Learning to outsmart a crisis: A strategic management view on managing aviation crises with machine learning

• Main Author: TAN, Kok Yew
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Strategic management; crisis management; airlines; machine learning; artificial intelligence; Strategic Management Policy
• Online Access: https://ink.library.smu.edu.sg/etd_coll/581; https://ink.library.smu.edu.sg/context/etd_coll/article/1579/viewcontent/Learning_to_Outsmart_a_Crisis___A_Strategic_Management_View_on_Managing_Aviation_Crises_with_Machine_Learning.pdf
• Institution: Singapore Management University

In strategic management literature, a crisis is public, unexpected, interferes with the norm, has negative impact on organizations, and generates widespread negative perceptions among stakeholders. Among crises, aviation crises are complex and present multiple vulnerabilities due to their scale, and the involvement of numerous stakeholders. With the high visibility of aviation crises due to the potential for mass injuries, deaths, and collateral damage, it could be seen as a full spectrum crisis – one of the worst among crises. The magnitude of each aviation crisis decides and allows the world to assess the efficacy of an airlines or aviation firm’s crisis management. With contemporary research using machine learning for sentiment analyses to map against established frameworks in assessing organizational tactics and review of strategies, this research proposes the use of pretrained machine learning models for sentiment and content analyses for crises in the aviation industry, mapped against the reputational standing of aviation firms after crises to assess the relationship between perceptual crisis management and a firm’s reputational impact from a crisis. Specifically, as the use of social media has been entrenched in management and communication strategies, this study retroactively examined the social media data of three airlines in crisis – Malaysia Airlines’ MH370 and AirAsia’s QZ8501 in 2014, and Ethiopian Airlines’ ETH302 in 2019. This research expands on the conventional approach of organizational learning in strategy literature by incorporating machine learning into the process, elevating the consistency, accuracy, and expediency of organizations breaking bad news in the face of reputational blows. The strategic and research innovation impact of this study is multifold – as a first validation of an emerging social media crisis communication framework (CONSOLE, by Tan et al., 2019) through a pilot study; in building a machine learning model which draws from past data and labels to classify organizational messages with high agreement levels with human coders; in deriving the effects of breaking bad news efficiency with crisis corporate reputation; and in developing the beta version of a dashboard powered by artificial intelligence which classifies and scores organizational messages based on the CONSOLE framework, and presents recommendations to improve the CONSOLE score. Bridging the academic wisdom from different fields and using technology to prevent the relearning of lessons while learning and incorporating the nuances of sentiments in the digital mediascape propel this research to present a holistic view which may guide firms beyond those in the aviation industry better in future crisis management.