A Data-Driven Approach to Air Traffic Delay Prediction and Sentiment Evaluation

  • Authors

    • Sushil Khairnar Software Engineer, Audible Inc
    • Deep Bodra Software Engineer, Audible Inc
    https://doi.org/10.14419/cdx7kx09

    Received date: June 28, 2025

    Accepted date: August 1, 2025

    Published date: August 8, 2025

  • Machine Learning, Predictive Analytics, Sentiment Analysis, Feature selection

  • Abstract

    Flight delays pose significant challenges to passengers and aviation stakeholders alike, causing not only inconvenience but also substantial economic losses. In this study, we present a machine learning-based approach to predict air traffic delays using real-world flight, airline, and airport datasets. We evaluate multiple regression models including Linear Regression, Lasso, Ridge, Decision Tree, and Random Forest through cross validation, achieving high predictive accuracy, particularly when departure delay is used as a feature. To complement this quantitative analysis, we conduct sentiment analysis on over 1,000 tweets related to flight delays, offering insights into public perception and emotional response. Our results indicate a strong correlation between departure and arrival delays (r 0.94) and highlight the reputational risks airlines face due to negative passenger experiences. The combined methodology demonstrates how predictive analytics and sentiment mining can be leveraged to mitigate the operational and perceptual impact of flight delays.

  • References

    1. Saleh Albahli, Waleed Albattah, and Yaser Khamayseh. 2022. Sentiment analysis for monitoring Twitter messages related to COVID-19 in Saudi Arabia using ensemble deep learning. Neural Computing and Applications 34 (2022), 12145–12158. hNps://doi.org/10.1007/s00521-021-06724-1
    2. Mehmet Cemal Atlıoğlu, Mustafa Bolat, Murat Şahin, Volkan Tunalı, and Deniz Kılınç. 2020. Supervised Learning Approaches to Flight Delay Prediction. Sakarya University Journal of Science 24, 6 (2020), 1223 – 1231. hNps://doi.org/10.16984/saufenbilder.710107
    3. Deep Bodra and Sushil Khairnar. 2025. Comparative performance analysis of modern NoSQL data technologies: Redis, Aerospike, and Dragonfly. Journal of Research, Innovation and Technologies 4, 2(8) (2025), 193–200. hNps://doi.org/10.57017/jorit.v4.2(8).05
    4. Johan Bollen, Huina Mao, and Xiaojun Zeng. 2011. Twitter mood predicts the stock market. Journal of Computational Science 2, 1 (2011), 1–8. hNps://doi.org/10.1016/j.jocs.2010.12.007
    5. Stephane Bratu and Cynthia Barnhart. 2004. An Analysis of Airline Passenger Delays Using Flight Operations and Passenger Booking
    6. Data. Air Traffic Control Quarterly 13 (01 2004). hNps://doi.org/10. 2514/atcq.13.1.1
    7. Ehsan Esmaeilzadeh and Seyedmirsajad Mokhtarimousavi. 2020. Ma- chine Learning Approach for Flight Departure Delay Prediction and Analysis. Transportation Research Record 2674, 8 (2020), 145–159. hNps://doi.org/10.1177/0361198120930014
    8. Takashi Fukumoto and Tomohiro Yamamoto. 2021. Analysis of Flight Delay Propagation Using Network Models. Journal of Advanced Trans- por-tation 2021 (2021), 8824706. hNps://doi.org/10.1155/2021/8824706
    9. Devamanyu Hazarika, Soujanya Poria, and Erik Cambria. 2022. RoBERTa for Sarcasm Detection in Social Media: A Context-Aware Approach. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL). Association for Computational Linguistics, 1234–1245. hNps://doi.org/10.18653/v1/2022.acl-main.567
    10. Sushil Khairnar. 2025. Application of Blockchain Frameworks for Decentralized Identity and Access Management of IoT Devices. Inter- national Journal of Advanced Computer Science and Applications 16, 6 (2025). hNps://doi.org/10.14569/IJACSA.2025.0160604
    11. Sushil Khairnar, Gaurav Bansod, and Vijay Dahiphale. 2019. A Lightweight Cryptographic Solution for 6LoWPAN Protocol Stack. In Intel- ligent Computing, Kohei Arai, Supriya Kapoor, and Rahul Bhatia (Eds.). Springer International Publishing, Cham, 977–994.
    12. Sushil Khairnar and Deep Bodra. 2025. Recommendation Engine for Amazon Magazine Subscriptions. International Journal of Advanced Com-puter Science and Applications 16, 7 (2025). hNps://doi.org/10. 14569/IJACSA.2025.0160796
    13. Young Jin Kim, Sun Choi, Simon Briceno, and Dimitri Mavris. 2016. A deep learning approach to flight delay prediction. In 2016 IEEE/AIAA35th Digital Avionics Systems Conference (DASC). 1–6. hNps://doi.org/ 10.1109/DASC.2016.7778092
    14. ]li2019twitter Yang Li, Ying Wang, and Jian Zhao. [n. d.]. Twitter data analysis in emergency situations: A study on flight delay events. Infor-mation Processing & Management ([n. d.]). hNps://doi.org/10.1016/ j.ipm.2019.102067
    15. Ke Liu, Kaijing Ding, Xi Cheng, Guanhao Xu, Xin Hu, et al. 2025. Airport Delay Prediction with Temporal Fusion Transformers. In IWCTS’24: Proceedings of the 17th ACM SIGSPATIAL International Work- shop on Computational Transportation Science. ACM, 5–11. hNps:
    16. //doi.org/10.1145/xxxxx
    17. Lei Liu, Shasha Zhai, and Yifan Zhang. 2020. Combining meteoro- logical and operational data for flight delay prediction using deep learning. Journal of Air Transport Management 89 (2020), 101894. hNps://doi.org/10.1016/j.jairtraman.2020.101894
    18. Chao Wang and Yifan Cao. 2022. Predictive analytics of flight delay us- ing XGBoost and time series analysis. Aerospace Science and Technology 123 (2022), 107462. hNps://doi.org/10.1016/j.ast.2022.107462
    19. Ning Xu, George L. Donohue, Kathryn B. Laskey, and Chun-Hung Chen. 2005. Estimation of Delay Propagation in the National Aviation System Using Bayesian Networks.
    20. Bojia Ye, Bo Liu, Yong Tian, and Lili Wan. 2020. A Methodology for Predicting Aggregate Flight Departure Delays in Airports Based on Super-vised Learning. Sustainability 12, 7 (2020). hNps://doi.org/10. 3390/su12072749
    21. Li Zhang, Yufei Li, and Hao Wang. 2023. Transformers for Flight Delay Prediction. IEEE Transactions on Intelligent Transportation Systems 24, 2 (2023), 1890–1902. hNps://doi.org/10.1109/TITS.2023.3245678

  • Downloads

  • How to Cite

    Khairnar, S., & Bodra, D. . (2025). A Data-Driven Approach to Air Traffic Delay Prediction and Sentiment Evaluation. International Journal of Basic and Applied Sciences, 14(4), 184-193. https://doi.org/10.14419/cdx7kx09