@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="munda-etal-2026-benchmarking">
<titleInfo>
<title>Benchmarking LLMs for Aspect-Based Sentiment Classification in Slovene Historical Periodicals</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tina</namePart>
<namePart type="family">Munda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Dobranić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uroš</namePart>
<namePart type="family">Šmajdek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Pejić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ciril</namePart>
<namePart type="family">Bohak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vojko</namePart>
<namePart type="family">Gorjanc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fišer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Montejo-Raez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Grisot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Blochowiak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Battaner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">munda-etal-2026-benchmarking</identifier>
<identifier type="doi">10.63317/22hvcbc23rts</identifier>
<location>
<url>https://aclanthology.org/2026.llms4ssh-1.11/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>103</start>
<end>113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking LLMs for Aspect-Based Sentiment Classification in Slovene Historical Periodicals
%A Munda, Tina
%A Dobranić, Filip
%A Šmajdek, Uroš
%A Pejić, Oliver
%A Bohak, Ciril
%A Gorjanc, Vojko
%A Fišer, Darja
%Y Montejo-Raez, Arturo
%Y Grisot, Cristina
%Y Blochowiak, Joanna
%Y Ljubešić, Nikola
%Y Battaner, Elena
%Y Rigau, German
%S Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca (Spain)
%F munda-etal-2026-benchmarking
%X 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.
%R 10.63317/22hvcbc23rts
%U https://aclanthology.org/2026.llms4ssh-1.11/
%U https://doi.org/10.63317/22hvcbc23rts
%P 103-113
Markdown (Informal)
[Benchmarking LLMs for Aspect-Based Sentiment Classification in Slovene Historical Periodicals](https://aclanthology.org/2026.llms4ssh-1.11/) (Munda et al., LLMs4SSH 2026)
ACL