Identifying key figures in Chinese historiographical texts via figure-centric social networks and self-seeded TrustRank

The narrative structures of numerous literary texts are inherently intricate, often impeding readers’ ability to grasp their core content. To mitigate this challenge, it is essential to develop analytical instruments that distill and foreground the most salient elements of such works—particularly those that drive narrative progression. In the contexts of historiographical texts, these pivotal elements frequently correspond to key figures. Key figures serve as critical catalysts in advancing plot development; thus, their systematic identification can significantly streamline the interpretive process for readers. Conventional approaches to literary understanding rely predominantly on close reading, yet surprisingly little scholarly attention has been devoted to the computational or structural identification of key figures within literary corpora. To bridge this gap, we introduce IFST (Identifying key Figures in Chinese historiographical texts through figure-centric Social networks and self-seeded TrustRank) to detect key figures in Chinese historiographical texts. First, IFST constructs a Figure-Centric Social Network (FCSN), wherein nodes represent figures, edges denote their co-appearance relationships in sentences of historiographical texts, and edge weights encode the frequency of their textual co-appearances, thereby capturing the intensity of interpersonal coupling. Second, IFST develops a self-seeded TrustRank algorithm to assign each figure a score that quantifies their importance in FCSN. Finally, figures are ranked in descending order of their importance score, with those at the apex designated as key figures. We evaluate IFST on Records of the Three Kingdoms —a foundational Chinese historiographical text renowned for its intricate political and military narrative. Empirical analysis reveals that IFST significantly outperforms baseline approaches in identifying key figures, and the key figures surfaced by our approach show strong alignment with human interpretive judgments, underscoring its validity as both an analytical instrument and a potential reading aid for complex literary corpora.

Authors

Institutions

Publication Details

Journal
PLoS ONE
Published
2026-11-19
DOI
https://doi.org/10.1371/journal.pone.0362803
Primary Topic
Digital Humanities and Scholarship
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Identifying key figures in Chinese historiographical texts via figure-centric social networks and self-seeded TrustRank

Jiale Wang, Shiyuan Zhou, Hongbing Liu, Junhao Wu
PLoS ONE
Digital Humanities and Scholarship
article

Identifying key figures in Chinese historiographical texts via figure-centric social networks and self-seeded TrustRank

Jiale Wang, Shiyuan Zhou, Hongbing Liu, Junhao Wu
article en

Abstract

The narrative structures of numerous literary texts are inherently intricate, often impeding readers’ ability to grasp their core content. To mitigate this challenge, it is essential to develop analytical instruments that distill and foreground the most salient elements of such works—particularly those that drive narrative progression. In the contexts of historiographical texts, these pivotal elements frequently correspond to key figures. Key figures serve as critical catalysts in advancing plot development; thus, their systematic identification can significantly streamline the interpretive process for readers. Conventional approaches to literary understanding rely predominantly on close reading, yet surprisingly little scholarly attention has been devoted to the computational or structural identification of key figures within literary corpora. To bridge this gap, we introduce IFST (Identifying key Figures in Chinese historiographical texts through figure-centric Social networks and self-seeded TrustRank) to detect key figures in Chinese historiographical texts. First, IFST constructs a Figure-Centric Social Network (FCSN), wherein nodes represent figures, edges denote their co-appearance relationships in sentences of historiographical texts, and edge weights encode the frequency of their textual co-appearances, thereby capturing the intensity of interpersonal coupling. Second, IFST develops a self-seeded TrustRank algorithm to assign each figure a score that quantifies their importance in FCSN. Finally, figures are ranked in descending order of their importance score, with those at the apex designated as key figures. We evaluate IFST on Records of the Three Kingdoms —a foundational Chinese historiographical text renowned for its intricate political and military narrative. Empirical analysis reveals that IFST significantly outperforms baseline approaches in identifying key figures, and the key figures surfaced by our approach show strong alignment with human interpretive judgments, underscoring its validity as both an analytical instrument and a potential reading aid for complex literary corpora.

PLoS ONEVol. 21(11)
Jiaxing Nanhu University (CN), Zhejiang Gongshang University (CN)
Digital Humanities and Scholarship
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon