Heat and park attendance: Evidence from ?small data? and ?big data? in Hong Kong

Urban heat disrupts the use of parks, although the extent of such disruptions remains disputed. Literature relies on small data methods, such as questionnaires, field studies, or human-subject experiments, to capture the behavioural response to heat. Their findings are often in contradiction with each other, possibly due to the small sample sizes, the short study period, or the few sites available in a single study. The rise of big data such as social media offers new opportunities, yet its reliability and usefulness remain unknown. This paper describes a study using Twitter data (tweets) to study park attendance under the influence of hot weather. Some 20,000 tweets geo-coded within major parks were obtained in Hong Kong over a period of three years. Field studies have been conducted in parallel in a large park covering the hot and cool seasons and some 40,000 attendance were recorded over three months. Both the small and big data were analyzed and compared to each other. Findings suggest that a 1 degrees C increase in temperature was associated with some 4% drop in park attendance and some 1% drop in park tweets. The differences between the two data sources be explained by the 'leakage' of indoor tweets to parks caused by GPS drift near buildings. The Universal Thermal Climate Index can better predict self-reported thermal sensations, compared with other biometeorological indicators. This study has contributed to methodologies and new evidence to the study of behaviors and thermal adaptations in an outdoor space, and geo-coded tweets can serve as a powerful data source.

Automated summary

Urban heat disrupts park usage, and the extent of this disruption is still debated. Previous studies have used small data methods, which often contradict each other due to limitations in sample size, study duration, and study sites. This study utilized Twitter data and field studies to examine park attendance under hot weather conditions. The findings suggest that a 1°C increase in temperature corresponds to a 4% decrease in park attendance and a 1% decrease in park-related tweets. The differences between the two data sources could be attributed to indoor tweets mistakenly associated with parks. The Universal Thermal Climate Index was found to be a better predictor of thermal sensations compared to other biometeorological indicators.