Document Type
Article
Publication Date
5-31-2023
Abstract
NASA’s Aviation Safety Reporting System (ASRS) database is the world's largest repository of voluntary, confidential safety information provided by aviation's frontline personnel. The database contains close to 2 million narratives, many of which describe everyday situations in which people saved the day. In these situations, people’s resilient behavior solved a problem, dealt with a malfunction, and maintained a safe operation despite a serious perturbation. To be able to extract lessons of such resilience from this large database, the use of machine learning algorithms is being explored. In this report, we describe a comparison between two such algorithms: BERT and Word2Vec. An identical search using both programs was done on a database containing approximately 270,000 ASRS reports. The comparison reveals some of the strength and weaknesses of each algorithm as well as the challenges inherent in using such algorithms to extract lessons of resilience from the ASRS database.
Repository Citation
Barshi, I.,
Matthews, B.,
& Feldman, J.
(2023). Extracting Lessons of Resilience Using Machine Mining of the ASRS Database. 22nd International Symposium on Aviation Psychology, 21.
https://corescholar.libraries.wright.edu/isap_2023/17
