Document Type : Research Paper

Authors

• Zohre Anisi Hemaseh ¹
• Mohammad Ali Afshar Kazemi ²
• Ehsan Mousavi Khanghah ³

¹ Department of Information Technology Management, Central Tehran Branch, Islamic Azad University, Tehran, Iran

² Department of Industrial Management, Central Tehran Branch, Islamic Azad University, Tehran, Iran

³ Department of Computer Engineering, Shahed University, Tehran, Iran

Abstract

The tourism industry, with its strategic role in the economic prosperity of a country, has become a passage for sustainable development. One of the necessities of every business is to know the preferences and understand the customer experience. Understanding the customer experience is often done through questionnaires and surveys, which has limitations that have caused the answers to be inaccurate, as well as the orientation of the questions based on the researcher's mind. With the emergence of social networks, users present their opinions regarding the experience they had with products and services. This causes the production of valuable big data. Online reviews are one such source of data, created from customers' self-reports of their experiences. Considering that the hotel industry in Iran needs to develop and increase the share of the international market, the online reviews of five-star hotels in Iran were analyzed on the world-renowned platform. In this study, the approach of frequency analysis and semantic network analysis was used to extract topics in the perceived experience of customers, then using factor analysis, hidden factors were discovered. Finally, to model the relationship between the factors and its effect on satisfaction, a linear regression model was performed. This research obtained valuable findings from the opinions of customers that in addition to the major role of staff behavior, room facilities in satisfaction, the different role of food service in different meals, the effect of the beauty of the city and the purpose of the trip can be mentioned.

Keywords

• tourism
• online reviews
• customer experience
• customer satisfaction
• semantic network analysis