Apply Data Mining Approach to Identify Non-revisit Factors for Hotel Industry

The development of social media has changed the way that travelers visit sightseeing spots. In tourism and hospitality industry, to enhance the revisit intention of passengers is an important issue for the purpose of increasing margin. In recent years, related researches had focused on the customers' revisit behaviors and factors. But, few studies have investigated the related issues that travelers do not want to visit again. Failure to revisit may bring a great damage to the company's revenue in the future. To avoid the occurrence of these injuries, a text mining approach will be employed to discover the reason why customers don't revisit from online textual reviews in social media. In this work, we attempt to define the candidate factors that may influence the non-revisit, and then use two feature selection methods, decision tree and Support Vector Machines -Recursive Feature Elimination (SVM-RFE) to find the crucial factors. Experimental results could be provided to travel service providers to improve service quality and effectively avoid future impact on passengers no longer visiting.