Comparative Analysis of Topic Modeling Techniques on ATSB Text Narratives Using Natural Language Processing

TL;DR

This study compares four prominent topic modeling techniques to analyze aviation incident narratives, aiming to enhance safety insights from textual accident reports using NLP methods on ATSB data.

Contribution

It provides a systematic comparison of pLSA, LSA, LDA, and NMF for extracting themes from aviation safety reports, highlighting their respective strengths and weaknesses.

Findings

LDA and NMF outperform pLSA and LSA in thematic coherence.

Each technique reveals different insights into incident narratives.

The study guides safety professionals in selecting suitable NLP methods.

Abstract

Improvements in aviation safety analysis call for innovative techniques to extract valuable insights from the abundance of textual data available in accident reports. This paper explores the application of four prominent topic modelling techniques, namely Probabilistic Latent Semantic Analysis (pLSA), Latent Semantic Analysis (LSA), Latent Dirichlet Allocation (LDA), and Non-negative Matrix Factorization (NMF), to dissect aviation incident narratives using the Australian Transport Safety Bureau (ATSB) dataset. The study examines each technique's ability to unveil latent thematic structures within the data, providing safety professionals with a systematic approach to gain actionable insights. Through a comparative analysis, this research not only showcases the potential of these methods in aviation safety but also elucidates their distinct advantages and limitations.