Synergizing Generative Pre-Trained Transformer (GPT) Chatbots in a Process-Based Writing Paradigm to Enhance University Students’ Writing Skills

Author:
Open Access
Publisher website
Google Scholar
Abstract
Background: The combination of the process-based writing framework and GPT-based chatbots establishes a dynamic and interactive environment, leading students through the stages of planning, drafting, revising, and editing. This collaborative approach not only elevates writing skills but also cultivates critical thinking and self-reflection, thereby transforming the writing process into a more effective and engaging learning experience. Despite the potential synergy to revolutionize the writing process, there exists a surprising lack of research within the educational domain exploring the impact of this innovative approach. Purpose: This study investigates the influence of a GPT-based chatbot within a process-based writing framework on university EFL students’ writing skills, specifically focusing on components such as organization, content, coherence-cohesion, logical connection, and argumentation. Method: Employing a sequential mixed methods type of research with a pre- and post-test design, 30 university EFL students were selected via purposive sampling technique. They engaged in 10 sessions that incorporated GPT-based chatbots within a process-based writing framework. Data collections were through pre-and post- writing tests, writing quizzes, and semi-structured interviews. Results: The results highlighted substantial improvements in participants’ writing performance, evident through a noteworthy increase in post-writing test scores (x̄=17.03) in comparison to pre-writing test scores (x̄=9.13). The study identified a progressive enhancement in four out of five writing components - organization, content, coherence-cohesion, and argumentation - across the 1st to 4th quizzes. However, the ‘logical connection’ component experienced a temporary decline during the 2nd and 3rd writing quizzes, rebounding significantly in the 4th quiz. Notably, the most improved writing components were ‘content’ and ‘argumentation,’ while the component related to ‘logical connection’ exhibited the least improved one. Qualitative findings further underscored participants’ acknowledgment of the effectiveness of the strategy in facilitating their writing tasks. Conclusion: The integration of chatbots within a writing framework was concluded as a facilitative pedagogical approach, fostering a dynamic, personalized, and effective learning experience, contributing to the multifaceted improvement of their writing skills. As educators and practitioners consider innovative approaches, this study provides a compelling case for the effective utilization of GPT-based chatbots in fostering language proficiency and a more engaging learning experience.

This publication has 19 references indexed in Scilit: