Exploring EFL students' prompt engineering in human-AI story writing: an Activity Theory perspective

The integration of NLG tools in education has generated many questions (Rospigliosi, 2023) and a growing interest among researchers. For instance, Gero et al. (2022) found NLG tools could support science writing by inspiring writers with sentences about scientific concepts; and Guo et al. (2023) found students could interact with chatbots to better prepare for classroom debates. Particularly in the context of language learning (Haristiani, 2019) NLG tools might provide language learners with real-time feedback and support in various language tasks (Chen et al., 2021). Besides, researchers have found NLG tool-based activities can positively influence English as a foreign language (EFL) students' willingness to engage in English language (Tai & Chen, 2020; Lee et al., 2023). However, individual EFL students may perceive the affordances of using NLG tools differently and some may even perceive affordances as constraints (Jeon, 2022). For EFL students to effectively interact with NLG tools to complete language tasks, it appears students will not only need strategies but also the right NLG tools (Woo et al., 2023). Activity theory (AT; Engeström, 1987) provides a framework to analyze how language learners interact with NLG tools as a mediated activity system. The present qualitative study applies AT to explore the rules governing the use of NLG tools by EFL students to write short stories. By analyzing EFL students' written reflections for the rules they have developed to interact with NLG tools, the study can provide insights into human-AI collaboration in education, improving pedagogy and tool design.