Abstract:Penggunaan dompet digital yang terus meningkat menghasilkan banyak ulasan pengguna yang dapat dimanfaatkan untuk mengevaluasi kualitas layanan. Penelitian ini bertujuan meningkatkan akurasi klasifikasi sentimen pengguna…
dompet digital menggunakan metode Stacking Ensemble Machine Learning yang mengombinasikan Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), dan AdaBoost dengan Logistic Regression sebagai meta-learner. Data ulasan diproses melalui tahapan text preprocessing meliputi case folding, cleaning, tokenizing, stopword removal, stemming, dan pembobotan fitur menggunakan TF-IDF. Penyeimbangan data dilakukan dengan SMOTE, sedangkan evaluasi model menggunakan 5-Fold Cross-Validation. Hasil penelitian menunjukkan bahwa model Stacking Ensemble memperoleh akurasi rata-rata 80,55%, lebih tinggi dibandingkan algoritma dasar. Evaluasi menggunakan Confusion Matrix, Classification Report, dan ROC Curve juga menunjukkan peningkatan nilai precision, recall, F1-score, dan kemampuan diskriminasi model. Hasil ini menunjukkan bahwa pendekatan Stacking Ensemble Machine Learning efektif untuk meningkatkan akurasi klasifikasi sentimen pengguna dompet digital serta mendukung evaluasi kualitas layanan berbasis opini pengguna.
The rapid growth of digital wallet usage has generated a large volume of user reviews that can be utilized to evaluate service quality. This study aims to improve the accuracy of digital wallet user sentiment classification using a Stacking Ensemble Machine Learning approach that combines Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), and AdaBoost with Logistic Regression as the meta-learner. User reviews were processed through text preprocessing stages, including case folding, text cleaning, tokenization, stopword removal, stemming, and TF-IDF feature weighting. Synthetic Minority Over-sampling Technique (SMOTE) was employed to address class imbalance, while model performance was evaluated using 5-Fold Cross-Validation. The experimental results show that the proposed Stacking Ensemble model achieved an average accuracy of 80.55%, outperforming the individual base learners. Furthermore, evaluations based on the Confusion Matrix, Classification Report, and Receiver Operating Characteristic (ROC) Curve demonstrated improvements in precision, recall, F1-score, and the model's discriminative capability. These findings indicate that the proposed Stacking Ensemble Machine Learning approach is effective in improving the accuracy of digital wallet user sentiment classification and can serve as a reliable tool for supporting service quality evaluation based on user opinions.
Abstract:Emas merupakan salah satu jenis komoditi yang paling banyak diminati untuk tujuan investasi, karena dipandang sebagai instrumen yang lebih aman dibandingkan saham serta memiliki nilai jual yang selalu bergerak mengikuti…
kondisi pasar. PT Victoeria Vici, sebagai pelaku usaha perhiasan emas custom, menghadapi kendala dalam menentukan estimasi harga jual kepada pelanggan, sebab proses pengerjaan pesanan custom membutuhkan waktu hingga 14 hari, sementara harga emas bergerak fluktuatif dan tidak terstruktur setiap harinya sehingga estimasi harga menjadi tidak akurat dan tidak efektif. Berdasarkan permasalahan tersebut, penelitian ini menerapkan konsep Data Mining dengan algoritma Trend Moment untuk mengestimasi harga emas pada rentang waktu tertentu. Data yang digunakan merupakan data historis harga emas per gram pada PT Victoeria Vici periode Agustus–Oktober 2021 sebanyak 92 data. Tahapan penelitian meliputi pengumpulan data, penentuan variabel X dan Y, eliminasi untuk memperoleh nilai konstanta a dan slope b, serta penerapan persamaan Y = a + bX untuk memperoleh nilai estimasi. Hasil perhitungan menunjukkan nilai a = 720.871,725 dan b = 3,108 sehingga model estimasi mampu menghasilkan proyeksi harga emas yang mendekati pola data historis. Model ini kemudian diimplementasikan ke dalam aplikasi berbasis desktop menggunakan Microsoft Visual Basic 2010 dan basis data Microsoft Access, dilengkapi Crystal Report untuk pencetakan laporan hasil estimasi. Hasil penelitian menunjukkan bahwa algoritma Trend Moment dapat membantu PT Victoeria Vici dalam memperoleh estimasi harga emas secara lebih cepat, konsisten, dan terdokumentasi.
Gold is one of the most sought-after commodities for investment purposes, as it is regarded as a safer instrument compared to stocks and has a selling value that constantly fluctuates with market conditions. PT Victoeria Vici, a custom gold jewelry business, faces difficulty in determining the estimated selling price offered to customers because the production process for custom orders takes up to 14 days, while gold prices move in an unstructured and fluctuating manner every day, making manual price estimation inaccurate and ineffective. Based on this problem, this study applies the concept of Data Mining using the Trend Moment algorithm to estimate gold prices over a certain period of time. The data used is historical daily gold price data per gram from PT Victoeria Vici for the period of August–October 2021, consisting of 92 records. The research stages include data collection, determination of the X and Y variables, elimination to obtain the constant value a and the slope b, and the application of the equation Y = a + bX to obtain the estimated value. The calculation results show a value of a = 720,871.725 and b = 3.108, so that the estimation model is able to produce gold price projections that closely follow the pattern of historical data. This model was then implemented into a desktop-based application using Microsoft Visual Basic 2010 and a Microsoft Access database, equipped with Crystal Report for printing estimation result reports. The results show that the Trend Moment algorithm can help PT Victoeria Vici obtain gold price estimations more quickly, consistently, and in a well-documented manner.
Abstract:Promosi penerimaan mahasiswa baru (PMB) merupakan salah satu faktor penting dalam meningkatkan jumlah dan kualitas calon mahasiswa. Namun, strategi promosi yang belum memanfaatkan data historis secara optimal dapat menyebabkan…
babkan kegiatan promosi kurang tepat sasaran. Penelitian ini bertujuan untuk menganalisis data historis PMB sebagai dasar dalam menyusun strategi promosi yang lebih efektif pada Jurusan Teknologi Informasi dan Komputer Politeknik Negeri Lhokseumawe. Penelitian menggunakan pendekatan kuantitatif deskriptif dengan memanfaatkan data sekunder PMB periode 2023–2025. Analisis dilakukan melalui tahapan data cleaning, transformasi data, statistik deskriptif, segmentasi calon mahasiswa, dan visualisasi data menggunakan dashboard analitik. Variabel yang dianalisis meliputi program studi, asal sekolah, jurusan asal sekolah, kecamatan, kabupaten/kota, provinsi, jalur masuk, dan sumber informasi pendaftar. Hasil penelitian menunjukkan bahwa sebagian besar pendaftar berasal dari Provinsi Aceh, khususnya Kabupaten Aceh Utara dan Kota Lhokseumawe, dengan dominasi lulusan jurusan IPA serta peminat terbesar pada Program Studi Teknik Informatika. Instagram dan website menjadi sumber informasi utama bagi calon mahasiswa. Pemanfaatan data historis melalui visualisasi data mampu memberikan informasi yang lebih komprehensif mengenai karakteristik calon mahasiswa sehingga dapat mendukung pengambilan keputusan dalam penyusunan strategi promosi PMB yang lebih terarah, efektif, dan berbasis data.
New student admissions (PMB) promotion is an important factor in increasing the number and quality of prospective students. However, promotional strategies that do not optimally utilize historical data can result in less targeted promotional activities. This study aims to analyze historical PMB data as a basis for developing a more effective promotional strategy in the Information and Computer Technology Department of the Lhokseumawe State Polytechnic. The study uses a descriptive quantitative approach utilizing secondary PMB data for the 2023–2025 period. The analysis was carried out through the stages of data cleaning, data transformation, descriptive statistics, prospective student segmentation, and data visualization using an analytical dashboard. The variables analyzed included study program, school of origin, major of origin of school, sub-district, regency/city, province, admission route, and applicant information sources. The results show that most applicants come from Aceh Province, especially North Aceh Regency and Lhokseumawe City, with a predominance of science graduates and the greatest interest in the Informatics Engineering Study Program. Instagram and websites are the main sources of information for prospective students. The use of historical data through data visualization can provide more comprehensive information regarding the characteristics of prospective students so that it can support decision-making in developing more targeted, effective, and data-based PMB promotion strategies.
Abstract:This study aims to determine the effect of using Google Earth media through the Contextual Teaching and Learning (CTL) model on the learning outcomes of social studies on natural phenomena material for fifth-grade students…
ts of SDN Telang 2 in the 2026/2027 academic year. The study used a quantitative approach with the Pre-Experimental Design method and One Group Pretest-Posttest Design. The research subjects were 17 students. Data collection techniques were carried out through tests, observations, and documentation. The research instrument was a multiple-choice test given before and after treatment. Data were analyzed using descriptive statistics and paired sample t-test. The results showed that the average pretest score of 68.82 increased to 79.41 in the posttest, with an increase of 10.59 points. The results of the paired sample t-test showed a significance value (2-tailed) of 0.000 <0.05, so H₀ was rejected and H₁ was accepted. These findings indicate that the use of Google Earth media through the CTL model has a significant effect on the learning outcomes of social studies on natural phenomena material. The integration of Google Earth and CTL provides a more contextual, interactive, and meaningful learning experience, helping students understand the concept of natural features more concretely. Therefore, Google Earth, through the CTL model, can be used as an alternative media and effective learning model to improve social studies learning outcomes in elementary schools.
Penelitian ini bertujuan untuk mengetahui pengaruh penggunaan media Google Earth melalui model Contextual Teaching and Learning (CTL) terhadap hasil belajar IPS materi kenampakan alam pada siswa kelas V SDN Telang 2 Tahun Pelajaran 2026/2027. Penelitian menggunakan pendekatan kuantitatif dengan metode Pre-Experimental Design dan desain One Group Pretest-Posttest Design. Subjek penelitian berjumlah 17 siswa. Teknik pengumpulan data dilakukan melalui tes, observasi, dan dokumentasi. Instrumen penelitian berupa tes pilihan ganda yang diberikan sebelum dan sesudah perlakuan. Data dianalisis menggunakan statistik deskriptif dan uji paired sample t-test. Hasil penelitian menunjukkan bahwa nilai rata-rata pretest sebesar 68,82 meningkat menjadi 79,41 pada posttest, dengan peningkatan sebesar 10,59 poin. Hasil uji paired sample t-test menunjukkan nilai signifikansi (2-tailed) sebesar 0,000 < 0,05, sehingga H₀ ditolak dan H₁ diterima. Temuan ini menunjukkan bahwa penggunaan media Google Earth melalui model CTL berpengaruh signifikan terhadap hasil belajar IPS materi kenampakan alam. Integrasi Google Earth dan CTL mampu memberikan pengalaman belajar yang lebih kontekstual, interaktif, dan bermakna sehingga membantu siswa memahami konsep kenampakan alam secara lebih konkret. Oleh karena itu, Google Earth melalui model CTL dapat dijadikan alternatif media dan model pembelajaran yang efektif untuk meningkatkan hasil belajar IPS di sekolah dasar.
Abstract:This study aims to analyze the effectiveness of using a Smartboard in increasing students' enthusiasm for learning in the Pancasila Education subject in grade V of SDN 07 Mudiak Lawe, Sungai Pagu District, South Solok Regency.…
gency. From initial observations, it was seen that students' enthusiasm for learning tended to be low, as seen from their inactive attitudes, little interaction, and easily distracted when teachers used less diverse learning methods. To address this, a Smartboard was proposed as an innovative solution. This tool is an interactive whiteboard that uses multimedia and audiovisual technology, so it can combine teaching materials with images, videos, and animations to make learning more interesting and diverse. The method used in this study was the correlation method, namely a quantitative method that studies the relationship between the use of Smartboard interactive features and the level of student enthusiasm for learning. The results showed that the use of Smartboard in learning was proven to be able to increase student enthusiasm for learning. After implementing the Smartboard, students appeared more active and enthusiastic during the learning process, so that their enthusiasm for learning increased and reduced boredom. The implementation of Smartboard involves game-based learning methods such as Duck Race Games and Wordwall, which successfully trigger students' curiosity, focus, and enthusiasm, and encourage them to actively participate in answering questions and interacting in class.
Abstract:This study investigates the difficulties faced by fourth-grade students at SDN 060878 Krakatau Medan Timur in understanding English classroom instructions. The research identifies four main obstacles: limited vocabulary…
mastery, low confidence and motivation, less varied teaching strategies, and minimal English exposure outside school. The study also highlights effective teacher efforts such as repeating instructions, providing bilingual explanations, using demonstrations, and implementing interactive activities. These findings are expected to guide teachers in creating more adaptive and supportive instructional practices in elementary English learning.
Abstract:This study aims to analyze the low English speaking and listening skills of 4th grade elementary school students at SD PAB 12 Sampali. The research approach used is descriptive qualitative, with interview methods to obtain…
in in-depth data from teachers and students regarding the obstacles they face during the English learning process. The results of the study indicate that the main factors influencing students' limited speaking and listening skills include lack of practice, minimal use of interesting learning media, and internal factors such as lack of self-confidence and less than optimal pronunciation. These findings provide an important overview of the need to develop more effective and innovative learning strategies to improve students' communication skills in English at the elementary level. It is hoped that the results of this study can be a reference for educators and educational institutions in improving the quality of English teaching in elementary schools.
Abstract:This study aims to evaluate the effectiveness of group learning methods in improving the English skills of sixth-grade students at SD Negeri 060878. Using a qualitative approach involving direct interviews, questionnaires,…
s, and documentation, this study identified three main problems that hinder the success of group learning: gender differences affecting group formation, difficulty ensuring the active participation of each member, and relatively long time for group management. The results of the study indicate that these problems cause group learning to be less effective and have an impact on the decline in students' English skills. Therefore, strategies such as forming inclusive groups, clear division of tasks, the use of participatory observation instruments, the utilization of technology, and the implementation of the Problem-Based Learning approach are recommended to improve the effectiveness of group learning and students' English skills. This study provides an important contribution to developing English teaching methods at the elementary school level by considering social aspects and more effective classroom management.
Abstract:Social and digital transformations have impacted early childhood parenting patterns, necessitating the strengthening of the family's role as the foundation for Islamic-based character education. This community service activity…
tivity aims to improve literacy and practice of Islamic parenting through the Quranic Parent School program at the Merpati Early Childhood Education Post in Kutawaluya District. The program is designed to build synergy between schools and families in supporting the social-emotional and spiritual development of early childhood. The method used is a community-based participatory approach with stages of needs identification, joint action planning, parenting class implementation, and periodic reflection and evaluation. Activities are implemented through workshops, reflective discussions, simulations of Islamic parenting practices, and the establishment of a parent forum as a forum for program sustainability. The results of the activity indicate an increase in parents' understanding of the concepts of fitrah (natural nature) and adab (good manners), changes in communication patterns to be more empathetic, and consistent habits of worship and restrictions on gadgets at home. Further impacts are seen in increased discipline and emotional regulation of children at school and the formation of a Quranic family learning community. The implications of this activity confirm that strengthening Islamic parenting through the Quranic Parent School model is effective in encouraging family-based social transformation and has the potential to be replicated in other PIAUD institutions with similar characteristics.
Abstract:The development of digital technology presents innovative opportunities in early childhood learning, particularly in stimulating language skills through interactive and meaningful approaches. Fairy tales as an educational…
l medium have narrative power in enriching vocabulary and building children's expressive abilities, especially when combined with Islamic values and multimedia support. This community service activity aims to improve the competence of early childhood education teachers in implementing interactive Islamic storytelling based on multimedia to optimize children's language development in Kutawaluya District. The method used was a participatory approach through the stages of needs assessment, workshops, media creation practice, classroom implementation assistance, and evaluative reflection with the teacher community. The results of the activity showed an increase in teacher capacity in designing and using digital media pedagogically, changes in learning interaction patterns to be more dialogic, and increased verbal participation of children in storytelling activities. In addition, a community of teacher practice was formed that collaboratively developed Islamic storytelling media as a sustainable innovation. The implications of this activity confirm that the integration of technology, Islamic values, and a participatory approach effectively encourages the transformation of early childhood learning practices. This model has the potential to be replicated in similar contexts to strengthen the quality of adaptive and character-building early childhood education.