Analysis of Civil Aviation Incident Reporting and Discovery Issues Based on Text Mining Techniques

DOI: https://doi.org/10.62517/jsse.202408302

Author(s)

Zhenzhong Zhang*

Affiliation(s)

CAAC Academy, Civil Aviation Flight University of China, Guanghan, Sichuan, China *Corresponding Author.

Abstract

In the aviation industry, ensuring safe operations is a top priority, however, the traditional regulatory model often faces problems such as information asymmetry and unclear inspection focus, resulting in a low problem detection rate and inefficient supervision. With the rapid development of big data and artificial intelligence technology, the construction of a risk management early warning system through the construction of a smart supervision platform can analyze the problems of the supervised parties in a multi-dimensional way, analyze and assess the overall operational risks of airports and airlines, so as to realize accurate supervision. In this paper, we will discuss in detail how to use text technology to analyze the unsafe event reports and inspections to find problems, in order to help realize precise supervision.

Keywords

Aviation Safety; Text Mining; Natural Language Processing; Problem Categorization; Risk Warning

References

[1]Xu Y. The Construction of Ecological Teaching Model of Reading and Appreciation for Ethnic Preparatory Course. Curriculum and Teaching Methodology, 2023, 6(12): 1-5. [2]Zhang Y, Wei L, Liu X, et al. Nanocellulose/N, O co-doped graphene composite hydrogels for high gravimetric and volumetric performance symmetric supercapacitors. International Journal of Hydrogen Energy, 2022, 47(79): 33827-33838. [3]Pidgeon N, O'Leary M. Man-made disasters: why technology and organizations (sometimes) fail. Safety science, 2000, 34(1-3): 15-30. [4]Kao A, Poteet S R. Natural language processing and text mining. Springer Science & Business Media, 2007. [5]Jia N, Zheng C, Sun W. Speech synthesis of children’s reading based on cycle GAN model//Journal of Physics: Conference Series. IOP Publishing, 2020, 1607(1): 012046. [6]Chapelle O, Sindhwani V, Keerthi S S. Optimization techniques for semi-supervised support vector machines. Journal of Machine Learning Research, 2008, 9(2). [7]Roßbach P. Neural Networks vs. Random Forests–Does it always have to be Deep Learning?. Germany: Frankfurt School of Finance and Management, 2018. [8]de Souza C S, Leitão C F, Prates R O, et al. Can inspection methods generate valid new knowledge in HCI? The case of semiotic inspection. International Journal of Human-Computer Studies, 2010, 68(1-2): 22-40. [9]Tixier A J P, Hallowell M R, Rajagopalan B, et al. Automated content analysis for construction safety: A natural language processing system to extract precursors and outcomes from unstructured injury reports. Automation in Construction, 2016, 62: 45-56.