Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal Pilar Nusa Mandiri Jurnal Cakrawala Pendas
Sena Aditia Apriadi
Universitas Muhammadiyah Kuningan
Computer Science & IT Education Languange, Linguistic, Communication & Media Mathematics Other

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

Found 2 Documents
Search

 1 
GENERATIVE AI-ENHANCED GAME-BASED LEARNING FOR CREATIVE SKILL DEVELOPMENT IN ELEMENTARY STUDENTS Yani Fitriyani; Sena Aditia Apriadi; Sulistiani; Ndaru Mukti Oktaviani
Jurnal Cakrawala Pendas Vol. 11 No. 4 (2025)
Publisher : Universitas Majalengka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31949/jcp.v11i4.15304

Abstract

Student creativity in Indonesia remains a serious problem that requires special attention, with the 2022 PISA survey identifying only 5% of students achieving high creativity. Science learning is also still limited in integrating technology to develop creativity, even though this ability is a very important competency in the digital era. This study aims to develop Game-based Learning (GBL) with Generative AI (Gen AI) to improve the creativity of 5th grade elementary school students. The research method uses Research and Development (RnD) with the ADDIE model including five stages: analysis, design, development, implementation, and evaluation. The subjects of this study were 20 5th grade students of SDN Kutakembaran 1. GBL was developed with the ChatGPT-3.5 API to produce adaptive learning content. ChatGPT-3.5 works by analyzing student responses, automatically generating game scenarios, questions, and challenges tailored to the individual student's ability level. This development is enriched with West Javanese cultural elements such as folklore, traditions, and local contexts to increase the relevance of learning. The research instruments include expert validation (n=5), a creativity rubric that measures four indicators (fluency, flexibility, originality, elaboration) through problem-solving tasks, and observation of student engagement using a Likert scale that records active participation. The expert validation results showed a feasibility score of 77.50 (good category) with an Aiken's V coefficient of 0.813 (p<0.001). Implementation resulted in a significant increase in the creativity dimensions: fluency (23%, p<0.05), flexibility (31%, p<0.01), originality (28%, p<0.05), and elaboration (19%, p<0.05). Student engagement reached an average of 78.60 with 80% positive responses, while technology acceptability reached 83.45%. The culture-based GBL-GenAI media has proven effective in developing student creativity and making a significant contribution to innovation in science learning for the transformation of Indonesian basic education.
MACHINE LEARNING FOR EMPLOYMENT POSITION MAPPING Sena Aditia Apriadi; Hilman Ferdinandus Pardede
Jurnal Pilar Nusa Mandiri Vol. 21 No. 2 (2025): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Pe
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v21i2.3028

Abstract

Employee performance directly impacts organizational efficiency, yet traditional HR analytics often lack predictive precision. This study bridges HR theory and machine learning by evaluating tree-based algorithms for employee data analysis. Using a dataset of 15,227 employee records, we tested the Bagged Decision Tree algorithm, focusing on variables such as talent, career values, and aspirations. The Bagged Decision Tree achieved 98.65% accuracy, with talent and career values as key predictors. Excluding aspiration values reduced accuracy slightly to 98.57%, while excluding career values lowered it significantly to 92.13%. These findings highlight the robustness of the Bagged Decision Tree in HR analytics and emphasize the importance of variable selection, particularly career values and talent, in predicting performance outcomes. Future work should further explore real-world implementation challenges.
Co-Authors Hilman Ferdinandus Pardede Ndaru Mukti Oktaviani Sulistiani Yani Fitriyani