The study purpose was to examine the extent to which students’ written communication style affects the accuracy of ChatGPT’s responses. As ChatGPT becomes increasingly utilized as an academic support tool, the ability to craft precise prompts is crucial. This research employed a descriptive quantitative approach and a light experimental design. The sample included 50 Communication Science students at UIN Raden Fatah Palembang, class of 2022, selected through purposive sampling. Students submitted their typical prompts, which were categorized into informative, narrative, descriptive, and persuasive styles. ChatGPT's responses were evaluated based on relevance, completeness, and factual accuracy. Results revealed that the descriptive style yielded the highest accuracy score (M = 4.10), followed by informative (M = 3.74), narrative (M = 3.51), and persuasive (M = 3.23). Pearson correlation analysis showed a significant positive relationship (r = 0.413, p = 0.003) between communication style and response accuracy. A simple linear regression produced the equation Y = 3.392 + 0.113X, indicating that an improvement in communication quality leads to more accurate ChatGPT responses.. This study highlights the importance of writing skills in digital interaction and recommends integrating AI literacy into higher education curricula so that students can effectively communicate with AI-powered systems..
Copyrights © 2025