Improving ChatGPT's Competency in Generating Effective Business Communication Messages: Integrating Rhetorical Genre Analysis into Prompting Techniques

Abstract

This study explores how prompting techniques, especially those integrated with rhetorical analysis results, may improve the effectiveness of artificial intelligence (AI)-generated business communication messages. I conducted an experiment to assess the effectiveness of these prompting techniques in the context of crafting a negative message generated with ChatGPT 3.5 ( n = 85). A multiple regression was calculated to explore prompting techniques’ impact on the negative message grades and how each technique influences the message grade. The results ( F(4, 80) = 31.84, p < .001), with an adjusted R2 = .595, indicate a positive relationship between prompting techniques and the effectiveness of AI-generated messages. This study also identified challenges related to students’ AI literacy. I conclude the study by recommending practical measures on how to incorporate AI into business and professional writing classrooms.