Modeling intra-destination travel behavior of tourists through spatio-temporal analysis

Abstract

Understanding the underlying behavioral mechanism of tourist destination choices is the first and foremost step in establishing effective and appropriate management measures for a scenic area. Few studies have used high-resolution and fine-grained spatio-temporal data to develop sophisticated statistical models for uncovering micro-scale tourist movements. This study combined Global Positioning Systems (GPS) and conventional questionnaire survey data of 312 respondents from Gulangyu, China, a small island with a total area of 1.87 km2, to develop multinomial logit (MNL) models for identifying factors that affect tourists’ destination choices. A market segmentation analysis for different ticket purchasers was then performed. The Watson and Westin pooling test demonstrated that destination choices vary significantly between joint- and single-ticket purchasers. Joint-ticket purchasers are shown to be a more regular group whose mobility behavior can be better predicted and modeled compared with single-ticket purchasers. Several policy implication are discussed based on the modeling results. The proposed modeling, findings, and discussions provide the basis for policy instruments and will be useful for the enhanced planning of on-site movement, improved regulation of tourist flows, and rationalized design and management of tourist destinations.