Understanding Park-Based Health-Promoting Behavior and Emotion with Large-Scale Social Media Data: The Case of Tianjin, China

Abstract

Urban parks' positive impacts on human physical, mental, and social well-being have been widely discussed in urban planning and public health literatures. As a result, scholars have invested considerable efforts in measuring park-based health-promoting behavior and emotion (e.g., physical activity, social interaction, and positive emotion). Recent years have seen a rapidly growing trend of using publicly available social media data as a potential measurement of park-based behavior. However, most ongoing studies focused on visitation amounts and paid little attention to finer-grained visitor behavior. In this study, we proposed a machine learning-aided text mining method to extract detailed park-based behavior using large-scale social media data, in this case, Dianping.com online reviews. Our approach combined manual labelling with machine learning-based natural language processing to leverage the accuracy of manual coding and the efficiency of computer-aided tools. By applying the method to 23,910 park-related reviews, we reveal the widely heterogenous health-promoting behavior and emotion of 34 urban parks in downtown Tianjin. This study shows how scholars and practitioners can turn unstructured social media data into structured behavioral insights that is helpful for making better places. Moreover, we discuss the limitations of the current approach and future research effort to validate and improve it.

Keywords: urban park, public health, urban analytics, social media data, text mining, natural language processing (NLP)