@inproceedings{feldkamp-etal-2026-growing,
title = "A Growing Literature of the Public Sphere: Fiction in {D}anish Newspapers (1666{--}1850)",
author = "Feldkamp, Pascale and
Lassche, Alie and
Eriksen, Rie and
Morgenstjerne, Kit and
Nielbo, Kristoffer and
Heinsen, Johan and
Bizzoni, Yuri",
editor = "Ogrodniczuk, Maciej and
Osenova, Petya and
Wissik, Tanja",
booktitle = "Proceedings of the First Workshop on Creating Interoperable Corpora of Historical Newspapers",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.pressmint-1.8/",
doi = "10.63317/4ekyjogsy8zg",
pages = "40--49",
abstract = "Digitized literary corpora of the 19th century largely focus on standalone volumes, sidelining the broader and more diverse literary production of the period. Fiction published in less enduring formats {--} such as novellas and serialized pieces in newspapers {--} remains underexplored, particularly for low-resource languages like Danish, despite the growing availability of digitized newspaper archives. This paper addresses that gap by identifying and tagging fiction in Danish newspapers (1666{--}1850). We (1) present a manually annotated dataset of 1,831 articles with both binary (fiction/nonfiction) and fine-grained subcategories (travelogue, biography, essay), and (2) evaluate a document-embedding classifier that achieves an F1-score of up to 0.89 for the fiction/nonfiction distinction. Building on this pipeline, we further provide two resources for future research: (a) fiction probability scores for nearly five million newspaper articles (n=4,898,084), and (b) a small, cleaned, and curated subset of newspaper fiction (n=139), intended as a growing resource."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feldkamp-etal-2026-growing">
<titleInfo>
<title>A Growing Literature of the Public Sphere: Fiction in Danish Newspapers (1666–1850)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Feldkamp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alie</namePart>
<namePart type="family">Lassche</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rie</namePart>
<namePart type="family">Eriksen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kit</namePart>
<namePart type="family">Morgenstjerne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristoffer</namePart>
<namePart type="family">Nielbo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johan</namePart>
<namePart type="family">Heinsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</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 the First Workshop on Creating Interoperable Corpora of Historical Newspapers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petya</namePart>
<namePart type="family">Osenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Wissik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Digitized literary corpora of the 19th century largely focus on standalone volumes, sidelining the broader and more diverse literary production of the period. Fiction published in less enduring formats – such as novellas and serialized pieces in newspapers – remains underexplored, particularly for low-resource languages like Danish, despite the growing availability of digitized newspaper archives. This paper addresses that gap by identifying and tagging fiction in Danish newspapers (1666–1850). We (1) present a manually annotated dataset of 1,831 articles with both binary (fiction/nonfiction) and fine-grained subcategories (travelogue, biography, essay), and (2) evaluate a document-embedding classifier that achieves an F1-score of up to 0.89 for the fiction/nonfiction distinction. Building on this pipeline, we further provide two resources for future research: (a) fiction probability scores for nearly five million newspaper articles (n=4,898,084), and (b) a small, cleaned, and curated subset of newspaper fiction (n=139), intended as a growing resource.</abstract>
<identifier type="citekey">feldkamp-etal-2026-growing</identifier>
<identifier type="doi">10.63317/4ekyjogsy8zg</identifier>
<location>
<url>https://aclanthology.org/2026.pressmint-1.8/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>40</start>
<end>49</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Growing Literature of the Public Sphere: Fiction in Danish Newspapers (1666–1850)
%A Feldkamp, Pascale
%A Lassche, Alie
%A Eriksen, Rie
%A Morgenstjerne, Kit
%A Nielbo, Kristoffer
%A Heinsen, Johan
%A Bizzoni, Yuri
%Y Ogrodniczuk, Maciej
%Y Osenova, Petya
%Y Wissik, Tanja
%S Proceedings of the First Workshop on Creating Interoperable Corpora of Historical Newspapers
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma de Mallorca, Spain
%F feldkamp-etal-2026-growing
%X Digitized literary corpora of the 19th century largely focus on standalone volumes, sidelining the broader and more diverse literary production of the period. Fiction published in less enduring formats – such as novellas and serialized pieces in newspapers – remains underexplored, particularly for low-resource languages like Danish, despite the growing availability of digitized newspaper archives. This paper addresses that gap by identifying and tagging fiction in Danish newspapers (1666–1850). We (1) present a manually annotated dataset of 1,831 articles with both binary (fiction/nonfiction) and fine-grained subcategories (travelogue, biography, essay), and (2) evaluate a document-embedding classifier that achieves an F1-score of up to 0.89 for the fiction/nonfiction distinction. Building on this pipeline, we further provide two resources for future research: (a) fiction probability scores for nearly five million newspaper articles (n=4,898,084), and (b) a small, cleaned, and curated subset of newspaper fiction (n=139), intended as a growing resource.
%R 10.63317/4ekyjogsy8zg
%U https://aclanthology.org/2026.pressmint-1.8/
%U https://doi.org/10.63317/4ekyjogsy8zg
%P 40-49
Markdown (Informal)
[A Growing Literature of the Public Sphere: Fiction in Danish Newspapers (1666–1850)](https://aclanthology.org/2026.pressmint-1.8/) (Feldkamp et al., PressMint 2026)
ACL