Journal of Geodesy and Geoinformation Science ›› 2024, Vol. 7 ›› Issue (2): 95-110.doi: 10.11947/j.JGGS.2024.0207

Previous Articles    

Spatial-temporal Patterns of Urban Parks' Effects on the Sentiments and Their Associated Factors Based on Social Media Data--a Case Study in Beijing

YUAN Yuting1,2, WANG Juan1,2, WEI Yali1,2, ZHU Yanrong1,2, SHI Changsheng3, MENG Bin1,2   

  1. 1. College of Applied Arts and Science, Beijing Union University, Beijing 100191, China
    2. Laboratory of Urban Cultural Sensing & Computing, Beijing Union University, Beijing 100191, China
    3. Beijing Guohuan Environmental Technology Co., Ltd., Tangshan 063020, China
  • Published:2024-06-25 Online:2024-09-04
  • Contact: WANG Juan, female, associate professor, research interests include data mining and urban environmental health.
  • About author:YUAN Yuting, female, graduate student, majors in geographic information science.
  • Supported by:
    *R&D Program of Beijing Municipal Education Commission(KM202211417015);Academic Research Projects of Beijing Union University(ZK10202209);The team-building subsidy of “Xuezhi Professorship” of the College of Applied Arts and Science of Beijing Union University(BUUCAS-XZJSTD-2024005);Academic Research Projects of Beijing Union University(ZKZD202305)

Abstract:

As the pivotal green space, urban parks play an important role in urban residents' daily activities. Thy can not only bring people physical health, but also can be more likely to elicit positive sentiment to those who visit them. Recently, social media big data has provided new data sources for sentiment analysis. However, there was limited researches that explored the connection between urban parks and individual's sentiments. Therefore, this study firstly employed a pre-trained language model (BERT, Bidirectional Encoder Representations from Transformers) to calculate sentiment scores based on social media data. Secondly, this study analysed the relationship between urban parks and individual's sentiment from both spatial and temporal perspectives. Finally, by utilizing structural equation model (SEM), we identified 13 factors and analyzed its degree of the influence. The research findings are listed as below: ① It confirmed that individuals generally experienced positive sentiment with high sentiment scores in the majority of urban parks; ② The urban park type showed an influence on sentiment scores. In this study, higher sentiment scores observed in Eco-parks, comprehensive parks, and historical parks; ③ The urban parks level showed low impact on sentiment scores. With distinctions observed mainly at level-3 and level-4; ④ Compared to internal factors in parks, the external infrastructure surround them exerted more significant impact on sentiment scores. For instance, number of bus and subway stations around urban parks led to higher sentiment scores, while scenic spots and restaurants had inverse result. This study provided a novel method to quantify the services of various urban parks, which can be served as inspiration for similar studies in other cities and countries, enhancing their park planning and management strategies.

Key words: urban parks; sentiment analysis; social media data; SEM; Beijing