Üretken Yapay Zekâ Destekli Bir Havayolu Yolcu Geri Bildirimi Analizi: En Önemli Olanı Ortaya Çıkarmak

Öz

Yoğun rekabetin yaşandığı havayolu endüstrisi, müşteri memnuniyetine büyük ölçüde dayanarak güçlü ve zayıf yönlerini değerlendirir. Çevrimiçi yolcu yorumları, müşterilerin görüşlerini, beklentilerini ve duygularını yansıtan zengin bir veri kaynağı sunar. Bu geri bildirimlerin analizi, havayollarının geliştirilmesi gereken alanları belirlemesine ve yolcular için en önemli olanı anlamasına yardımcı olur. Bu çalışma, 2024 yılında Trip Advisor web sitesinden toplanan Türk Hava Yolları yorumlarını yorumlamak için Google Gemini’nin sıfırdan yönlendirme (zero-shot prompting) yaklaşımını kullanarak, alan spesifik ince ayara gerek kalmadan modelin etkinliğini göstermektedir. Bulgular, algılanan hizmet kalitesini, performansını ve değeri etkileyen faktörleri ortaya koymakta ve üretici yapay zekânın uzmanlaşmış müşteri duygu analizindeki potansiyelini ve havayolu endüstrisindeki uygulamalarını göstermektedir.

Anahtar Kelimeler

• Müşteri yorumları analizi
• doğal dil işleme
• büyük dil modelleri
• üretken AI
• google gemini

A Generative AI-Driven Analysis of Airline Passenger Feedback: Revealing What Matters Most

Öz

The airline industry, characterized by intense competition, relies heavily on customer satisfaction to assess strengths and weaknesses. Online passenger reviews provide a rich source of data, capturing customers’ opinions, expectations, and emotions. Analyzing this feedback helps airlines identify areas for improvement and understand what matters most to passengers. This study employs a zero-shot prompting approach using Google Gemini to interpret Turkish Airlines reviews from Trip Advisor in 2024, demonstrating the model’s effectiveness without domain-specific fine-tuning. The findings highlight factors influencing perceived service quality, performance, and value, illustrating the potential of generative AI in specialized customer sentiment analysis and its practical applications in the airline industry.

Anahtar Kelimeler

• Customer review analysis
• natural language processing
• large language models
• generative AI
• google gemini

Kaynakça

1. Al-Otaibi S T, Rasheed A. Review and Comparative Analysis of Sentiment Analysis Techniques. Informatica. 2022; 46 (1): 33–44
2. Hai Z, Kim K C J ve Yang C. Identifying features in opinion mining via intrinsic and extrinsic domain relevance. IEEE Trans Knowl Data Eng. 2014; 26 (3): 634.
3. Cui J, Wang Z ve Cambria E. Survey on sentiment analysis: evolution of research methods and topics. Artificial Intelligence Review. 2023; (56): 8469–8510.
4. Taherdoost E ve Madanchian M. Artificial Intelligence and Sentiment Analysis: A Review in Competitive Research. Computers, 2023; 12 (37).
5. Khan M T, Durrani M ve Ali A. Sentiment analysis and the complex natural language. Complex Adapt Syst Model. 2016; 4 (2).
6. Ramadhan F, Sitanggang A, Wibawa J ve Radliya N. Implementation of Digital Marketing Strategy with Chatbot Technology. Int. J. Artif. Intell. Res. 2023; 7 (2): 132.
7. Wu S ve Gao Y. Machine Learning Approach to Analyze the Sentiment of Airline Passengers’ Tweets. Transp. Res. Rec. 2023; 2678 (1).
8. Patel A, Oza P ve Agrawal S. Sentiment Analysis of Customer Feedback and Reviews for Airline Services using Language Representation Model. Procedia Comput. Sci. 2023; 218: 2459–2467.

9. Sezgen E, Mason K J ve Mayer R. Voice of airline passenger: A text mining approach to understand customer satisfaction..J. Air Transp. Manag. 2019; 77: 65–74.
10. Siering M, Deokar A V ve Janze C. Disentangling consumer recommendations: Explaining and predicting airline recommendations based on online reviews. Decis. Support Syst. 2018; 107: 52–63.
11. Kumar S ve Zymbler M. A. Machine learning approach to analyze customer satisfaction from airline tweets. J. Big Data. 2019; 6 (62).
12. Lucini F, Tonetto L M, Fogliatto F S ve Anzanello M J. Text mining approach to explore dimensions of airline customer satisfaction using online customer reviews. J. Air Transp. Manag. 2020; 83 (4).
13. Sudirjo F, Diantoro K, Al-Gasawneh J -A, Azzaakiyyah H K ve Ausat A M A. Application of ChatGPT in Improving Customer Sentiment Analysis for Businesses. Jurnal Teknologi Dan Sistem Informasi Bisnis. 2023; 5 (3): 283–288.
14. Wang Z, Xie Q, Ding Z, Feng Y ve Xia R. Is ChatGPT a good sentiment analyzer? A preliminary study. arXiv preprint. 2023. arXiv 2304.04339.
15. Agarwal B, Mittal N, Bansal P ve Garg S. Sentiment Analysis Using Common-Sense and Context Information. Journal of Computational Intelligence and Neuroscience. 2015; 6:715730.
16. Das B ve Chakraborty S. An Improved Text Sentiment Classification Model Using TF-IDF and Next Word Negation. 2018; 10.48550/arXiv.1806.06407.
17. Hassan A U, Hussain J, Hussain M, Sadiq M ve Lee S. Sentiment Analysis of Social Networking Sites (SNS) Data Using Machine Learning Approach for the Measurement of Depression. In: International Conference on Information and Communication Technology Convergence (ICTC). Jeju, South Korea: IEEE, 2017.
18. Akter A ve Aziz M T. Sentiment Analysis on Facebook Group Using Lexicon Based Approach. In: 3rd International Conference on Electrical Engineering and Information Communication Technology (ICEEICT); September 2016.
19. Dhaoui C, Webster C M ve Tan L P. Social Media Sentiment Analysis: Lexicon Versus Machine Learning. Journal of Consumer Marketing. 2017; 34 (6): 480-488.
20. George A S ve George A H. A review of chatgpt ai’s impact on several business sectors. Partners Universal International Innovation Journal, 2023; 1 (1): 9–23.
21. Radford A, Narasimhan K, Salimans T ve Sutskever I. Improving language understanding by generative pre-training. pre-print, 2018.
22. Chen H, De P, Hu Y J ve Hwang B H. Wisdom of crowds: The value of stock opinions transmitted through social media. The Review of Financial Studies. 2014; 27: 1367–1403.
23. Tetlock P C. Giving content to investor sentiment: The role of media in the stock market. The Journal of Finance. 2007; 62 (3): 1139–1168.
24. Singh N ve Jaiswal U C. Sentiment Analysis Using Machine Learning: A Comparative Study. ADCAIJ (Advances in Distributed Computing and Artificial Intelligence Journal) Regular Issue. 2023; 12 (1): 2255-2863.