Big social data and customer decision making in vegetarian restaurants: A combined machine learning method. (September 2021)

• Record Type: Journal Article
• Authors: Nilashi, Mehrbakhsh; Ahmadi, Hossein; Arji, Goli; Alsalem, Khalaf Okab; Samad, Sarminah; Ghabban, Fahad; Alzahrani, Ahmed Omar; Ahani, Ali; Alarood, Ala Abdulsalam
• Is Part Of: Journal of retailing and consumer services. Volume 62(2022)
• Publication Date: 2021-09
• Subjects: Online reviews -- Food quality -- Vegetarian friendly restaurants -- Text mining -- Segmentation; Retail trade -- Periodicals; Service industries -- Periodicals; Customer services -- Periodicals; Commerce de détail -- Périodiques; Service à la clientèle -- Périodiques; Customer services; Retail trade; Periodicals; 658.87
• DOI: 10.1016/j.jretconser.2021.102630
• Languages: English
• ISSNs: 0969-6989

Abstract

Abstract: Customers increasingly use various social media to share their opinion about restaurants service quality. Big data collected from social media provides a data platform to improve the service quality of restaurants through customers' online reviews, where online reviews are a trustworthy and reliable source that helps consumers to evaluate food quality. Developing methods for effective evaluation of customer-generated reviews of restaurant services is important. This study develops a new method through effective learning techniques for customer segmentation and their preferences prediction in vegetarian friendly restaurants. The method is developed through text mining (Latent Dirichlet Allocation), cluster analysis (Self Organizing Map) and predictive learning technique (Classification and Regression Trees) to reveal the customer' satisfaction levels from the service quality in vegetarian friendly restaurants. Based on the obtained results of our experiments on the data vegetarian friendly restaurants in Bangkok, the models constructed by Classification and Regression Trees were able to give an accurate prediction of customers' preferences on the basis of restaurants' quality factors. The results showed that customers' online reviews analysis can be an effective way for customers segmentation to predict their preferences and help the restaurant managers to set priority instructions for service quality improvements.