Journal of Soft Computing and Information Technology

Journal of Soft Computing and Information Technology

Predicting Airline Passenger Satisfaction Using Hybrid Neural Networks

Document Type : Persian Original Article

Authors
Saed Dadgar 1
Zoleikha Jahanbakhsh Naghadeh 2
1 Department of Computer Engineering, ST.C., Islamic Azad University, Tehran, Iran.
2 Department of Computer Engineering, Nag.C., Islamic Azad University, Naghadeh, Iran.
10.22034/jscit.2025.493690.2081
Abstract
After the COVID-19 pandemic, the aviation industry faced significant challenges, including a sharp decline in the number of passengers. As conditions returned to normal, improving service quality to enhance passenger satisfaction and loyalty became increasingly important. In this regard, leveraging advanced technologies and deep learning can play a crucial role in predicting passenger satisfaction and optimizing services. In this study, a hybrid model based on Bidirectional Long Short-Term Memory (BiLSTM), Convolutional Neural Network (CNN), and an Attention Mechanism is proposed to predict passenger satisfaction. BiLSTM is employed for processing textual data and capturing long-term dependencies, the attention mechanism is utilized to focus on important features while ignoring less relevant information, and CNN is used to extract key features from the data. In the proposed model, the output of BiLSTM, enhanced by the attention mechanism, is combined with CNN to improve prediction accuracy. This combination enables the simultaneous utilization of BiLSTM’s ability to process sequential data along with attention weighting and CNN’s capability to extract local features, ultimately enhancing the accuracy and performance of passenger satisfaction prediction.

The dataset used consists of 129,880 passenger reviews and includes 24 key features. The final label in this dataset classifies passenger satisfaction into two categories: "satisfied" and "dissatisfied." Experimental results show that the combination of these three components (BiLSTM + CNN + Attention) achieved 99.75% accuracy, 99.97% recall, and 99.86% F1-score, demonstrating the superior performance of the proposed model in predicting passenger satisfaction. Therefore, this model can significantly assist airlines in improving service quality and increasing passenger loyalty.
Keywords
Airline industry
airlines
passenger satisfaction
BiLSTM
convolutional neural network
passenger loyalty
1] Choi, J., Seol, H., Lee, S., Cho, H., & Park, Y. (2008). Customer satisfaction factors of mobile commerce in Korea. Internet research, 18(3), 313-335. ‏
[2] Behn, B. K., & Riley Jr, R. A. (1999). Using nonfinancial information to predict financial performance: The case of the US airline industry. Journal of Accounting, Auditing & Finance, 14(1), 29-56. ‏
[3] Hariguna, T., Baihaqi, W. M., & Nurwanti, A. (2019). Sentiment analysis of product reviews as a customer recommendation using the naive Bayes classifier algorithm. International Journal of Informatics and Information Systems, 2(2), 48-55. ‏
[4] Chen, C. F. (2008). Investigating structural relationships between service quality, perceived value, satisfaction, and behavioral intentions for air passengers: Evidence from Taiwan. Transportation Research Part A: Policy and Practice, 42(4), 709-717. ‏
[5] Weng, J., Yu, J., Di, X., Lin, P., Wang, J. J., & Mao, L. Z. (2023). How does the state of bus operations influence passengers’ service satisfaction? A method considering the differences in passenger preferences. Transportation Research Part A: Policy and Practice, 174, 103734. ‏
[6] Tiernan, S., Rhoades, D. L., & Waguespack, B. (2008). Airline service quality: Exploratory analysis of consumer perceptions and operational performance in the USA and EU. Managing Service Quality: An International Journal, 18(3), 212-224. ‏ doi: 10.1108/09604520810871847.
[7] Hong, A. C. Y., KHAW, K. W., Chew, X., & Yeong, W. C. (2023). Prediction of US airline passenger satisfaction using machine learning algorithms. Data Analytics and Applied Mathematics (DAAM), 7-22. ‏
[8] Nurdina, A., & Puspita, A. B. I. (2023). Naive Bayes and KNN for Airline Passenger Satisfaction Classification: Comparative Analysis. Journal of Information System Exploration and Research, 1(2). ‏
[9] Hayadi, B. H., Kim, J. M., Hulliyah, K., & Sukmana, H. T. (2021). Predicting Airline Passenger Satisfaction with Classification Algorithms. International Journal of Informatics and Information Systems, 4(1), 82-94.
[10] Pereira, F., Costa, J. M., Ramos, R., & Raimundo, A. (2023). The impact of the COVID-19 pandemic on airlines’ passenger satisfaction. Journal of Air Transport Management, 112, 102441. ‏
[11] Dike, S. E., Davis, Z., Abrahams, A., Anjomshoae, A., & Ractham, P. (2024). Evaluation of passengers' expectations and satisfaction in the airline industry: an empirical performance analysis of online reviews. Benchmarking: An International Journal, 31(2), 611-639. ‏
[12] Mirthipati, T. (2024). Enhancing Airline Customer Satisfaction: A Machine Learning and Causal Analysis Approach. arXiv preprint arXiv:2405.09076. ‏
[13] Ibrahim, A. O., Yi, C. C., Elsafi, A., & Ghaleb, F. A. (2023, December). Revolutionizing Airline Customer Satisfaction Analysis with Machine Learning Techniques. In International Conference of Reliable Information and Communication Technology (pp. 141-152). Cham: Springer Nature Switzerland. ‏
[14] Shahid, R., Mozumder, M. A. S., Sweet, M. M. R., Hasan, M., Alam, M., Rahman, M. A, & Islam, M. R. (2024). Predicting Customer Loyalty in the Airline Industry: A Machine Learning Approach Integrating Sentiment Analysis and User Experience. International Journal on Computational Engineering, 1(2), 50-54. ‏
[15] Salehinejad, H., Sankar, S., Barfett, J., Colak, E., & Valaee, S. (2017). Recent advances in recurrent neural networks. arXiv preprint arXiv:1801.01078. ‏
[16] Liyanage, S., Abduljabbar, R., Dia, H., & Tsai, P. W. (2022). AI-based neural network models for bus passenger demand forecasting using smart card data. Journal of Urban Management, 11(3), 365-380. ‏
[17] Parnian P. (2022). Customer Reviews Classification with Text Mining and Deep Learning Approach (Case Study: Digikala Customers Reviews), 14(4), 675-694 doi: https://doi.org/10.22059/JIBM.2022.334338.4255
[18] Park, S.-H., Kim, M.-Y., Kim, Y.-J., & Park, Y.-H. (2022). A Deep Learning Approach to Analyze Airline Customer Propensities: The Case of South Korea. Applied Sciences, 12(4), 1916. https://doi.org/10.3390/app12041916
[19] Ouf, S. (2023). An optimized deep learning approach for improving airline services. Computers, Materials & Continua, 75(1), 1213–1233. https://doi.org/10.32604/cmc.2023.034399
Journal of Soft Computing and Information Technology
Volume 14, Issue 3
Autumn - October
Autumn 2025
Pages 1-12

XML
PDF 649.92 K
Supplementary File
1.1-12.pdf