@inproceedings{hamilton-etal-2025-city,
title = "A City of Millions: Mapping Literary Social Networks At Scale",
author = "Hamilton, Sil and
Hicke, Rebecca and
Mimno, David and
Wilkens, Matthew",
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-1.46/",
doi = "10.18653/v1/2025.nlp4dh-1.46",
pages = "543--549",
ISBN = "979-8-89176-234-3",
abstract = "We release 70,509 high-quality social networks extracted from multilingual fiction and nonfiction narratives. We additionally provide metadata for {\textasciitilde}30,000 of these texts (73{\%} nonfiction and 27{\%} fiction) written between 1800 and 1999 in 58 languages. This dataset provides information on historical social worlds at an unprecedented scale, including data for 2,510,021 individuals in 2,805,482 pair-wise relationships annotated for affinity and relationship type. We achieve this scale by automating previously manual methods of extracting social networks; specifically, we adapt an existing annotation task as a language model prompt, ensuring consistency at scale with the use of structured output. This dataset serves as a unique resource for humanities and social science research by providing data on cognitive models of social realities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamilton-etal-2025-city">
<titleInfo>
<title>A City of Millions: Mapping Literary Social Networks At Scale</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sil</namePart>
<namePart type="family">Hamilton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Hicke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Mimno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Wilkens</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>We release 70,509 high-quality social networks extracted from multilingual fiction and nonfiction narratives. We additionally provide metadata for ~30,000 of these texts (73% nonfiction and 27% fiction) written between 1800 and 1999 in 58 languages. This dataset provides information on historical social worlds at an unprecedented scale, including data for 2,510,021 individuals in 2,805,482 pair-wise relationships annotated for affinity and relationship type. We achieve this scale by automating previously manual methods of extracting social networks; specifically, we adapt an existing annotation task as a language model prompt, ensuring consistency at scale with the use of structured output. This dataset serves as a unique resource for humanities and social science research by providing data on cognitive models of social realities.</abstract>
<identifier type="citekey">hamilton-etal-2025-city</identifier>
<identifier type="doi">10.18653/v1/2025.nlp4dh-1.46</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4dh-1.46/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>543</start>
<end>549</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A City of Millions: Mapping Literary Social Networks At Scale
%A Hamilton, Sil
%A Hicke, Rebecca
%A Mimno, David
%A Wilkens, Matthew
%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 hamilton-etal-2025-city
%X We release 70,509 high-quality social networks extracted from multilingual fiction and nonfiction narratives. We additionally provide metadata for ~30,000 of these texts (73% nonfiction and 27% fiction) written between 1800 and 1999 in 58 languages. This dataset provides information on historical social worlds at an unprecedented scale, including data for 2,510,021 individuals in 2,805,482 pair-wise relationships annotated for affinity and relationship type. We achieve this scale by automating previously manual methods of extracting social networks; specifically, we adapt an existing annotation task as a language model prompt, ensuring consistency at scale with the use of structured output. This dataset serves as a unique resource for humanities and social science research by providing data on cognitive models of social realities.
%R 10.18653/v1/2025.nlp4dh-1.46
%U https://aclanthology.org/2025.nlp4dh-1.46/
%U https://doi.org/10.18653/v1/2025.nlp4dh-1.46
%P 543-549
Markdown (Informal)
[A City of Millions: Mapping Literary Social Networks At Scale](https://aclanthology.org/2025.nlp4dh-1.46/) (Hamilton et al., NLP4DH 2025)
ACL
- Sil Hamilton, Rebecca Hicke, David Mimno, and Matthew Wilkens. 2025. A City of Millions: Mapping Literary Social Networks At Scale. In Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities, pages 543–549, Albuquerque, USA. Association for Computational Linguistics.