@inproceedings{murugaraj-etal-2025-mining,
title = "Mining the Past: A Comparative Study of Classical and Neural Topic Models on Historical Newspaper Archives",
author = "Murugaraj, Keerthana and
Lamsiyah, Salima and
During, Marten and
Theobald, Martin",
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-1.39/",
doi = "10.18653/v1/2025.nlp4dh-1.39",
pages = "452--463",
ISBN = "979-8-89176-234-3",
abstract = "Analyzing historical discourse in large-scale newspaper archives requires scalable and interpretable methods to uncover hidden themes. This study systematically evaluates topic modeling approaches for newspaper articles from 1955 to 2018, comparing probabilistic LDA, matrix factorization NMF, and neural-based models such as Top2Vec and BERTopic across various preprocessing strategies. We benchmark these methods on topic coherence, diversity, scalability, and interpretability. While LDA is commonly used in historical text analysis, our findings demonstrate that BERTopic, leveraging contextual embeddings, consistently outperforms classical models in all tested aspects, making it a more robust choice for large-scale textual corpora. Additionally, we highlight the trade-offs between preprocessing strategies and model performance, emphasizing the importance of tailored pipeline design. These insights advance the field of historical NLP, offering concrete guidance for historians and computational social scientists in selecting the most effective topic-modeling approach for analyzing digitized archives. Our code will be publicly available on GitHub."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="murugaraj-etal-2025-mining">
<titleInfo>
<title>Mining the Past: A Comparative Study of Classical and Neural Topic Models on Historical Newspaper Archives</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keerthana</namePart>
<namePart type="family">Murugaraj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salima</namePart>
<namePart type="family">Lamsiyah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marten</namePart>
<namePart type="family">During</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Theobald</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>Analyzing historical discourse in large-scale newspaper archives requires scalable and interpretable methods to uncover hidden themes. This study systematically evaluates topic modeling approaches for newspaper articles from 1955 to 2018, comparing probabilistic LDA, matrix factorization NMF, and neural-based models such as Top2Vec and BERTopic across various preprocessing strategies. We benchmark these methods on topic coherence, diversity, scalability, and interpretability. While LDA is commonly used in historical text analysis, our findings demonstrate that BERTopic, leveraging contextual embeddings, consistently outperforms classical models in all tested aspects, making it a more robust choice for large-scale textual corpora. Additionally, we highlight the trade-offs between preprocessing strategies and model performance, emphasizing the importance of tailored pipeline design. These insights advance the field of historical NLP, offering concrete guidance for historians and computational social scientists in selecting the most effective topic-modeling approach for analyzing digitized archives. Our code will be publicly available on GitHub.</abstract>
<identifier type="citekey">murugaraj-etal-2025-mining</identifier>
<identifier type="doi">10.18653/v1/2025.nlp4dh-1.39</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4dh-1.39/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>452</start>
<end>463</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mining the Past: A Comparative Study of Classical and Neural Topic Models on Historical Newspaper Archives
%A Murugaraj, Keerthana
%A Lamsiyah, Salima
%A During, Marten
%A Theobald, Martin
%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 murugaraj-etal-2025-mining
%X Analyzing historical discourse in large-scale newspaper archives requires scalable and interpretable methods to uncover hidden themes. This study systematically evaluates topic modeling approaches for newspaper articles from 1955 to 2018, comparing probabilistic LDA, matrix factorization NMF, and neural-based models such as Top2Vec and BERTopic across various preprocessing strategies. We benchmark these methods on topic coherence, diversity, scalability, and interpretability. While LDA is commonly used in historical text analysis, our findings demonstrate that BERTopic, leveraging contextual embeddings, consistently outperforms classical models in all tested aspects, making it a more robust choice for large-scale textual corpora. Additionally, we highlight the trade-offs between preprocessing strategies and model performance, emphasizing the importance of tailored pipeline design. These insights advance the field of historical NLP, offering concrete guidance for historians and computational social scientists in selecting the most effective topic-modeling approach for analyzing digitized archives. Our code will be publicly available on GitHub.
%R 10.18653/v1/2025.nlp4dh-1.39
%U https://aclanthology.org/2025.nlp4dh-1.39/
%U https://doi.org/10.18653/v1/2025.nlp4dh-1.39
%P 452-463
Markdown (Informal)
[Mining the Past: A Comparative Study of Classical and Neural Topic Models on Historical Newspaper Archives](https://aclanthology.org/2025.nlp4dh-1.39/) (Murugaraj et al., NLP4DH 2025)
ACL