Machine Learning Aids in Understanding Park-based Health-promoting Behavior and Emotion

Strategic Insights -

Research published by Harvard University's Institute for Quantitative Social Science has made significant strides in analyzing park-based health-promoting behavior and emotion using machine learning-aided text mining methods. By extracting detailed park-based behavior from large-scale social media data, the study aimed to provide a more accurate understanding of the positive impacts of urban parks on human physical, mental, and social well-being. The research leveraged manually labeled data and machine learning-based natural language processing models to analyze 23,910 park-related online reviews in Tianjin, China, revealing the diverse health-promoting behavior and emotion reported in 34 urban parks.

Key Takeaways:

  • The study employed a machine learning-aided text mining method to analyze social media data and extract detailed park-based behavior, providing a more accurate understanding of urban parks' impacts on human well-being.
  • The research used 23,910 park-related online reviews in Tianjin, China, revealing the widely heterogeneous health-promoting behavior and emotion reported in 34 urban parks.
  • This study demonstrated the potential of using machine learning-aided text mining to analyze unstructured social media data, offering insights for urban planners and public health professionals.
  • The research highlighted the importance of manual labeling in conjunction with machine learning-based models to ensure the accuracy of extracted data.
  • The study's findings can inform the development of more effective urban planning strategies and public health initiatives in cities around the world.
  • The research was conducted by Tianyu Su and his team at Harvard University's Institute for Quantitative Social Science.
  • The study's results have been peer-reviewed and published in the journal Cities.

Statistics:

  • 23,910: The number of park-related online reviews analyzed in the study.
  • 34: The number of urban parks in downtown Tianjin where health-promoting behavior and emotion were reported.
  • 162. Cities: The issue number of the journal where the study was published.

Sources:

  • Su, T., et al. (2025). Understanding Park-based Health-promoting Behavior and Emotion With Large-scale Social Media Data: the Case of Tianjin, China. Cities, 162.
  • NewsRx (2025, July 8). Studies from Harvard University Describe New Findings in Machine Learning (Understanding Park-based Health-promoting Behavior and Emotion With Large-scale Social Media Data: the Case of Tianjin, China). China Weekly News.