Claim Missing Document
Check
Articles

Pemanfaatan Gemini AI Sebagai Media Pendukung Pembelajaran Di SMKS Arroja Tasikmalaya Alicia Pramesti; Alfadl Habibie; Taofik Muhammad
JURNAL ILMIAH PENELITIAN MAHASISWA Vol 4 No 6 (2026): Desember
Publisher : Kampus Akademik Publiser

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61722/jipm.v4i6.3158

Abstract

Advances in digital technology and the demands of 21st-century learning call for adaptive and personalised learning resources; however, at SMKS Arroja Tasikmalaya, Year 11 pupils still face difficulties in understanding abstract and complex subject matter, teachers have limited time for individual support, and pupils show little initiative in asking questions. This study aims to describe the utilisation of Gemini AI as a learning support tool at SMKS Arroja Tasikmalaya. The study employs a qualitative approach using a survey method. Data were collected through non-participant observation, semi-structured interviews with IT teachers and students, and a questionnaire distributed to 50 Year 11 TKJ students. Data analysis was conducted using the Miles and Huberman interactive model through the stages of data reduction, data presentation, and drawing conclusions, supplemented by triangulation of sources and techniques. The results of the study indicate that Gemini AI is utilised selectively and specifically for difficult topics such as subnetting, IP addresses, and network troubleshooting, with teachers acting as facilitators who guide students’ exploration and subsequently discuss the results in class. Students gave positive feedback: over 90 per cent found Gemini AI easy to use, 70 per cent considered it a useful learning resource, 64 per cent felt it helped them complete tasks more quickly, and 74 per cent felt it aided their learning. However, the benefits regarding in-depth understanding (around 46 per cent) and independent learning (38–52 per cent) were not yet optimal. The main constraints were limited internet connectivity (74 per cent) and the need for technical guidance (48 per cent). These findings suggest that the use of Gemini AI has the potential to enhance vocational learning provided it is supported by adequate internet infrastructure, teachers’ scaffolding strategies, and improved digital literacy amongst students so that the technology is used critically and does not lead to dependency.
Penerapan Model 10-Fold Cross-Validation dalam Memprediksi Strategi Belajar Siswa SMA Berdasarkan Aspek Self-Regulated Learning (Manajemen Sumber Daya) Diah Ayu Choirunnisa; Sulidar Fitri; Taofik Muhammad
Switch : Jurnal Sains dan Teknologi Informasi Vol. 4 No. 4 (2026): Juli : Switch : Jurnal Sains dan Teknologi Informasi
Publisher : Asosiasi Profesi Telekomunikasi Dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/switch.v4i4.1003

Abstract

Selecting the appropriate learning strategy is crucial for high school students; however, educators often struggle to identify strategies that align with each individual's Self-Regulated Learning (SRL) capabilities. This study aims to predict high school students' learning strategies based on the SRL aspect of resource management by applying the 10-fold cross-validation (C4.5) algorithm using the Knowledge Discovery in Databases (KDD) method. The study utilized 537 valid data points collected from students of SMA Negeri 1 Singaparna. A predictive model was constructed using 23 predictor attributes and evaluated through 10-fold cross-validation to assess its performance and reliability. The results indicate relatively low model performance, with an accuracy of 50.9% and an F1-score of 49.9%. This performance is attributed primarily to class imbalance and feature overlap among the learning strategy categories. The analysis identified the attribute "understanding improves when studying with peers" as the root node, with an Information Gain value of 0.042. These findings suggest that the resource management aspect of SRL is insufficient to serve as a sole predictor of students' learning strategies. Future research is recommended to incorporate other dimensions of SRL to improve predictive accuracy and provide a more comprehensive understanding of students' learning strategy preferences.