From Hotel Reviews to City Similarities: A Unified Latent-Space Model

• DOI: 10.3390/electronics9010197
• Publication Date: 2020-01-21T08:04:43Z
• Authors: Luca Cagliero; Moreno La Quatra; Daniele Apiletti
• Keywords: Point of interest; Hospitality; User-Generated Content; Urban Computing

A large portion of user-generated content published on the Web consists opinions and reviews products, services, places in textual form. Many travellers tourists routinely rely such to drive their choices, shaping trips visits any place earth, specifically select hotels cities. In context hospitality management, a challenging research problem is identify effective strategies explain hotel ratings correlation with urban context. Under this umbrella, paper investigates use sentence-based embedding models deeply explore similarities dissimilarities between cities terms corresponding surrounding points interests. Reviews point interest (POI) descriptions are jointly modelled unified latent space, allowing us investigate dependencies guest feedbacks neighborhood at different aggregation levels. The experiments performed public TripAdvisor hotel-review datasets confirm applicability effectiveness proposed approach.