Research Supporting Data for Policy Synergy Knowledge Extraction Based on Large Language Models

Read full text Summarise with VIRAT
Authors: yang long
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Text: This policy text dataset is composed of the policy texts related to the cultural, tourism and sports industries in China from 2010 to 2024, which were collected from the central government's official website and the "Peking University Legal Database" system. Juzhen: Policy Joint Publisher Matrix, used to calculate the intensity of cooperation among entities and to draw the topological structure of the cooperation network among entities. Tool: Identifies policy tools and conducts statistical analysis of data results. BERTopic: Paragraphs, word segmentation, text vectors, and time labels for bertopic topic clustering. PMCindex: Evaluation results and statistics of the coordination degree of various local policies.

Fields of Study & Subjects

Computational and Text Analysis Methods Topic Modeling Public Policy and Administration Research

Publication details

Journal / source
ScienceDB
Publication date
9 March 2026
Language
ZH
Document type
Dataset