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: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:Sports-related minor injuries are common occurrences in school-based physical education activities, yet literacy regarding appropriate first aid management remains limited among teachers and students. This community service…
ice program aimed to improve knowledge, skills, and preparedness in managing minor sports injuries through a digital-based educational intervention entitled Smart Recovery. The program was implemented among junior high school (SMP) teachers and students in Banyumas Regency, Indonesia, using a participatory and technology-integrated approach. Activities consisted of program socialization, theoretical and practical training on minor injury management based on the RICE principle (Rest, Ice, Compression, Elevation), and the pilot implementation of the Smart Recovery digital application. Program effectiveness was evaluated using pre-test and post-test assessments, practical skill observations, and user feedback questionnaires. The results demonstrated a substantial improvement in participants’ knowledge, with average scores increasing from 62.4 to 88.6, and 95% of participants successfully performing the RICE procedures correctly after training. Furthermore, 92% of users reported that the digital application facilitated their understanding of injury management, while 87% perceived the platform as user-friendly and applicable for physical education learning. The integration of hands-on training and digital learning media proved effective in enhancing sports injury literacy, digital competence, and safety awareness in school settings. These findings indicate that the Smart Recovery program has strong potential as a sustainable and scalable model for promoting sports safety education within junior high schools.
Keywords : minor sports injury; RICE method; digital learning; Smart Recovery; physical education
Abstract:This study aims to determine the influence of public perception on the quality of public services at the Department of Population and Civil Registration (Disdukcapil) of Bogor Regency. The type of research used is descriptive…
ptive quantitative. The population in this study consists of people who carried out administrative services at the Disdukcapil office of Bogor Regency, with a total sample of 100 respondents. Data analysis was conducted using the Weighted Means Score (WMS) method. The results of the study show that: (1) The highest average score from the analysis of public service quality indicators was the indicator related to “technical service requirements at Disdukcapil being easy to understand by the public,” which obtained an average value of 3.50, categorized as good. Another high indicator was “the completion of administrative processes at Disdukcapil on time,” with an average score of 3.55, also categorized as good. Meanwhile, the lowest average score was 3.19, categorized as fairly good, on indicators such as “the public feeling that their security is guaranteed when managing administrative services at Disdukcapil” and “service officers being disciplined in providing services to the community.” (2) The final recapitulation of the analysis across the ten main indicators of public service quality shows that the highest average score was found in the Certainty indicator, with a score of 3.48, categorized as fairly good. On the other hand, the lowest average scores were in the Discipline and Comfort indicators, both with scores of 3.23, also categorized as fairly good. (3) Overall, the average score of all public service quality indicators in this study was 3.34, categorized as fairly good. This indicates that, in general, the public perceives the quality of public services at the Disdukcapil of Bogor Regency to be fairly good. The recommendation given is that Disdukcapil Bogor Regency should further improve the discipline of its officers regarding their presence at the workplace or service counters, as well as their punctuality in serving the community, and also create a more comfortable environment and waiting area for the public accessing services.
Abstract:PayLater services are one of the rapidly growing digital financial innovations widely utilised in fintech apps in Indonesia, including Kredivo and Akulaku. User reviews on the Google Play Store reflect a range of experiences,…
nces, from satisfaction with the ease of use of the service to complaints regarding bills, interest rates, late payment fees, credit limits, and app performance. This study aims to classify the sentiment of user reviews regarding PayLater services on the Kredivo and Akulaku apps using the Multinomial Naïve Bayes algorithm. Data was collected via web scraping from the Google Play Store and automatically labelled based on user ratings, with ratings of 1-2 classified as negative sentiment and ratings of 4-5 as positive sentiment, whilst a rating of 3 was excluded as it was considered ambiguous. Following a preprocessing stage comprising cleaning, case folding, tokenisation, stopword removal, and stemming, as well as feature extraction using TF-IDF, 3,652 reviews were obtained with a training-to-test data split ratio of 80:20. The results indicate that positive sentiment dominates the dataset at 56.49%, whilst negative sentiment accounts for 43.51%. Analysis by application revealed that Kredivo was dominated by positive sentiment (68.20%), whilst Akulaku was dominated by negative sentiment (51.70%). The Naïve Bayes multinomial model achieved an accuracy of 84.13%, with average precision, recall, and F1-score values of 0.84, demonstrating good and balanced classification performance across both sentiment classes.
Abstract:This study aims to analyze the evaluation of public policy and environmental disaster mitigation predictions regarding the cancellation of the strategic glass industry development in Rempang Island. The study employed a…
qualitative approach with a case study design and data collection through systematic literature review. Data analysis was conducted using the interactive model of Miles, Huberman & Saldana (2014). The results show that the Rempang Eco City National Strategic Project (NSP) failed comprehensively due to a procedurally flawed and non-participatory formulation process. Economic valuation research by Trend Asia et al. (2025) found that the average household income of Rempang residents reached IDR 32.77 million per household per month, far exceeding the government’s claim of IDR 3 million, while potential environmental losses reached IDR 109 million per household per month. Based on Dunn’s (2003) six policy evaluation criteria, this policy proved to be ineffective, inefficient, inadequate, inequitable, unresponsive, and inappropriate. President Prabowo Subianto’s decision to exclude Rempang Eco City from the NSP list through Presidential Regulation No. 12 of 2025 was the right step, yet still requires more decisive regulation to provide legal certainty for affected communities.
Abstract:Halal certification has become an essential mechanism for ensuring that products meet Islamic requirements while also maintaining standards of safety, quality, and consumer protection. Despite its growing importance, awareness…
reness and understanding of halal certification remain relatively limited among community members, particularly women who play a central role in household purchasing decisions. This community engagement initiative was designed to enhance the knowledge and awareness of members of the Family Welfare Empowerment Organization (PKK) in Sidodadi Village, Kedaton District, Bandar Lampung City, regarding the significance of halal certification in consumer products. The program engaged 30 participants and applied a participatory educational approach consisting of counseling sessions, interactive discussions, lectures, and question-and-answer activities. Knowledge acquisition was evaluated through pre-test and post-test assessments. The findings demonstrated a marked improvement in participants’ understanding, with average scores increasing from 51.3% prior to the intervention to 94.0% afterward. The program not only strengthened participants’ awareness of halal-certified products but also encouraged more informed and responsible consumption practices. These results highlight the effectiveness of community-based halal literacy initiatives in fostering greater public understanding and supporting the development of a halal-conscious society.
Abstract:The agriculture sector plays a strategic role in the national economy and is highly dependent on fertilizer availability on support crop productivity. This study aimed to analyze the effectivenss of subsidized fertilizer…
er distribution and its impact on rice productivity in the tidal lowland areas of Tanjung Lago District, Banyuasin Regency. The research employed both quantitative and qualitative descriptive approaches using a stratified random sampling method involving 60 farmers who received subsidized fertilizer and 30 farmers who did not reveive subsidizer fertilizer. The effectiveness of subsidizer fertilizer distribution was evaluated using a likert scale based on the Six Appropriateness Principles, while the impct on rice productivity was analyzed by comparing the productivity levels of the two farmer groups. The findings showed that the distribution of subsidized fertilizer was generally categorized as moderately effective, with an average effectiveness score of 71,33%. The price compliance indicator was classified as highly effective (91,66%), while location suitability was categorized as effective (81,00%). Meanwhile, quantity appropriateness, fertilizer type suitability, and timeliness of distribution were categorized as moderately effective. The findings showed that the distribution of subsidized fertilizer was generally categorized as moderately effective, with an average effectiveness score of 71.33%. The price compliance indicator was classified as highly effective (91.66%), while location suitability was categorized as effective (81.00%). Meanwhile, quantity appropriateness, fertilizer type suitability, and timeliness of distribution were categorized as moderately effective. In contrast, the fertilizer quality suitability indicator was still considered ineffective, with an effectiveness score of 55%. The use or subsidized fertilizer also contributed positively to rice productivity. Farmers receiving subsidized fertilizer achieved an average rice productivity of 3.77 ton ha⁻¹, whereas farmers who did non receive subsidized fertilizer produced an average productivity of 3.20 ton ha⁻¹. This resulted in a productivity defference of 0.57 ha⁻¹.. equivalent to approximately 17.81%.
Abstract:This study aims to improve the ability to write descriptive essays using the drill method among seventh-grade students in Class VII-2 at Pangeran Antasari Junior High School in Medan. The use of the drill method is expected…
ted to help students understand the material and write descriptive essays, thereby improving their skills. This study was conducted at Pangeran Antasari Junior High School in Medan. The research subjects were the 7th-grade Class 2, consisting of 30 students. The study was conducted in two cycles, with each cycle consisting of two sessions. Research data were obtained from (1) observations, (2) interviews, and (3) tests in the form of student assignments (written work) and photographic documentation taken during the activities. The results of the study indicate that the use of the drill method can improve students’ ability to write descriptive essays. This is evidenced by improvements in the learning process, particularly in the learning environment, where students are more focused during instruction. This is evident in the pre-cycle average student score of 66.16; in Cycle I, the average score increased to 73.5, and in Cycle II, it further increased to 82.5. Overall, in Cycle II, all aspects of descriptive writing showed a highly significant improvement. Based on these research results, it can be concluded that the use of the drill method was successful and capable of improving the descriptive writing skills of seventh-grade students in Class VII-2 at Pangeran Antasari Junior High School in Medan.
Abstract:Hypertension is a chronic condition characterized by increased blood pressure on the artery walls, which can lead to serious complications such as stroke, kidney failure, and heart disease. This study aimed to determine…
the effect of deep breathing relaxation techniques on lowering blood pressure in elderly people in Bate Linteng and Lambunot Villages, Aceh Besar. This quantitative study used a pre-experimental design using a one-group pretest-posttest. The study was conducted from August 26 to August 31, 2024, with a population and sample of 16 elderly respondents with a history of hypertension. Data collection was conducted through observation using an observation sheet and the provision of deep breathing relaxation techniques. The results showed that the average blood pressure before the intervention was 148/90 mmHg with a standard deviation of 9.674, while after the intervention, it decreased to 143/87 mmHg with a standard deviation of 9.050. The statistical test results using the Paired Sample t-Test showed a significance value of 0.000 (p < 0.05), indicating a significant effect between deep breathing relaxation techniques and blood pressure reduction. The results of this study are expected to provide information for hypertension sufferers and their families that deep breathing relaxation techniques are a form of non-pharmacological therapy that can be performed independently to control blood pressure.