Optimizing Learning Materials With DeepSeek Transformer In diEvaluasi System
DOI:
https://doi.org/10.31598/sintechjournal.v8i2.1903Keywords:
Adaptive Learning, DeepSeek Transformer, Personalized Education, ICT, Educational TechnologyAbstract
Most digital learning media presented learning materials uniformly, ignoring individual student needs and learning profiles. This study aimed to develop and evaluate diEvaluasi, an adaptive learning system based on the DeepSeek Transformer model. The system adapted content delivery using student profiles derived from pre-test scores, interaction history, and cognitive patterns. A quasi-experimental method was applied to 60 eleventh-grade high school students divided into experimental and control groups. The DeepSeek model was fine-tuned using ICT learning materials and student interaction data. The results showed a 40.2% improvement in post-test scores in the experimental group, compared to 20.4% in the control group. Students in the experimental group also recorded longer learning times and higher repetition rates. These findings indicated that the diEvaluasi system effectively improved academic performance and engagement through personalized material sequencing. The system provided a practical approach to implementing AI-powered adaptive learning in secondary education, especially in ICT contexts.
References
[1] L. Lukman, R. Agustina, and R. Aisy, “Problematika Penggunaan Artificial Intelligence (AI) untuk Pembelajaran di Kalangan Mahasiswa STIT Pemalang,” Madaniyah, vol. 13, no. 2, pp. 242–255, 2023. doi: 10.58410/madaniyah.v13i2.826
[2] A. Franz et al., “Pelatihan Penerapan Artificial Intelligence (AI) untuk Menunjang Aktifitas Pembelajaran pada Sekolah Dasar Daarul Hijrah Al-Amin Samarinda,” JLP : Jurnal Lentera Pengabdian, Oct. 2023. doi: 10.59422/lp.v1i04.139
[3] K. S. Kartini and I. N. T. A. Putra, “Respon Siswa Terhadap Pengembangan Media Pembelajaran Interaktif Berbasis Android,” Jurnal Pendidikan Kimia Indonesia, vol. 4, pp. 12–19, 2020. doi: 10.23887/jpk.v4i1.24981
[4] E. Panadero and J. Alonso-Tapia, “How Do Students Self-Regulate? Review of Zimmerman‟s Cyclical Modelof Self-Regulated Learning,” Anales de Psicologia, vol. 30, no. 2, pp. 450–462, 2014. doi: 10.6018/analesps.30.2.167221
[5] A. Vaswani et al., “Attention Is All You Need,” Conference on Neural Information Processing Systems, 2017. doi: 10.48550/arXiv.1706.03762
[6] C. Wang and M. Kantarcioglu, “A Review of DeepSeek Models’ Key Innovative Techniques,” ArXiv, Mar. 2025. doi: 10.48550/arXiv.2503.11486
[7] A. Paramythis and S. Loidl-Reisinger, “Adaptive Learning Environments and e-Learning Standards,” IEEE Transactions on Learning Technologies, 2023.
[8] N. Nurhayati, M. Suliyem, I. Hanafi, and T. T. D. Susanto, “Integrasi AI dalam collaborative learning untuk meningkatkan efektivitas pembelajaran,” Academy of Education Journal, vol. 15, no. 1, pp. 1063–1071, 2024. doi: 10.47200/aoej.v15i1.2372
[9] A. H. Kaluge, “Pemanfaatn AI Untuk Meningkatkan Pemahaman Konsep Matematika di Era Digital,” SEMNAPTIKA IV, 2024.
[10] F. Naseer and S. Khawaja, “Mitigating Conceptual Learning Gaps in Mixed-Ability Classrooms: A Learning Analytics-Based Evaluation of AI-Driven Adaptive Feedback for Struggling Learners,” Applied Sciences, vol. 15, no. 8, p. 4473, 2025. doi: 10.3390/app15084473
[11] Z. Qian et al., “Harnessing the Power of Large Language Model for Uncertainty Aware Graph Processing,” ArXiv, Mar. 2024.
[12] I. Ghozali, “Aplikasi analisis multivariete dengan program IBM SPSS 23,” 2018.
[13] D. Eriawan and L. V. Putra, “Pengaruh Model Pembelajaran Savi Berbantuan Cafas terhadap Pemahaman Konsep Siswa,” JANACITTA : Journal of Primary and Children’s Education, vol. 8, pp. 2615–6598, Mar. 2025. doi: 10.35473/janacitta.v8i1.3862
[14] E. Humolungo, G. Abdullah, and P. Fakultas Ilmu Pendidikan Univesitas Negeri Gorontalo, “Pengaruh Model Pembelajaran Inquiry Berbantuan Media Wordwall Terhadap Hasil Belajar Siswa Materi Wujud Zat dan Perubahan di Kelas IV SD,” SCIENCE : Jurnal Inovasi Pendidikan Matematika dan IPA, vol. 5, no. 2, 2025.
[15] X. Wang, Z. Chen, H. Wang, L. Hou U, Z. Li, and W. Guo, “Large language model enhanced knowledge representation learning: A survey,” Data Sci Eng, pp. 1–24, 2025. doi: 10.48550/arXiv.2407.00936
[16] P. P. Kuantitatif, “Metode Penelitian Kunatitatif Kualitatif dan R&D,” Alfabeta, Bandung, 2016.
[17] H. N. Boone Jr and D. A. Boone, “Analyzing likert data,” The Journal of extension, vol. 50, no. 2, p. 48, 2012. doi: 10.34068/joe.50.02.48
[18] N. Zebua, “Optimalisasi Potensi dan Pemanfaatan Artificial Intelligence (AI) Dalam Mendukung Pembelajaran di Era Society 5.0,” Pentagon : Jurnal Matematika dan Ilmu Pengetahuan Alam, vol. 2, no. 4, pp. 185–195, Dec. 2024. doi: 10.62383/pentagon.v2i4.314
[19] Supriyatmoko, K. Anam, and W. Kurniawan, “Model Pembelajaran Adaptif Berbasis Kecerdasan Buatan: Peluang Dan Tantangan Dalam Mewujudkan Pendidikan Personalisasi,” STRATEGY : Jurnal Inovasi Strategi dan Model Pembelajaran, Jan. 2025. doi: 10.51878/strategi.v5i1.4944
[20] I. N. T. A. Putra, A. Yuniarti, H. Fabroyir, and I. P. B. G. P. Raharja, “Transformer Performance Evaluation in 3D Reconstruction of Balinese Mask Wood Carving,” in 2024 International Seminar on Intelligent Technology and Its Applications (ISITIA), 2024, pp. 285–289.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 I Nyoman Tri Anindia Putra, I Gede Bagastia Widi Atmaja, Komang Mahendra, Gede Agus Supriatmaja, I Putu Mas Yuda Pratama
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
1.png)
