Key points are not available for this paper at this time.
Although ChatGPT provides excellent features as a writing assistant tool, few empirical studies have been conducted on its integration into writing education investigating students’ usage pattern and impact on the writing skills of students. This exploratory research aims to fill this research gap by analyzing prompts initiated by students and examining the effects of ChatGPT-assisted narrative writing to explore the educational potential of ChatGPT in college-level L2 writing. Toward this end, the study recruited 44 university students in South Korea. The study explored their patterns of use of ChatGPT and the effects of the narrative writing intervention assisted by ChatGPT. The major findings were as follows. The top three request prompts were: Request for language use, Request for revision, Request for information. The most frequent requests were related to linguistic aspects, and ChatGPT demonstrated successful surface-level error detection. Next, the results of the paired sample t-test and Wilcoxon signed rank test to determine the effect of ChatGPT-assisted narrative writing demonstrated high post-test scores in writing fluency and overall performance, and this difference was statistically significant. On the other hand, the post-test scores for syntactic complexity were lower than those for the pre-test, and this difference was also significant. Regarding clause complexity, clausal complements per clause exhibited a significant increase in the post-test. Based on these findings, the pedagogical implications are suggested.
Jiyoung Seo (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: