Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Text to Network: Constructing a Knowledge Graph of Taiwan-Based China Studies Using Generative AI

Hsuan-Lei Shao

TL;DR

This work addresses the challenge of navigating decades of Taiwan-based China Studies by converting unstructured academic texts into a structured, interactive knowledge graph. An AI-assisted pipeline uses LLMs to extract subject–predicate–object triples from 1,367 papers (1996–2019) and applies rigorous preprocessing (divergence reduction, semantic label merging, deduplication, and abbreviation mapping) before visualization. The resulting D3.js-based system enables real-time, network-centric exploration of concepts and relationships, revealing thematic clusters, trajectories, and research gaps while reducing reliance on linear text consumption. By combining machine-generated semantic linking with a lightweight knowledge graph framework, the approach offers a scalable, data-driven alternative to traditional ontology construction and could inform digital humanities infrastructure for regional knowledge systems.

Abstract

Taiwanese China Studies (CS) has developed into a rich, interdisciplinary research field shaped by the unique geopolitical position and long standing academic engagement with Mainland China. This study responds to the growing need to systematically revisit and reorganize decades of Taiwan based CS scholarship by proposing an AI assisted approach that transforms unstructured academic texts into structured, interactive knowledge representations. We apply generative AI (GAI) techniques and large language models (LLMs) to extract and standardize entity relation triples from 1,367 peer reviewed CS articles published between 1996 and 2019. These triples are then visualized through a lightweight D3.js based system, forming the foundation of a domain specific knowledge graph and vector database for the field. This infrastructure allows users to explore conceptual nodes and semantic relationships across the corpus, revealing previously uncharted intellectual trajectories, thematic clusters, and research gaps. By decomposing textual content into graph structured knowledge units, our system enables a paradigm shift from linear text consumption to network based knowledge navigation. In doing so, it enhances scholarly access to CS literature while offering a scalable, data driven alternative to traditional ontology construction. This work not only demonstrates how generative AI can augment area studies and digital humanities but also highlights its potential to support a reimagined scholarly infrastructure for regional knowledge systems.

From Text to Network: Constructing a Knowledge Graph of Taiwan-Based China Studies Using Generative AI

TL;DR

This work addresses the challenge of navigating decades of Taiwan-based China Studies by converting unstructured academic texts into a structured, interactive knowledge graph. An AI-assisted pipeline uses LLMs to extract subject–predicate–object triples from 1,367 papers (1996–2019) and applies rigorous preprocessing (divergence reduction, semantic label merging, deduplication, and abbreviation mapping) before visualization. The resulting D3.js-based system enables real-time, network-centric exploration of concepts and relationships, revealing thematic clusters, trajectories, and research gaps while reducing reliance on linear text consumption. By combining machine-generated semantic linking with a lightweight knowledge graph framework, the approach offers a scalable, data-driven alternative to traditional ontology construction and could inform digital humanities infrastructure for regional knowledge systems.

Abstract

Taiwanese China Studies (CS) has developed into a rich, interdisciplinary research field shaped by the unique geopolitical position and long standing academic engagement with Mainland China. This study responds to the growing need to systematically revisit and reorganize decades of Taiwan based CS scholarship by proposing an AI assisted approach that transforms unstructured academic texts into structured, interactive knowledge representations. We apply generative AI (GAI) techniques and large language models (LLMs) to extract and standardize entity relation triples from 1,367 peer reviewed CS articles published between 1996 and 2019. These triples are then visualized through a lightweight D3.js based system, forming the foundation of a domain specific knowledge graph and vector database for the field. This infrastructure allows users to explore conceptual nodes and semantic relationships across the corpus, revealing previously uncharted intellectual trajectories, thematic clusters, and research gaps. By decomposing textual content into graph structured knowledge units, our system enables a paradigm shift from linear text consumption to network based knowledge navigation. In doing so, it enhances scholarly access to CS literature while offering a scalable, data driven alternative to traditional ontology construction. This work not only demonstrates how generative AI can augment area studies and digital humanities but also highlights its potential to support a reimagined scholarly infrastructure for regional knowledge systems.
Paper Structure (14 sections, 4 figures)

This paper contains 14 sections, 4 figures.

Table of Contents

  1. Introduction
  2. Methodology
  3. Triplet Annotation
  4. Preprocessing: Reduce Divergence
  5. Preprocessing II: Semantic Label Merging
  6. Preprocessing III: Duplicate Removal
  7. Preprocessing IV: Abbreviation Mapping
  8. Visualization System Design
  9. Data Loading Module
  10. Layout Engine and Edge Label Management
  11. Interactive Filtering and Search
  12. User Interaction and Controls
  13. Evaluation
  14. Conclusion and Future Work

Figures (4)

  • Figure 1: Dataset Structure
  • Figure 2: Basic Triplet Visualization
  • Figure 3: Original Triplet and Reduced Divergence
  • Figure 4: Knowledge Graph UI Design