IDEAS home Printed from https://ideas.repec.org/a/spr/custns/v11y2024i1d10.1007_s40547-023-00141-y.html
   My bibliography  Save this article

Strategic Formation of CEO Apologies: Emulating Post-Crisis Public Statements Through GPT-4

Author

Listed:
  • Jeong-Ah Park

    (Korea Advanced Institute of Science and Technology)

  • Hye-Jin Kim

    (Korea Advanced Institute of Science and Technology)

Abstract

In this research, we delve into the capacity of the GPT-4 artificial intelligence model to emulate CEO apology statements during crises, which are significant in shaping public trust and perception of a company. We introduce a novel method, “Prompt Engineering for CEO Apology,” which guides the AI to mimic distinct CEO writing styles and adapt to specific crisis contexts. Our study tests GPT-4’s capabilities using data beyond its last update in September 2021, assessing its adaptability to new and varied scenarios. Our proposed framework, grounded in the principles of rhetorical persuasion (ethos, pathos, and logos), incorporates detailed crisis and CEO writing style information into the prompts. We utilized the word2vec model and cosine similarity for a brief quantitative assessment of GPT-4’s ability to replicate CEO apologies, revealing its potential in mimicking human-like narratives. Additionally, we attempted to develop a specialized GPT model for CEO apologies, integrating our approach directly into its training for enhanced practical application. Our research aims to determine the most effective prompts for AI, marking a significant step toward using AI’s potential in human-like communication, with applications extending beyond business to politics, healthcare, education, and more.

Suggested Citation

  • Jeong-Ah Park & Hye-Jin Kim, 2024. "Strategic Formation of CEO Apologies: Emulating Post-Crisis Public Statements Through GPT-4," Customer Needs and Solutions, Springer;Institute for Sustainable Innovation and Growth (iSIG), vol. 11(1), pages 1-17, December.
    • Handle: RePEc:spr:custns:v:11:y:2024:i:1:d:10.1007_s40547-023-00141-y
    DOI: 10.1007/s40547-023-00141-y
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s40547-023-00141-y
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.
    File URL: https://libkey.io/10.1007/s40547-023-00141-y?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:spr:custns:v:11:y:2024:i:1:d:10.1007_s40547-023-00141-y. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.