Understanding Factors Affecting Tourist Distribution in Urban National Parks Based on Big Data and Machine Learning

Abstract

Urban national parks (UNPs) provide tourism services in cities worldwide. However, the factors affecting tourist distributions in UNP activity and path spaces remain uncertain. Using Web crawler technology, location big data were tracked and sampled in Donghu National Park in Wuhan, China, and 12 predictor variables were analyzed using a machine-learning method (i.e., random forest). The consistency of the big data compared to the population census and tourist observations was determined at 79.5% and 77.8%, respectively. The tourist number (p) and tourist density (p/ha) per day in the park space in Donghu National Park were 0–2,531 p and 0–198.0 p/ha, respectively. Peak tourist periods showed pressure flows of 0.3–34.5‰ between scenic areas in the park. An analytical framework was formulated for UNPs to link the urban environment, park attributes, and configurational attributes, which here explained 66.4%–72.5% of the tourist distribution in the path and activity spaces. Random forest models performed better than geographically weighted regression (GWR) or ordinary least squares (OLS) models, indicating a complex nonlinear relationship between the independent variables and tourist distribution in UNP spaces, rather than the linear relationship that has previously been found in urban parks. First, both activity and path spaces near developed urban environments or park entrances bore higher tourism pressure. Second, winding routes attracted tourists to path spaces, while water landscapes attracted tourists to both path and activity spaces. Third, tourism pressure in path spaces was determined by configurational attributes. These results are important reference points for the planning and management of UNPs.