Customer decision-making analysis based on big social data using machine learning: a case study of hotels in Mecca.

Area of Science:

• Business Analytics
• Computational Social Science
• Tourism and Hospitality Management

Background:

• Big social data and user-generated content offer timely insights into customer behavior.
• Analyzing customer satisfaction in tourism is crucial, with electronic word-of-mouth (eWOM) providing a rich data source.
• Traditional quantitative surveys have limitations; big social data analysis offers a complementary approach.

Purpose of the Study:

• To develop and validate a hybrid methodology for analyzing big social data on traveler decision-making for hotels in Mecca, Saudi Arabia.
• To leverage supervised learning, text mining, and machine learning for customer satisfaction analysis.
• To segment travelers and understand their satisfaction based on online reviews.

Main Methods:

• A hybrid methodology combining supervised learning (Support Vector Regression with Sequential Minimal Optimization - SMO), text mining (Latent Dirichlet Allocation - LDA), and segmentation (k-means) was developed.
• Data were collected from traveler online reviews of Mecca hotels on TripAdvisor.
• The methodology involved segmenting data and revealing traveler satisfaction for each segment.

Main Results:

• The developed hybrid method proved effective for analyzing big social data related to traveler behavior.
• The approach successfully segmented travelers and identified satisfaction levels based on their online reviews.
• The study demonstrated the efficacy of machine learning and text mining in understanding customer demands in the hospitality sector.

Conclusions:

• The hybrid methodology is effective for big social data analysis and traveler segmentation in the context of Mecca hotels.
• Findings provide actionable insights for hotel managers to enhance service quality and customer satisfaction.
• Utilizing eWOM analysis is a valuable strategy for understanding and meeting customer demands in the tourism industry.