This study aims to analyse global aviation research trends in maintenance, safety and regulation (2015–2024) to identify key themes and contributions.
Probabilistic analysis, combined with text mining techniques, is used in this study based on Web of Science data to conduct thematic exploration through logistic regression (LR) and Markov chain modelling, providing a comprehensive assessment of contributions across countries, affiliations and journals.
Logistic regression enables the prediction and forecasting of growth trends in UAVs, aviation operations and air traffic management using a dataset of N = 6,900. Markov process analysis applied at institutional, national and journal levels indicates predominantly positive transition behaviour, while aviation materials and structures demonstrate comparatively slower progression.
This study used a unique combination of probabilistic analysis, text mining, LR and Markov chain modelling to examine research patterns. By integrating them, the study provides a novel means of mapping themes, identifying research gaps and analysing contributions from different countries, institutions and journals more effectively.
