Volume 28, Issue 7 pp. 2509-2525
RESEARCH ARTICLE

City Influence Network: Mining and Analyzing the Influence of Chinese Cities Based on Social Media

Lihua Wang

Lihua Wang

Faculty of Data Science, City University of Macau, Macau SAR, China

Search for more papers by this author
Shengyi Jiang

Corresponding Author

Shengyi Jiang

Faculty of Data Science, City University of Macau, Macau SAR, China

School of Information Technology & Engineering, Guangzhou College of Commerce, Guangzhou, China

Correspondence:

Shengyi Jiang ([email protected])

Search for more papers by this author
First published: 18 September 2024
Citations: 2

ABSTRACT

There have been very few studies done on measuring the influence of all prefecture-level cities on a national scale due to the limited availability of public data, challenges in data collection, and insufficient data comprehensiveness. In this paper, we aim to fill this gap by investigating this problem in China. We first collected 692,859 news articles spanning one full year from the WeChat Official Accounts of 339 cities and Taiwan Province, which served as our study area and dataset. Then, we developed a city extractor module to reduce the ambiguity of place names and constructed a city interaction network. Then, we modeled the City Influence Index (CII) and the intensity of its influence. Finally, we proposed an analytical framework that examines the relationship between CII and Gross Domestic Product (GDP), compares it with the Global Cities Index, conducts influence analysis of cities at different levels, and more. The experimental results demonstrate that our analytical framework can effectively measure the influence of cities on a national scale and uncover the implicit relationships between cities. In doing so, our study offers a new perspective for measuring city influence. Code is available at: https://github.com/vczero/CII.

Conflicts of Interest

The authors declare no conflicts of interest.

Data Availability Statement

The data that support the findings of this study are available from the corresponding author upon reasonable request.

The full text of this article hosted at iucr.org is unavailable due to technical difficulties.