Claim Missing Document
Check
Articles

Comparing Data Splitting Ratios in Student Sentiment Analysis Using the Naïve Bayes Algorithm Rofiatus Sabila, Annisa Zulfi; Asyhari, Ardian; Pitri, Rizka
Desimal: Jurnal Matematika Vol. 9 No. 2 (2026): Desimal
Publisher : Universitas Islam Negeri Raden Intan Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/djm.v9i2.32231

Abstract

Hybrid learning has become an integral component of higher education, making student feedback an important source of information for evaluating learning quality and improving instructional practices. Although sentiment analysis has been widely applied in educational research, limited attention has been given to how different training–testing data-splitting ratios influence classification performance. This study aimed to compare the performance of the Naïve Bayes algorithm using three data-splitting ratios (60:40, 70:30, and 80:20) for classifying students' sentiments toward hybrid learning at UIN Raden Intan Lampung during the second semester of the 2024–2025 academic year. A quantitative approach was employed to analyze 4,728 student opinions collected from 394 respondents. The analytical procedure consisted of text preprocessing, sentiment labeling using the InSet Lexicon, TF-IDF feature extraction, and Naïve Bayes classification, followed by performance evaluation using accuracy, precision, recall, and F1-score. The findings revealed that 70.3% of the opinions expressed positive sentiment, while 29.7% were negative, indicating that students generally perceived hybrid learning favorably despite challenges related to instructional delivery and internet connectivity. The comparison of data partitions showed similar overall performance, with accuracy values of 79% for the 60:40 split, 78% for the 70:30 split, and 79% for the 80:20 split. However, the 80:20 configuration achieved the strongest class-level performance, producing an F1-score of 87% for positive sentiment and 51% for negative sentiment. These findings demonstrate that Naïve Bayes provides stable performance across different data partitions, while the 80:20 ratio offers the most balanced configuration for sentiment classification within the scope of this dataset and analytical framework.
Respon Pondok Pesantren Diniyyah Putri Terhadap Modernisasi Pendidikan Islam Asyhari, Ardian; Sagala, Rumadani; Kendedes, Iin
TADRIS: Jurnal Pendidikan Islam Vol 12 No 2 (2017)
Publisher : State Islamic Institute of Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19105/tjpi.v12i2.1505

Abstract

Penelitian ini bertujuan untuk memahami modernisasi, penerapan kurikulum, dan aneka bentuk pengembangan Pendidikan Islam yang dilaksanakan di Pondok Pesantren Diniyyah Putri Lampung untuk meningkatkan mutu lembaga pendidikan. Jenis penelitiannya adalah penelitian lapangan (field research) bersifat kualitatif (qualitatif research). Pengumpulan data dilakukan dengan observasi, wawancara, dan dokumentasi. Hasil penelitian menunjukkan modernisasi yang dilakukan di Pondok Pesantren Diniyyah Putri Lampung berfokus pada Sarana dan prasarana, kurikulum, dan metodologi pembelajaran. Penerapan kurikulum pada tingkat MTs dan MA dilakukan dengan menerapkan kurikulum terpadu yang merupakan perpaduan antara kurikulum 2013, kurikulum intrakurikuler, ekstrakurikuler, dan kurikulum Diniyyah putri. Dampak modernisasi Pondok Pesantren Diniyyah Putri Lampung terklasifikasi dari dampak terhadap guru, siswi/santriwati, Lulusan/alumni, dan Dampak Terhadap kepercayaan masyarakat.Kata Kunci: Modernisasi, Pesantren, dan Pendidikan Islam.
Pengaruh Model Conceptual Understanding Procedures Berbantuan PhET Simulation terhadap Hasil Belajar IPA SMP Nur Hidayah; Yuberti; Ardian Asyhari
SAKALIMA: Pilar Pemberdayaan Masyarakat Pendidikan Vol. 3 No. 3 (2026): July-September | SAKALIMA: Pilar Pemberdayaan Masyarakat Pendidikan
Publisher : WISE Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70211/sakalima.v3i3.556

Abstract

This study examined the effect of the Conceptual Understanding Procedures (CUPs) learning model assisted by PhET Simulation on junior secondary students' science learning outcomes. The study was motivated by low cognitive achievement in Grade VIII science, particularly motion concepts, and by the need for instruction that combines structured conceptual negotiation with interactive visualization. A quasi-experimental nonequivalent control group design was employed with 60 Grade VIII students at MTs Muhammadiyah Sukarame Bandar Lampung. Class VIII A served as the experimental class and learned through CUPs assisted by PhET Simulation, whereas Class VIII B received direct instruction. Data were collected using pretest and posttest instruments, classroom-observation sheets, and documentation. The test instrument met the criteria of validity, reliability, difficulty level, and discrimination index. The experimental class obtained a higher posttest mean score (82.13) than the control class (70.27). The independent-samples t-test indicated a significant difference, t(58)=5.78, p<0.001, with a large effect size (Cohen's d=1.49). The N-gain score of the experimental class was 0.71, while the control class reached 0.49. These findings indicate that CUPs assisted by PhET Simulation strengthens conceptual understanding, cognitive engagement, and science learning outcomes by integrating individual reasoning, triplet discussion, whole-class negotiation, and interactive visualization. The study implies that science teachers should combine guided simulation worksheets with structured conceptual dialogue to support meaningful reconstruction of motion concepts.
Integrating Augmented Reality into Blended Learning for Improved Magnetism Conceptual Understanding Ardian Asyhari; Ajo Dian Yusandika; Sergii Sharov
Jurnal Penelitian Fisika dan Aplikasinya (JPFA) Vol. 14 No. 1 (2024)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jpfa.v14n1.p33-48

Abstract

In pursuing innovative educational strategies, this study investigates the integration of Augmented Reality (AR) with blended learning to enhance students' conceptual understanding of magnetism. Utilizing AR as a significant educational tool provides an immersive experience that aids in comprehending complex concepts. At the same time, blended learning combines traditional classroom methods with online resources for a more effective approach. This research employs an experimental design with a pretest-posttest control group involving 60 students from the Islamic University of Raden Intan Lampung enrolled in a physics course on magnetism. The experimental group experienced AR-enhanced blended learning, while the control group received traditional blended learning without AR. Quantitative data analysis included descriptive statistics and the N-Gain test to measure the intervention's effectiveness, with ANOVA used to examine differences in conceptual understanding between the groups. Qualitative data was gathered through semi-structured interviews and analyzed thematically to identify common themes and patterns. The results indicate a significant improvement in the experimental group's understanding of magnetism compared to the control group, highlighting AR's effectiveness in enhancing interactivity and engagement, facilitating the visualization of abstract concepts, and reinforcing the linkage between theory and practical application. These findings offer educators and curriculum developers valuable insights, laying a foundation for future interdisciplinary educational research.    
Co-Authors Adis Veliana Anjani Adis Veliana Anjani Agusta, Mutia Velli Ajo Dian Yusandika Akbar Handoko Al Qusri, Muhammad Fariq Amaliyah Dwi Cahyaningrum Amar Syafaat Amelya, Putri Andrea Bagas Bambang Budi Wiranto Bayan, Rocelia Pasco Bayu Putra Cahyaningrum, Amaliyah Dwi Dayangku Intan Diah Andika Sari Dicy Maulana Dina Hariyanti Dinda Nurjanah Dixit, Aparna Djoa, Dominikus Djago Dwi Handoko Dwi Handoko Erwinsyah, Heru Fauza Farida Feti Yunita Sari Fijira Pasyah Fredi Ganda Putra Ghifar Javad H Aziz Gita Putri Clara Happy Komikesari Happy Komikesari Hasan Hariri Helda Silvia Helda Silvia, Helda Herli Candra Saputra Herli Candra Saputra, Herli Candra Heru Juabdin Sada Iis Nanda Octana Indah Veronika Intan Islamia Irwandani Kendedes, Iin Kendedes, Iin Mapunda, Waziri Mohamed Masyuni, Siti Michalska-Domańska, Marta Misbah Misbah Mohamad Muhassin Muhammad Aridan Muhammad Benard Muhammad Fariq Al Qusri Muhammad Sifa’i Mukarramah Mustari, Mukarramah Murih Rahayu Muzannur Muzannur Muzannur, Muzannur Muzannur, Muzannur Nanang Supriadi Neli Neli Nopal Reza Efendi Nur Hidayah Nurul Apriyadi Nurul Hidayati Murtafiah Ocha Septianti Octana, Iis Nanda Orin Neta Julia Panse, Vishal R Pitri, Rizka Putri Maharani Putri Maharani Putri, Lia Pebriana Rahma Diani Rahma Diani, Rahma Rahman, Nor Farahwahidah Abdul Rijal Firdaos Rijal Firdaos Rizki Wahyu Yunian Putra Rofiatus Sabila, Annisa Zulfi Rofiqul Umam Rumadani Sagala Santi Widyawati Sarwanto Sarwanto Sarwanto Sarwanto Saxena, Arti Sergii Sharov Sifa’i, Muhammad Siti Amelia Agustin Siti Masyuni Sowiyah Sowiyah Sri Latifah Sunyono - - Susanti Susanti Susanti Susanti Undang Rosidin Wan Jamaluddin Z Widayanti Widayanti Widayanti Widayanti Widha Sunarno Widha Tri Sunarno Windo Dicky Irawan Yahya AD Yahya AD, Yahya Yani Suryani Yuberti