Understanding the User-Generated Geographic Information by Utilizing Big Data Analytics for Health Care

Area of Science:

• Urban Planning
• Public Health
• Data Science

Background:

• Achieving an active lifestyle involves dedicated exercise or integrating activity into daily routines.
• Location-Based Social Network (LBSN) data offers a novel approach to studying physical activity patterns.

Purpose of the Study:

• To examine the influence of diverse physical engagements on participant density dispersion in Shanghai.
• To evaluate the dependability of big data from social networks (Weibo) for physical activity research compared to traditional methods.
• To investigate the relationship between check-in data (time, class, place, frequency) and geographic features.

Main Methods:

• Utilized a mix of spatial, temporal, and visualization methodologies.
• Employed Kernel Density Estimation for geographical assessment.
• Analyzed Weibo check-in data for physical venues (gyms, parks) and applied relative difference formulation for gender disparity analysis.

Main Results:

• Physical activities and frequency allocation were mapped based on hour-to-day consumption habits.
• Observed prevalence of check-ins, peak times for venue visits, and identified gender disparities in physical activity engagement.
• Demonstrated the utility of LBSN data for understanding physical activity patterns and their geographical distribution.

Conclusions:

• Integrating physical activity into daily routines is crucial for an active lifestyle and overall well-being.
• LBSN data, specifically Weibo check-ins, provides valuable insights into population-level physical activity and its spatial distribution.
• Further research can leverage these methods to inform public health initiatives and urban planning in Shanghai.