}) @ {LREC} 2026",
    month = may,
    year = "2026",
    address = "Palma de Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/revision-previews/2026.llms4ssh-1.11/",
    doi = "10.63317/22hvcbc23rts",
    pages = "103--113",
    abstract = "Historical newspapers present substantial challenges for computational sentiment analysis due to OCR noise, archaic linguistic features, and the absence of domain-specific labeled training data. This paper examines whether instruction-following LLMs can support targeted, mention-level sentiment inference in such conditions. We benchmark four instruction-following LLMs on a manually annotated sample of collective-identity mentions drawn from Slovene historical newspapers. The results provide a benchmark for targeted sentiment classification in OCR-degraded historical Slovene and offer an empirically grounded assessment of the capabilities and limitations of an instruction-tuned LLM in digital humanities research."
}