Spatiotemporal cluster analysis of reputable tourist accommodation in Greater Amman Municipality, Jordan

Abstract

Purpose To test the applicability of the user-generated content (UGC) derived from social travel network sites for online reputation management, the purpose of this study is to analyze the spatial clustering of the reputable hotels (based on the TripAdvisor Best-Value indicator) and reputable outdoor seating restaurants (based on ranking indicator). Design/methodology/approach This study used data mining techniques to obtain the UGC from TripAdvisor. The Hierarchical Density-Based Spatial Clustering method based on algorithm (HDBSCAN) was used for robust cluster analysis. Findings The findings of this study revealed that best value (BV) hotels and reputable outdoor seating restaurants are most likely to be located in and around the central districts of the urban tourist destinations where population and economic activities are denser. BV hotels' spatiotemporal cluster analysis formed clusters of different sizes, densities and shape patterns. Research limitations/implications This study showed that reputable hotels and restaurants (H&Rs) are concentrated within districts near historic city centers. This should be an impetus for applied research on urban investment environments. Practical implications The findings would be rational guidance for entrepreneurs and potential investors on the most attractive tourism investment environments. Originality/value There has been a lack of studies focusing on analyzing the spatial clustering of the H&Rs using UGC. Therefore, to the best of the authors’ knowledge, this study is the first to map and analyze the spatiotemporal clustering patterns of reputable hotels (TripAdvisor BV indicator) and restaurants (ranking indicator). As such, this study makes a significant methodological contribution to urban tourism research by showing pattern change in H&Rs clustering using data mining and the HDBSCAN algorithm.