A City of Millions: Mapping Literary Social Networks At Scale

2025-02-26

AI Summary

This study addresses the challenge of automatically constructing high-quality social network data from multilingual historical narrative texts to support empirical analysis of historical social structures in the humanities and social sciences. Method: It introduces a novel approach that reformulates manual social network annotation as a structured large language model prompting task, integrating multilingual coreference resolution with a joint relation-type–intimacy labeling framework to enable consistent, cross-lingual, and cross-genre automated extraction. Contribution/Results: The project processes 70,509 literary and non-literary texts spanning 58 languages from 1800–1999, yielding a structured social network dataset comprising 1.19 million individuals and 2.8 million relational pairs, accompanied by 30,000 metadata records. To date, this constitutes the largest curated, structured social network resource in the humanities, substantially advancing historical social cognition modeling and digital humanities research.

Technology Category

• Application Domains: Humanities & Computational Social Science
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Social Networks and Social Media: Computational social science
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

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 1,192,855 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 provides an unprecedented resource for the humanities and social sciences by providing data on cognitive models of social realities.

Problem

• Mapping large-scale literary social networks
• Automating extraction of historical social data
• Providing multilingual narrative social insights

Innovation

• Automated social network extraction
• Language model prompt adaptation
• Structured output for consistency