Construction of a Performance Arts Knowledge Graph Based on Large Language Models and Its Geospatial Distribution Analysis
Advances in Computer, Signals and Systems · 2026 · 10 (2)
DOI: 10.23977/acss.2026.100212 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advances in Computer, Signals and Systems, 2026.
Abstract (Originalsprache)
: Performance arts data is characterized by unstructured formats, multi-source heterogeneity, and sparse spatio-temporal distribution, rendering traditional management methods insufficient for revealing the underlying complex social networks and resource allocation patterns. This paper presents a framework for the construction and analysis of a performance arts knowledge graph powered by Large Language Models (LLMs). The approach utilizes LLMs to extract named entities and relational structures from unstructured performance records, integrated with an entity resolution algorithm to address naming redundancy and inconsistencies. A knowledge graph is constructed via the Neo4j graph database, where degree centrality and spatial radiation indices are applied to analyze core patterns in the performance market regarding subject distribution and geographical circulation. Experimental results indicate that the performance arts market exhibits a significant power-law distribution, with core leading entities demonstrating a strong spatial correlation between their total performance frequency and geographical reach.
Zitieren
APA
(2026). Construction of a Performance Arts Knowledge Graph Based on Large Language Models and Its Geospatial Distribution Analysis. Advances in Computer, Signals and Systems, 10(2). https://doi.org/10.23977/acss.2026.100212
Vancouver
Construction of a Performance Arts Knowledge Graph Based on Large Language Models and Its Geospatial Distribution Analysis. Advances in Computer, Signals and Systems. 2026;10(2). doi:10.23977/acss.2026.100212
BibTeX
@article{euvimed2026,
title = {Construction of a Performance Arts Knowledge Graph Based on Large Language Models and Its Geospatial Distribution Analysis},
journal = {Advances in Computer, Signals and Systems},
year = {2026},
volume = {10},
number = {2},
doi = {10.23977/acss.2026.100212}
}
EUVIMED