THE PATTERN OF ENCOURAGEMENT OF MAN 2 MALANG CITY STUDENTS IN WRITING CHATGPT-ASSISTED REVIEWS

Abstract

This study aims to explore the pattern of students' motivation in interaction with ChatGPT in review text writing activities. The main focus of the research lies in how students design and use prompts as strategies in directing AI responses at the revision stage (rewriting), rather than on the written output. This research uses a qualitative approach with a descriptive-analytical design. The research subjects consisted of students in two Phase F classes specializing in Science and Technology at MAN 2 Malang City. The learning activity adopts Donald M. Murray's writing process strategy so that ChatGPT is specifically integrated as a dialogical partner in the revision phase of the review text. Data in the form of 154 prompts obtained from 62 units of student interaction with ChatGPT were analyzed through a thematic coding process. The results showed that student interactions formed a diverse pattern of impulse strategies, including evaluative impulses, directed revisions, and response controls. These strategies reflect different levels of cognitive engagement in utilizing AI as a digital scaffolding in students' Proximal Development Zones (ZPDs). However, most prompts are still oriented towards general and technical improvements, indicating an effort to minimize the cognitive load in the revision process. These findings suggest that the quality of interaction with AI is highly dependent on students' ability to design prompts in a specific and reflective way. The study emphasizes that prompting is a key competency in AI-based learning and needs to be explicitly developed as part of digital literacy in pedagogical practice.