Abstract:Public Services at the Office of Investment and One-Stop Integrated Services of Southwest Sumba Regency are basic services in government administration. Public Services are an important indicator in assessing government…
performance, both at the central and regional levels. Quality public services have implications for public satisfaction, because the public directly assesses the performance of the services provided. The low quality of Services in Southwest Sumba has so far encouraged the government to immediately improve the quality of services, especially those related to the required service licensing services, which are adjusted to the capabilities and needs of the region in managing them. Then, another problem found in the community is that the public does not understand the information related to licensing services that can be done online due to the lack of socialization from officers of the Office of Investment and One-Stop Integrated Services of Southwest Sumba Regency regarding licensing that can be accessed online. The results of the Naïve Bayes method classification with a total of 71 positive sentiments and 31 negative sentiments. The accuracy value is 78.36%, margin of error is 9.10%, positive prediction precision is 85.92%, negative prediction precision is 61.292%, positive data recall is 83.56%, and negative data recall is 65.52%.
Abstract:The increasing volume of patient visits in primary healthcare facilities (such as community health centers and clinics) demands efficient resource management and scheduling systems. The inability to predict patient arrival…
al patterns often leads to long queues and suboptimal allocation of medical personnel. To overcome these issues, this study proposes the development of an intelligent framework based on Stacking Ensemble Learning to accurately classify and predict patient revisit frequency patterns. The proposed architecture integrates three heterogeneous base classification models (base learners), namely Logistic Regression (LR), Support Vector Machine (SVM) with non-linear Radial Basis Function (RBF) kernel projection, and Random Forest (RF). The probability predictions from these three base models are then combined into a secondary Logistic Regression based meta-learner to optimize the final decision and reduce the predictive bias of single models. Experiments were conducted using a dataset sourced from actual primary healthcare medical records, totaling 499 data entries. Given the highly imbalanced distribution of demographic data, the preprocessing stages were comprehensively designed, encompassing numerical scale feature standardization and the application of the SMOTE (Synthetic Minority Oversampling Technique) class balancing algorithm. Model testing was performed using a 5-fold stratified cross-validation scheme to ensure the robustness of the model's generalization. Comprehensive evaluation results proved that the Stacking Ensemble architecture achieved peak performance with an Accuracy of 88.4%, Precision of 85%, Recall of 90%, and an F1-Score of 0.88. Furthermore, curve analysis revealed an Area Under the Receiver Operating Characteristic (AUC-ROC) score of 0.961 and a Precision-Recall AUC of 0.95, consistently outperforming the capabilities of each individual baseline model. These findings confirm that combining hybrid machine learning models can produce highly stable and reliable predictions while minimizing false negative errors. This architecture holds massive potential for practical implementation as the foundation of a decision support system in managing operational services within primary healthcare facilities.
Abstract:Student mental health disorders have become an increasingly important issue due to their significant impact on academic performance and psychological well-being. Machine learning-based approaches offer a promising alternative…
ative for supporting early detection; however, only a limited number of studies have conducted comprehensive evaluations of various ensemble learning algorithms by simultaneously considering predictive performance, computational efficiency, and statistical significance. This study aims to compare ten classification algorithms, namely Random Forest, Extra Trees, Gradient Boosting, Hist Gradient Boosting, AdaBoost, XGBoost, LightGBM, CatBoost, Logistic Regression, and Stacking Ensemble, using 5-fold Stratified Cross-Validation. Model performance was evaluated using Accuracy, Precision, Recall, F1-Score, Receiver Operating Characteristic–Area Under the Curve (ROC-AUC), training time, inference time, confusion matrix, feature importance, as well as One-Way Analysis of Variance (ANOVA) and post-hoc Tukey’s Honestly Significant Difference (Tukey HSD) tests. The experimental results show that CatBoost achieved the highest classification performance, with an Accuracy of 84.86%, an F1-Score of 87.19%, a Recall of 88.03%, and an ROC-AUC of 0.9220. XGBoost delivered comparable predictive performance with a substantially shorter training time (3.92 seconds), while LightGBM was the most computationally efficient algorithm, requiring an average training time of only 0.85 seconds. In contrast, the Stacking Ensemble required the longest training time (215.41 seconds) without providing a statistically meaningful performance improvement over the boosting-based models. The ANOVA results revealed significant differences in ROC-AUC among the evaluated models (p < 0.001), whereas the Tukey HSD test indicated that most boosting algorithms did not differ significantly from one another. These findings provide practical guidance for selecting classification algorithms by balancing predictive performance and computational efficiency to support early mental health screening systems for university students.
Abstract:Transformasi sistem kesehatan membutuhkan pendekatan yang tidak hanya berorientasi pada pelayanan kuratif, tetapi juga pada pencegahan, ketahanan gizi, dan pemanfaatan data secara presisi. Kajian ini bertujuan menganalisis…
is integrasi ketahanan gizi berbasis Precision Public Health dalam memperkuat resiliensi sistem kesehatan. Dengan pendekatan mixed methods sequential explanatory, kajian mengombinasikan analisis kuantitatif dan kualitatif untuk menilai hubungan antara integrasi data gizi, stratifikasi risiko, tata kelola kesehatan, dan kapasitas adaptif sistem. Hasil kajian menunjukkan bahwa ketahanan gizi perlu diposisikan sebagai determinan strategis dalam transformasi sistem kesehatan, bukan sekadar luaran kebijakan pangan. Integrasi data gizi dengan data sosial, lingkungan, epidemiologi, dan spasial memungkinkan intervensi yang lebih tepat sasaran, pengembangan sistem peringatan dini, serta peningkatan kapasitas sistem menghadapi krisis global. Temuan ini memperluas kerangka Precision Public Health dan Health System Resilience dengan menempatkan ketahanan gizi sebagai penghubung antara sistem pangan, data, pencegahan penyakit, dan tata kelola kesehatan. Implikasinya adalah perlunya interoperabilitas data lintas sektor dan kebijakan kesehatan yang lebih prediktif, adaptif, berkeadilan, dan berkelanjutan.
The transformation of the health system requires an approach that focuses not only on curative care, but also on prevention, nutritional resilience, and the precise use of data. This study aims to analyse the integration of nutritional resilience based on Precision Public Health in strengthening the resilience of the health system. Using a sequential explanatory mixed-methods approach, the study combines quantitative and qualitative analyses to assess the relationship between the integration of nutritional data, risk stratification, health governance, and the system’s adaptive capacity. The study’s findings indicate that nutritional resilience must be positioned as a strategic determinant in health system transformation, rather than merely an outcome of food policy. The integration of nutritional data with social, environmental, epidemiological, and spatial data enables more targeted interventions, the development of early warning systems, and an enhancement of the system’s capacity to cope with global crises. These findings expand the frameworks of Precision Public Health and Health System Resilience by positioning nutritional resilience as a link between food systems, data, disease prevention, and health governance. The implications are the need for cross-sectoral data interoperability and health policies that are more predictive, adaptive, equitable, and sustainable.
Abstract:Agricultural development is pivotal for economic growth, food security, and poverty alleviation, particularly in developing countries. This paper explores the factors driving agricultural development, innovative practices,…
s, and strategic frameworks essential for sustainable growth. The research highlights the interconnections between technology adoption, policy frameworks, and market access, emphasizing the need for an inclusive approach that addresses the needs of smallholder farmers who constitute a significant portion of the agricultural workforce. Through a comprehensive review of current literature, case studies, and empirical data analysis, the study identifies key challenges facing the agricultural sector, such as climate change, land degradation, and access to resources. Innovations in agricultural practices, including precision farming, biotechnology, and sustainable land management, are discussed as vital components for enhancing productivity and resilience. Additionally, the role of policy interventions in promoting agricultural research and development, facilitating access to markets, and ensuring food security is critically assessed. The findings indicate that fostering collaboration among stakeholders—governments, private sectors, and local communities—is crucial for achieving sustainable agricultural development. Ultimately, this research aims to provide actionable insights and policy recommendations that promote agricultural innovation and improve the livelihoods of farmers, thereby contributing to enhanced food security and economic prosperity.
Abstract:The purpose of this study is to Determine the Quality of Service for the First Time Certificate Issuance at the Donggala Regency Land Office. Qualitative method as the basis of the research, the object of the research is…
the quality of the service of the First Time Certificate Issuance at the Donggala Regency Land Office, while the research subject involves the apparatus that serves the service process as the target of analysis. Informants are selected based on the Purposive Sampling technique. Data collection is carried out through literature studies, field studies (observation and interviews), data analysis is carried out inductively through the stages of reduction, presentation, and conclusion. Based on the results of the research, the quality of the first certificate issuance service at the Donggala Regency land office is as follows: The Dimension of Precision Has Been Running Quite Effectively However, the Dimension of Speed Has Not Been Effective, the Dimension of Convenience Has Not Been Fully Effective, and the Dimension of Justice Has Not Been Fully Effective. In conclusion, the quality of the service for the issuance of certificates for the first time at the Donggala Regency Land Office has not been effective.
Abstract:General elections have an important role in democratic systems in all countries. In this context, sentiment analysis plays an important role in revealing the public's views on political parties. This study analyzes sentiment…
ment towards the Partai Demokrasi Indonesia Perjuangan (PDIP) in the 2024 General Election using the Naive Bayes algorithm. This method classifies social media content related to PDIP into positive (support) or negative (criticism) categories. The analysis results show 100% precision in identifying positive sentiment, but recall is only 97.11%, indicating that some positive sentiment was missed. For negative sentiment, the precision was 94.33% with a recall of 100%, indicating the ability to recognize negative sentiment but little negative prediction error. This study provides an in-depth understanding of the PDIP's perception in the 2024 General Election, supports better political decision making and provides insight to the PDIP in understanding the public's views.
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:Mechanical Engineering Education (PTM) demands logical precision and mastery of high technology, creating an intensive academic burden for students. This condition often leads to an invisible dichotomy between "campus obligations"…
ligations" and "religious obligations," where Muslim PTM students struggle to maintain consistency in Islamic discipline, such as five-times prayer and moral development. This research aims to explore the challenges faced by Mechanical Engineering Education (PTM) students in maintaining Islamic discipline amid high academic demands. The method used is a Literature Review with a critical approach, which collects and analyzes various literature to identify gaps in knowledge. The main findings reveal that the primary challenges include the decline of ethical values such as honesty due to the impact of social changes and technological advancements, the risk of weakened character caused by the influence of global secular culture, and the heavy curriculum burden that leads to mental and physical exhaustion as well as conflicts between academic schedules and religious obligations. Furthermore, students' excessive focus on achieving high GPA and technical skills often neglects moral development, compounded by the lack of integration of the ta’dib concept and insufficient support from social environments that can enforce discipline. Therefore, a holistic and integrated solution is necessary to make Islamic ethics the foundation of academic and professional behavior,balancing technical expertise and spiritual aspects so that PTM students can become competent individuals with strong Islamic character.
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.