@inproceedings{cohen-etal-2025-historical,
title = "Historical Ink: Exploring Large Language Models for Irony Detection in 19th-Century {S}panish",
author = "Cohen, Kevin and
Manrique-G{\'o}mez, Laura and
Manrique, Ruben",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Bizzoni, Yuri and
Miyagawa, So and
Alnajjar, Khalid},
booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
month = may,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.nlp4dh-1.48/",
doi = "10.18653/v1/2025.nlp4dh-1.48",
pages = "559--569",
ISBN = "979-8-89176-234-3",
abstract = "This study explores the use of large language models (LLMs) to enhance datasets and improve irony detection in 19th-century Latin American newspapers. Two strategies were employed to evaluate the efficacy of BERT and GPT models in capturing the subtle nuances nature of irony, through both multi-class and binary classification tasks. First, we implemented dataset enhancements focused on enriching emotional and contextual cues; however, these showed limited impact on historical language analysis. The second strategy, a semi-automated annotation process, effectively addressed class imbalance and augmented the dataset with high-quality annotations. Despite the challenges posed by the complexity of irony, this work contributes to the advancement of sentiment analysis through two key contributions: introducing a new historical Spanish dataset tagged for sentiment analysis and irony detection, and proposing a semi-automated annotation methodology where human expertise is crucial for refining LLMs results, enriched by incorporating historical and cultural contexts as core features."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cohen-etal-2025-historical">
<titleInfo>
<title>Historical Ink: Exploring Large Language Models for Irony Detection in 19th-Century Spanish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Manrique-Gómez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruben</namePart>
<namePart type="family">Manrique</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-234-3</identifier>
</relatedItem>
<abstract>This study explores the use of large language models (LLMs) to enhance datasets and improve irony detection in 19th-century Latin American newspapers. Two strategies were employed to evaluate the efficacy of BERT and GPT models in capturing the subtle nuances nature of irony, through both multi-class and binary classification tasks. First, we implemented dataset enhancements focused on enriching emotional and contextual cues; however, these showed limited impact on historical language analysis. The second strategy, a semi-automated annotation process, effectively addressed class imbalance and augmented the dataset with high-quality annotations. Despite the challenges posed by the complexity of irony, this work contributes to the advancement of sentiment analysis through two key contributions: introducing a new historical Spanish dataset tagged for sentiment analysis and irony detection, and proposing a semi-automated annotation methodology where human expertise is crucial for refining LLMs results, enriched by incorporating historical and cultural contexts as core features.</abstract>
<identifier type="citekey">cohen-etal-2025-historical</identifier>
<identifier type="doi">10.18653/v1/2025.nlp4dh-1.48</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4dh-1.48/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>559</start>
<end>569</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Historical Ink: Exploring Large Language Models for Irony Detection in 19th-Century Spanish
%A Cohen, Kevin
%A Manrique-Gómez, Laura
%A Manrique, Ruben
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Bizzoni, Yuri
%Y Miyagawa, So
%Y Alnajjar, Khalid
%S Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-234-3
%F cohen-etal-2025-historical
%X This study explores the use of large language models (LLMs) to enhance datasets and improve irony detection in 19th-century Latin American newspapers. Two strategies were employed to evaluate the efficacy of BERT and GPT models in capturing the subtle nuances nature of irony, through both multi-class and binary classification tasks. First, we implemented dataset enhancements focused on enriching emotional and contextual cues; however, these showed limited impact on historical language analysis. The second strategy, a semi-automated annotation process, effectively addressed class imbalance and augmented the dataset with high-quality annotations. Despite the challenges posed by the complexity of irony, this work contributes to the advancement of sentiment analysis through two key contributions: introducing a new historical Spanish dataset tagged for sentiment analysis and irony detection, and proposing a semi-automated annotation methodology where human expertise is crucial for refining LLMs results, enriched by incorporating historical and cultural contexts as core features.
%R 10.18653/v1/2025.nlp4dh-1.48
%U https://aclanthology.org/2025.nlp4dh-1.48/
%U https://doi.org/10.18653/v1/2025.nlp4dh-1.48
%P 559-569
Markdown (Informal)
[Historical Ink: Exploring Large Language Models for Irony Detection in 19th-Century Spanish](https://aclanthology.org/2025.nlp4dh-1.48/) (Cohen et al., NLP4DH 2025)
ACL