Online Otel Yorumlarının Metin Madenciliği Teknikleri ile İncelenmesi: Bakü Otelleri Örneği

Öz

İletişim teknolojilerinde yaşanan gelişmelerin tüketicilere satın alma ve satın aldıkları ürünler hakkında deneyimlerini paylaşma imkanı sunması sonucunda online platformlar turizm sektörünü derinden etkileyen unsurlara dönüşmüştür. Tüketicilerin online ortamlarda giderek daha fazla yorum paylaşması sonucunda he tüketiciler hem de tedarikçiler için değerli bilgiler içeren büyük veri yığınları oluşmuştur. Bu büyük verinin analiz edilme ihtiyacı ise büyük veri analiz yöntemlerinin online üzerinde kullanılmaya başlamasına neden olmuştur. Bu çalışmada ise booking.com üzerinde yer alan 5 yıldızlı Bakü otellerine ilişkin 3.275 adet yorum büyük veri analiz yöntemlerinden olan metin madenciliği teknikleri kullanılarak incelenmiştir. Yorumlar veri ön işleme sürecine tabi tutulmuş ve sonrasında kelime sıklık ve ağırlıkları hesaplanmıştır. Daha sonra birliktelik analizleri kullanılarak hangi terimlerin birlikte kullanıldığı tespit edilmiştir. Sonuç olarak yorumlarda personel, oda ve otel terimlerinin en sık kullanılan terimler olduğu saptanmıştır.

Anahtar Kelimeler

• Online Yorumlar
• Metin Madenciliği
• Kelime Sıklıkları
• Metin Analizi

Investigation of Online Hotel Reviews with Text Mining Techniques: The Case of Baku Hotels

Öz

Online environments turn into platforms that influence the tourism sector deeply as a result of advancements in communication technologies to give customer a chance to buy tourism products online and write reviews about their experience. As more and more travelers contribute their travel experience on travel websites, a huge amount of hotel reviews is generated daily. The reviews shared daily on these platforms constitute big data that contain useful information for both customers and suppliers. The necessity of analyzing these big data causes to use of data mining techniques in tourism research. In this research text mining techniques which is a natural extension of data mining used to examine 3.275 Baku hotels’ reviews from booking.com. First reviews are prepared for analyzing with using the preprocessing technique. Then term frequency was constituted by using the TF-IDF technique. Consequently, it is found that staff, room, and hotel are the most spoken topics on hotel reviews.

Anahtar Kelimeler

• Online Reviews
• Text Mining
• Term Frequency

Kaynakça

1. Akgöz, E., ve Tengilimoğlu, E. (2015) Online Müşteri Değerlendirmelerinin, Tesis Özellikleri Açısından İncelenmesi; Booking.Com Örneği. 16. Ulusal Turizm Kongresi, Çanakkale Onsekiz Mart Üniversitesi, 12-15 Kasım, Çanakkale. ss: 145-165.
2. Amaro, S. and Duarte P. (2015). An İntegrative Model Of Consumers' Intentions to Purchase Travel Online, Tourism Management, 46(2015): 64-79.
3. Balouchi, M., Aziz, Y., A., Rahman, A., Hasangholipour, T., Khanlari, A., Rahmani A., A. and Raja Y. R., N. (2017). Explaining and Predicting Online Tourists’ Behavioural Intention in Accepting Consumer Generated Contents, Journal of Hospitality and Tourism Technology, 8(2): 168-189.
4. Bilgihan, A. (2012). The Role of Flow in Creatıng E-Loyalty: The Case of Online Hotel Booking Websites. Unpublished Doctor of Philosophy Dissertation, University of Central Florida, Orlando, Florida.
5. Buhalis, D. and Law, R. (2008). Progress in Information Technology and Tourism Management: 20 Years on and 10 Years After the Internet-The State of Etourism Research. Tourism Management, 29(2008): 609-623.
6. Chu, W., T. and Huang, W., H. (2017). Cultural Difference and Visual Information on Hotel Rating Prediction. World Wide Web, 20(2017): 595-619.
7. Dirsehan, T. (2016). An Application of Text Mining to Capture and Analyze eWOM: A Pilot Study on Tourism Sector. (Edit) Rathore, S. and Panwar, A. Capturing, Analyzing, and Managing Word of Mouth in the Digital Marketplace.(pp. 168-186). IGI Global, USA.
8. Emarketer (2018). Global Digital Travel Sales 2018. [Online] https://www.emarketer.com/content/global-digitaltravel- sales-2018. [Access Date; 10.12.2018].

9. Ertek, G., Tapucu, D., and Arın, I. (2013). Text Mining with RapidMiner. (Edit) Markus H. and Ralf K. RapidMiner: Data Mining Use Cases and Business Analytics Applications. Chapman & Hall/CRC Data Mining and Knowledge Discovery Series. Chapman and Hall/CRC.
10. Fang, B., Ye, Q., Kucukusta, D. and Law, R. (2016). Analysis of the Perceived Value of Online Tourism Reviews: Influence of Readability and Reviewer Characteristics. Tourism Management, 52(2016): 498- 506.
11. Fazzolari, M. and Petrocchi, M. (2018). A Study on Online Travel Review Through Intelligent Data Analysis. Information Technology & Tourism, 20(4): 37-58.
12. Godnov, U. and Redek, T. (2016). Application of Text Mining in Tourism: Case of Croatia. Research Notes And Reports / Annals of Tourism Research, 58(2016): 156-170.
13. Hu, Y., H., Chen, Y., L. and Chou, H., L. (2017). Opinion Mining From Online Hotel Reviews –A Text Summarization Approach. Information Processing and Management, 53(2017): 436-449.
14. Lee, P. J., Hu, Y. H. and Lu, K. T. (2018). Assessing the Helpfulness of Online Hotel Reviews: A Classification-Based Approach. Telematics and Informatics, 35(2018): 436-445.
15. Liu, Z., Zhang, Z., Law, R. and Zhang, A. (2019). Posting Reviews on OTAS: Motives, Rewards And Effort. Tourism Management, 70(2019): 230-237.
16. Muneta, A., Elena, M. and Andrea, O. L. (2013). ICT Impact on Tourism Industry. International Journal of Management Cases, 15(2): 87-98.
17. Nusair, K. & Parsa, H.G. (2011). Introducing Flow Theory to Explain the Interactive Online Shopping Experience in A Travel Context. International Journal of Hospitality Tourism Administration, 121(2011): 1-20.
18. Phillips, P., Zigan, K., Silva, M.M.S. and Schegg, R. (2015). The Interactive Effects of Online Reviews on the Determinants of Swiss Hotel Performance: A Neural Network Analysis. Tourism Management, 50(2015): 130-141.
19. Tengilimoğlu, E. ve Öztürk, Y. (2019a) Online Yorumların Faydalı Bulunma Durumunun İncelenmesi: Konaklama İşletmeleri Üzerine Bir Araştırma. 20. Ulusal Turizm Kongresi, Anadolu Üniversitesi, 16-19 Ekim, Eskişehir. ss: 659-670.
20. Tengilimoğlu, E. ve Öztürk, Y. (2019b) Metin Madenciliği Yöntemleri ile Online Yorumların Kümelenmesi: Bakü Otelleri Örneği. 5. International Congress of Social Science, Uluslararası Balkan Üniversitesi, Üsküp, Makedonya. ss: 595-610.
21. Tengilimoğlu, E., Göral, R. ve Akgöz, E. (2017) Olumlu Ve Olumsuz Geri Bildirimlerin Memnuniyet Düzeylerine Göre İncelenmesi: Booking.Com Örneği. 18. Ulusal Turizm Kongresi, Mardin Artuklu Üniversitesi, 18-22 Ekim, Mardin. ss: 556-570.
22. TripAdvisor (2017). TripBarometer, Traveler Trends & Motivations Global Findings. [Online] https://www.tripadvisor.com.tr/TripAdvisorInsights/w4594, [Access Date: 10.10.2020].
23. Wong, C. U. I and Qi, S. (2017). Tracking the Evolution of a Destination's Image By Text-Mining Online Reviews - The Case of Macau. Tourism Management Perspectives, 23(2017): 19-29.
24. Xiang, Z., Schwartz, A., Gerdes, J., H. and Uysal, M. (2015). What Can Big Data and Text Analytics Tell Us About Hotel Guest Experience and Satisfaction? International Journal of Hospitality Management, 44(2015): 120–130.
25. Zhang, J. J., and Verma, R. (2017). What Matters Most to Your Guests: An Exploratory Study of Online Reviews. Cornell Hospitality Report, 17(4): 3-13.