A machine learning approach to segmentation of tourists based on perceived destination sustainability and trustworthiness. (March 2021)

• Record Type: Journal Article
• Authors: Penagos-Londoño, Gabriel I.; Rodriguez–Sanchez, Carla; Ruiz-Moreno, Felipe; Torres, Eduardo
• Is Part Of: Journal of destination marketing & management. Volume 19(2021)
• Publication Date: 2021-03
• Subjects: Segmentation -- Perceived sustainability -- Trustworthiness -- Security -- Machine learning approach -- Genetic algorithm; Place marketing -- Periodicals; Tourism -- Management -- Periodicals; Electronic journals; 658.8005
• DOI: 10.1016/j.jdmm.2020.100532
• Languages: English
• ISSNs: 2212-571X

Abstract

Abstract: Segmentation studies are crucial for planning sustainability strategies, and tourists' perceptions of destinations offer important segmentation criteria. The aim of this study is to understand and describe the tourist segments with similar levels of perceived destination sustainability and trustworthiness. Perceived sustainability and perceived trustworthiness are based on tourists' perceptions of the impacts of tourism development and policies of destinations and are measured as multidimensional constructs. Based on a sample of 438 tourists from Chile and Ecuador aged over 17 years, a metaheuristic (genetic algorithm) is employed to select the most useful variables for segmentation using a machine learning process. The results reveal three tourist segments: Extremely optimistic (Segment 3), Optimistic (Segment 2) and Moderately optimistic (Segment 1). These segments differ considerably in terms of the impacts of the dimensions of destination sustainability (environmental, sociocultural, and economic) and trustworthiness (ability, benevolence, and integrity). However, they do not differ in terms of most sociodemographic characteristics. As segmentation criteria, perceived sustainability and trustworthiness can help when analyzing the effectiveness of sustainability strategies and actions by the public and private institutions at tourist destinations. Highlights: A metaheuristic optimization algorithm to select relevant variables for a clustering machine learning segmentation process. Segments differ regarding destination perceived sustainability and trustworthiness. This segmentation criteria can help analyzing destination sustainability strategies. Three segments were found: Extremely optimistic, Optimistic, Moderately optimistic.