Integrating ChatGPT-driven self-assessment and Debate Based on Inquiry Learning (DBOIL) to enhance students’ argumentation skills: Leveraging AI for quality science learning aligned with SDG 4

¹ Department of Science Education, Universitas Negeri Surabaya, Indonesia
² Department of Science Education, Universitas Islam Lamongan, Indonesia
³ Department of English Literature, Universitas Islam Negeri Sunan Ampel Surabaya, Indonesia
⁴ Baptist Health Medical Group, Baptist Health Quality Network, United States of America

^* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

Argumentation is an important skill in science learning, yet most students are not really proficient at it. It has been shown that the Debate-Based on Inquiry Learning (DBOIL) model significantly enhances these skills. It is still challenging to encourage students to come up with arguments that are indeed deep, incisive, and relevant. Artificial Intelligence (AI), in the form of ChatGPT, has shown itself to be a viable solution to all these issues. The aim of this research is to examine and evaluate the effectiveness of integrating ChatGPT-driven self-assessment and DBOIL-based science learning in improving students’ argumentation skills. A one-group pretest-posttest design, involving 33 first-year students of a Science Education Undergraduate Program at an Indonesian state university, was conducted. The results of this research demonstrate that the intervention improves students’ argumentation skills. ChatGPT is a large language model capable of providing you with personalized, constructive, and quality feedback. Improvement is made possible by this feature. The integration of ChatGPT in the DBOIL framework not only makes the inquiry process better, but also allows students to comprehend, discuss, and debate science issues in a more meaningful way, which is in line with Sustainable Development Goal (SDG) 4.