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, including pilots, air traffic controllers, mechanics, flight attendants, dispatchers, and other members of the aviation community and the public. 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: Perilog and Word2Vec. An identical search using both programs was done on a database containing approximately 470,000 ASRS reports submitted between 1988 and 2022. 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.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Extracting Lessons of Resilience Using Machine Mining of the ASRS Database


    Contributors:

    Conference:

    22nd International Symposium on Aviation Psychology (ISAP) ; 2023 ; Rochester, NY, US


    Type of media :

    Conference paper


    Type of material :

    No indication


    Language :

    English




    ASRS Form for Mechanics

    Online Contents | 1999




    Ground Operations and ASRS

    L. Connell / D. Wichner / A. M. Jakey | NTIS | 2013


    ASRS GA Weather Encounters

    Online Contents | 2007