Effects of a ChatGPT-based flipped learning guiding approach on learners’ courseware project performances and perceptions

Abstract

In recent decades, flipped learning has been adopted by teachers to improve learning achievement. However, it is challenging to provide all students with instant personalised guidance at the same time. To address this gap, based on Chat Generative Pre-trained Transformer (ChatGPT) and the learning scaffolding theory, I developed a ChatGPT-based flipped learning guiding approach (ChatGPT-FLGA) according to the analysis, design, development, implementation and evaluation model. To investigate the effectiveness of ChatGPT-FLGA, a quasi-experiment was conducted in the learning activities of a courseware project. One of two classes was randomly assigned to the experimental group, while the other was assigned to the control group. The students in both classes received flipped classroom instruction and conducted discussions through Tencent QQ applications, but only those in the experimental group learned with ChatGPT-FLGA. The results revealed that the ChatGPT-FLGA significantly improved students’ performance, self-efficacy, learning attitudes, intrinsic motivation and creative thinking. The research findings enrich the literature on ChatGPT in flipped classrooms by addressing the influence of ChatGPT-FLGA on students' performance and perceptions. Implications for practice or policy: Teachers and universities should utilise ChatGPT as a tool for supporting students’ learning and promoting their problem-solving skills. Course designers and academic staff can leverage ChatGPT-FLGA to enact student-centred pedagogical transformation in massive open online courses or flipped learning. Course designers should master how to use ChatGPT-FLGA and its learning system, to foster learners’ self-regulated learning, help them promote online self-efficacy and overcome difficulties in learning motivation and creative thinking ability.

Ähnliche Arbeiten