Is it too late now to say we're sorry? Examining anxiety contagion and crisis communication strategies using machine learning.

Abstract

In this paper, we explore the role of perceived emotions and crisis communication strategies via organizational computer-mediated communication in predicting public anxiety, the default crisis emotion. We use a machine-learning approach to detect and predict anxiety scores in organizational crisis announcements on social media and the public's responses to these posts. We also control for emotional and language tones in organizational crisis responses using a separate machine learning algorithm. Perceived organizational anxiety positively influences public anxiety, confirming the occurrence of emotional contagion from the organization to the public. Crisis response strategies moderated this relationship, so that responsibility acknowledgment lowered public anxiety the most. We argue that by accounting for emotions expressed in organizational crisis responses, organizations may be able to better predict and manage public emotions.