Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Pendas : Jurnah Ilmiah Pendidikan Dasar International Journal of Educational Management and Innovation (IJEMI)
Carreza, Arqoma Nurveda
Unknown Affiliation
Education Languange, Linguistic, Communication & Media Social Sciences Other

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
From Prompt to Pedagogy: Designing AI-Generated Science Comics Through ChatGPT to Employ Critical Thinking Skills Purnomo, Aris Rudi; Asteria, Prima Vidya; Abidin, Muhamad Rois; Carreza, Arqoma Nurveda; Sohnui, Suhailee
International Journal of Educational Management and Innovation Vol. 7 No. 2 (2026): in press
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/ijemi.v7i2.14685

Abstract

Background/purpose. In science learning, critical thinking skills are essential indicators for delivering deep learning. In doing so, teaching alone is not enough to make students acquire the skills. Therefore, teachers need media such as e-comics for use in their classrooms. In this study, we examine the use of ChatGPT 4.0 as a tool for automatically generating visual representations from prompts to bring out the essence of critical thinking skills. Materials/methods. This study used Design and Development Research (DDR), including needs analysis, design, and development, and expert validation. The instruments were a questionnaire and a validation rubric. The data were analyzed descriptively, considering the number of questionnaire items selected. A validation rubric is used to gain expert judgment over the quality of the e-comic developed using ChatGPT. Results. The findings indicate that “Cells” (67%) and “Pollution” (65%) were perceived as the most difficult topics. The developed e-comic was rated highly valid in terms of content, while minor improvements were suggested for media aspects such as engagement and visual consistency. The study also resulted in an AI-Prompted Comic Design Framework consisting of five stages, namely, need analysis, narrative design, prompt engineering, AI-based visual generation, and expert validation. Conclusion. The study demonstrates that ChatGPT can be effectively used to develop structured, visually consistent e-comics for science learning. The proposed framework provides practical guidance for integrating AI into instructional media design to support students’ critical thinking. However, the effectiveness of the e-comic in improving learning outcomes requires further investigation in future studies.
EVALUASI PROGRAM PELATIHAN PERANCANGAN ASESMEN BERBASIS KECERDASAN ARTIFISIAL BERDASARKAN KUALITAS PRODUK ASESMEN GURU Rusijono; Pradana, Hirnanda Dimas; Carreza, Arqoma Nurveda
Pendas : Jurnal Ilmiah Pendidikan Dasar Vol. 11 No. 03 (2026): Volume 11 No. 03, September 2026 Processed
Publisher : Program Studi Pendidikan Guru Sekolah Dasar FKIP Universitas Pasundan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23969/jp.v11i03.62518

Abstract

This study aimed to evaluate a training program on designing artificial intelligence (AI)-based assessments, focusing on the quality of the assessment products created by teachers. Although generative AI offers new opportunities for assessment design, teachers' ability to utilize it pedagogically requires strengthening through structured training. An evaluative research method with a descriptive quantitative approach was applied to 25 teachers participating in a five-stage training program: content delivery, AI demonstration, a design workshop, independent product development, and a presentation and feedback session. The products were assessed using a five-aspect rubric—alignment with learning objectives, instrument quality, authenticity, AI integration, and rubric quality—on a scale of 1 to 4. The results showed an overall average of 3.44 (categorized as "very good"), with the highest score in alignment with learning objectives (M=3.64) and the lowest in AI integration (M=3.08). 56% of participants achieved the "very good" category, while 44% fell into the "good" category. The findings indicate that product-based evaluation provides an authentic picture of teachers' competency attainment while identifying areas requiring improvement, particularly regarding the critical and reflective use of AI.
Co-Authors Abidin, Muhamad Rois Asteria, Prima Vidya Purnomo, Aris Rudi RUSIJONO Sohnui, Suhailee