Creating Competitive Advantage from Non Structured Data: A Text Mining Approach in Turkish Hospitality Sector

Abstract

In recent years, data are exploded and they become more unstructured as a result of increasing web pages, e-mails, social media, photos and video contents. Traditional databases are not enough now to manage such data. However, organizations should manage them to gain competitive advantages. In other terms, hospitality managers should focus on satisfying customers by listening to them. In today’s information age, customers can be heard via their comments on travel websites that provide “big data.” As unstructured data are increased now, companies face with ‘big data’ and data mining tools should be applied to transform mass data into information and even into knowledge. The main purpose of this paper is to present a text-mining procedure to be used in marketing strategies to discover competitive elements in the hospitality sector from different locations in Turkey. Text mining is a powerful tool to analyze texts as main unstructured data. They are mostly available in the tourism sector in the form of tourists’ satisfaction and dissatisfaction stories. In this study, firstly, the mostly repeated words in the positive and negative reviews are revealed and then, the relationship of these words with the total points of the facility is investigated and finally, the revealed characteristics are discussed with Herzberg’s two-factor motivation theory. They are grouped into two categories: (1) motivators: words correlated with total review scores only in the positive reviews; and (2) hygiene factors: words negatively correlated with total review scores only in the negative reviews. In addition, the motivation-related attributes are discussed in terms of their differences between different locations in Turkey.