Deep learning mechanism and big data in hospitality and tourism: Developing personalized restaurant recommendation model to customer decision-making

Abstract

With the increasing ubiquity of booking restaurants through online platforms, the need for restaurant recommender systems that satisfy individual preferences has grown. Previous studies have found it challenging to reflect preferences in multiple aspects because customers' restaurant experiences were approached from a single aspect. This study proposes a novel personalized recommender system that uses the aspect-based sentiment analysis (ABSA) technique to derive granular customer preferences and recommend restaurants accordingly. The proposed model’s performance was empirically validated using customer review data from the global review platform Yelp. Initially, the ABSA technique was used to elaborately analyze sentiment scores for five major aspects of restaurants. Subsequently, aspect-specific sentiment scores were applied to a deep learning prediction model to learn the latent interactions between customers and restaurants. The proposed restaurant recommendation model demonstrated superior prediction compared to the five previous proposed recommendation model, especially yielding improved performance instead of models reflecting overall sentiment scores. Additionally, the impact of various aspect sentiments for the restaurant recommender system was empirically validated, and the results were presented from multiple perspectives based on the model configuration and parameters.