Invited Speakers

Prof. Chengyuan Jia
Zhejiang University, China

Bio: Chengyuan Jia, Ph.D., is a ZJU100 Young Professor at the College of Education, Zhejiang University. Her research focuses on the application of artificial intelligence and emerging technologies in language learning and academic writing. Her recent work examines generative-AI-assisted writing, human–AI interaction, learner engagement, and the responsible integration of AI into education, using learning analytics and process-oriented methods to understand how learners interact with, evaluate, and use AI-generated support.


Speech Title: Comparing Translanguaging and Prompt Engineering Pedagogies in GenAI-Assisted EFL Academic Writing: A Randomized Controlled Trial

Abstract: The effectiveness of generative artificial intelligence (GenAI) in EFL academic writing depends not only on technological affordances but also on the pedagogical design guiding learners’ engagement. This randomized controlled trial compared translanguaging, which encourages learners to use their full linguistic repertoires, with prompt engineering, which develops their ability to formulate effective English prompts. Thirty-four EFL university students were randomly assigned to a translanguaging group (n = 14) or a prompt engineering group (n = 20). Both groups completed a guided research-paper writing task using the same GenAI system. Final writing performance was evaluated with an analytic rubric, writing speed and fluency through screen recordings, and post-task writing anxiety with a self-report questionnaire. No significant between-group difference was found in final writing performance, suggesting outcome-level equivalence. However, the translanguaging group wrote significantly faster and more fluently and reported significantly lower writing anxiety than the prompt engineering group. These findings indicate that comparable written outcomes may be achieved through different processual and affective pathways. Translanguaging may facilitate smoother, less anxiety-provoking writing by legitimizing learners’ full linguistic resources, whereas prompt engineering may strengthen strategic human–AI interaction and AI literacy. The two approaches may therefore serve as complementary pedagogies selected according to instructional priorities and learner needs.