Effects of ChatGPT on Students Academic Performance:Mediating Role of Prompt Engineering

Abstract

This paper focuses on the use of advanced machine learning models, such as ChatGPT, in education. ChatGPT, a language learning model by OpenAI, has shown potential for reshaping education through enhanced teaching methods, increased student engagement, and personalised learning experiences. Despite these promising features, the potential drawbacks of the technology remain unclear. This paper seeks to examine the impacts of ChatGPT on students' academic performance, with a special emphasis on the role of 'prompt engineering' in this context. This research employs a quantitative method to examine the impact of ChatGPT on student academic performance in various universities across Pakistan. An online survey was distributed, garnering responses from 37 students at several institutions. The questions focused on demographic details and the impact of ChatGPT on academic performance parameters such as learning, quality of work, and creativity, with the role of prompt engineering as a mediating factor. Data was analysed using SPSS, with Cronbach's alpha used to ensure reliability and internal consistency of the responses, which showed a high degree of correlation among responses. The results indicated a positive relationship between the use of ChatGPT and academic performance (Naveed et al., 2023). However, while most students were aware of ChatGPT's capabilities, the majority did not use it for examination preparation. The study also found that prompt engineering played a mediating role between ChatGPT usage and student academic performance, highlighting the importance of effective prompt design in optimising the benefits of AI in educational settings.