UMA - Open Access Journals (Universitas Medan Area)
Not a member yet
5228 research outputs found
Sort by
Identifikasi Sentimen pada Data Teks Media Sosial Melalui Pendekatan Pembelajaran Terawasi
Full text linkAnalisis sentimen pada data teks media sosial menjadi penting untuk memahami opini publik, sehingga penelitian ini bertujuan untuk mengidentifikasi sentimen pada data teks media sosial melalui pendekatan pembelajaran terawasi. Dataset yang digunakan terdiri dari tweet dan ulasan produk yang telah dilabeli sentimen positif maupun negatif. Proses penelitian dilakukan melalui beberapa tahapan, yaitu prapemrosesan data (Removal of Stopwords, Lemmatization and Word Stemming, Spell Correction), Ekstraksi Fitur (N-Grm, Word count dan Tf-Idf Vectorizer) serta penerapan algoritma Multinomial Naive Bayes, dan Support Vector Machine (SVM). Hasil penelitian menunjukkan bahwa penghapusan stopwords menurunkan kinerja model, sehingga tetap menggunakan stopwords. Stemming dan lemmatization juga tidak memberikan pengaruh terhadap kinerja model, sedangkan spell correction dapat meningkatkan akurasi sekitar 2% tetapi dengan trade-off waktu komputasi yang tinggi. Pada tahap ekstraksi fitur, TF-IDF menghasilkan akurasi yang lebih tinggi dibandingkan Word Count. Algoritma Multinomial Naive Bayes menghasilkan akurasi sebesar 79,73% dengan AUC-ROC sebesar 0,85. Sedangkan SVM dengan kernel linear mendapatkan hasil terbaik dengan akurasi 82% dan AUC-ROC 0,88, lebih tinggi daripada RBF kernel yang hanya mencapai akurasi 77,79% dan AUC-ROC 0,82. Hasil penelitian ini dapat disimpulkan bahwa SVM dengan kernel linear lebih sesuai untuk klasifikasi teks berdimensi tinggi
Integrating Blockchain-Based Smart Contracts for Digital Certification: A Micro-Credentials Model for Vocational Higher Education
Full text linkThe rapid advancement of the digital industry requires vocational education in Indonesia to undergo transformation, particularly in providing competency validation systems that are efficient, adaptive, and trustworthy. In reality, however, competency certification processes in many vocational institutions are still conducted manually and tend to be bureaucratic, limiting their ability to respond to the dynamic needs of industry. This condition may reduce graduates’ competitiveness and widen the skills gap between vocational education and the labor market. Micro-credentials have emerged as an innovative approach to recognizing competencies in a modular, flexible, and industry-oriented manner. Nevertheless, their implementation still faces significant challenges, especially in terms of validation speed, reliability, and transparency. To address these challenges, this study develops a micro-credential–based competency validation model integrated with blockchain technology through the use of smart contracts at Politeknik LP3I Medan. This research adopts a Research and Development (R&D) approach based on the Borg and Gall model, including needs analysis, learning module design, system development, limited trials, expert validation, and effectiveness evaluation. Alpha testing involving 15 students demonstrates a system success rate of 95%, with an average verification time of 14.4 seconds. Usability evaluation indicates that the system is user-friendly and well accepted
DIVERSITY AND MORPHOLOGY OF ORNAMENTAL PLANTS IN KARO REGENCY: BOTANICAL INVENTORY AND SUSTAINABLE USE POTENTIAL
Full text linkThis study aims to document the diversity and morphological traits of ornamental plants in Karo Regency and assess their potential for sustainable use. Employing a qualitative descriptive approach, field surveys at Brastagi were conducted at 8 days, morphological observations, and semi-structured interviews with local communities and experts were held with 10 keys conducted. Sixteen ornamental species from 12 families were identified, including terrestrial and epiphytic orchids, ferns, and flowering plants such as Begonia laruei and Ixora javanica. These species are found at elevations of 920–1,000 meters within montane tropical rainforest habitats characterized by high humidity and limited light. Morphological adaptations indicate resilience to these specific conditions. Production data indicate the important economic role of ornamental plant cultivation in Karo Regency. Chrysanthemum, rose, and tuberose are the most widely cultivated species. This reflects their socioeconomic relevance. The integration of botanical and ethnobotanical data provides essential baseline information supporting biodiversity conservation and sustainable horticulture development. This research contributes valuable insights supporting conservation planning and community-based sustainable development in North Sumatra
MOLECULAR PHYLOGENY OF RODENTIA DERIVED FROM NRAS GENE SEQUENCES
Full text linkRodentia is the most diverse mammalian order, yet phylogenetic relationships among several rodent lineages remain incompletely resolved, particularly when inferred predominantly from mitochondrial markers. This study aims to assess the potential of the nuclear NRAS (Neuroblastoma RAS viral oncogene homolog) gene for reconstructing rodent phylogeny. A total of 18 NRAS nucleotide sequences representing major rodent families were retrieved from the NCBI GenBank database, with Equus caballus and Oryctolagus cuniculus used as outgroups. Sequence alignment and model selection were performed using MEGA 12 under Maximum Likelihood criteria. Phylogenetic reconstruction was conducted using the Maximum Likelihood method with the T92+G+I substitution model and 1,000 bootstrap replicates. Pairwise genetic distances were estimated using the p-distance method and visualized through a heatmap to examine divergence patterns. The results indicated that NRAS evolution is best explained by models incorporating invariant sites and rate heterogeneity, reflecting strong functional constraints combined with lineage-specific variation. The inferred phylogeny is largely congruent with established rodent systematics, and genetic distance patterns independently support the recovered topology. These findings suggest that NRAS represents a reliable nuclear marker that offers complementary phylogenetic information alongside mitochondrial data in Rodentia phylogenetic studies
Strategi Kelembagaan Tim Pemenangan Rahmat Mirzani Djausal dan Jihan Nurlela dalam Pemilihan Gubernur Lampung 2024
Full text linkThis article aims to analyze the institutional strategy of the winning team of Rahmat Mirzani Djausal and Jihan Nurlela in the 2024 Lampung Gubernatorial Election. The problem is focused on how networks of political parties, customary community organizations, and religious organizations were established and synergized to secure electoral victory. To address this issue, the study applies the network institutionalism theory, which emphasizes the importance of relationships between formal and informal actors in local political processes. The data were collected through in-depth interviews with representatives of supporting political parties, customary leaders, religious figures, election organizers, and political observers, complemented by observation and document analysis. The data were qualitatively analyzed using data reduction, data presentation, and conclusion drawing techniques. The findings indicate that the victory of Rahmat Mirzani Djausal and Jihan Nurlela was strongly influenced by the successful integration of political party machinery, social legitimacy from customary institutions, and moral as well as electoral mobilization by religious organizations. This study concludes that an integrated network-based institutional strategy is a decisive factor in winning the 2024 Lampung gubernatorial election and plays a significant role in strengthening the effectiveness of local political mobilization
Design and Engineering of an AI-Enabled Mobile Microlearning Application Integrating Short-Form Video and Learning Analytics for Vocational Soft Skills Development
Full text linkThe rapid growth of mobile technologies has reshaped how learning systems are designed, deployed, and evaluated, particularly in vocational education contexts. From a Mobile Software Engineering perspective, learning platforms must address constraints such as short interaction cycles, heterogeneous devices, scalability, and real-time analytics. This study focuses on the design and engineering of an AI-enabled mobile microlearning application that integrates short-form video, learning analytics, and LMS services to support vocational students’ soft-skills development. The proposed system is engineered as a mobile-first application with modular micro-content (60–180 seconds), rule-based personalization, and event-driven analytics to capture user interaction patterns. A Research and Development approach using the ADDIE framework is adopted, with emphasis on the software design, architecture, and prototyping stages. Validation involves expert review of system usability, content–software alignment, and limited pilot testing with end users. The results demonstrate that a mobile-engineered microlearning system can achieve high completion rates, acceptable latency under concurrent access, and effective analytics-driven feedback loops. The study contributes a practical mobile software engineering artefact and design insights for AI-enabled learning applications in vocational education
Comparative Analysis of Naïve Bayes and K-Nearest Neighbor for Lexicon-Based Emotion Classification of Paxel App User Reviews
Full text linkThe rapid growth of app-based delivery services has increased the importance of understanding user emotions as an indicator of service quality. User reviews on digital platforms provide valuable insights into customer perceptions, satisfaction levels, and service-related issues. This study aims to compare the performance of Naïve Bayes and K-Nearest Neighbor (KNN) algorithms in classifying user emotions related to the Paxel application. The dataset was collected from Google Play Store and X (Twitter) using web scraping techniques and subsequently processed through text pre-processing stages, including case folding, tokenization, and stopword removal. Emotion labels were assigned using the NRC Indonesian Emotion Lexicon, while feature extraction was performed using the TF-IDF method. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) was applied prior to model training. Experimental results show that the Naïve Bayes model achieved the highest overall accuracy of 90.83% with a weighted F1-score of 0.90, while the KNN model obtained an accuracy of 81.21% and a weighted F1-score of 0.77. Both models performed well in identifying happy, sad, and neutral emotions, whereas anger remained the most challenging class to classify. Overall, Naïve Bayes demonstrated more consistent and reliable performance for sentiment analysis tasks.
Developing Madasari Beach Tourism through the Hexahelix Approach
Full text linkThis study is motivated by the potential of Madasari Beach as an emerging tourism destination in Pangandaran Regency, which is expected to develop in parallel with Pangandaran Beach and Batukaras Beach. The purpose of this research is to formulate a sustainable development strategy for Madasari Beach using the Hexahelix approach, which involves six key stakeholders: government, academia, the business sector, local communities, media, and community organizations. Using a qualitative, descriptive-analytical approach, the study explores the dynamics of collaboration among these actors in developing a competitive and resilient tourism destination. The findings reveal that the government remains a dominant actor but lacks structural synergy with other stakeholders, while community participation is high yet not formally institutionalized. Local businesses face financial and marketing challenges, and academic engagement tends to be project-based rather than continuous. Media and financial institutions, although having strategic potential, remain underutilized. These findings highlight the need for an integrated Hexahelix collaboration framework to strengthen institutional synergy, empower local communities, and promote digital transformation and narrative-based tourism branding. The study concludes that the development of Madasari Beach must transcend physical infrastructure and adopt a collaborative governance model that harmonizes economic, social, and cultural sustainability, thereby significantly enhancing local revenue and long-term destination competitiveness in Pangandaran Regency
Classification of Bougainvillea Plant Types Using Convolutional Neural Network Algorithm
No full textBougainvillea is one of the most popular ornamental plants, featuring a variety of types with morphological characteristics that often appear very similar. This resemblance frequently complicates the conventional identification process, particularly for sellers and buyers at Rabiku Florist. This study aims to develop an Android application capable of automatically classifying different bougainvillea types using a Convolutional Neural Network (CNN) algorithm. The system is developed using the Rapid Application Development (RAD) methodology, leveraging the MobileNetV2 architecture and integrating it with the TensorFlow Lite framework to ensure compatibility with mobile devices. The application is designed to identify five types of bougainvillea using digital images captured via the device’s camera or selected from the user’s gallery. Based on implementation results, the system demonstrates strong classification performance and delivers accurate information to users. This application is intended to serve as a practical and user-friendly tool for both the general public and businesses in accurately identifying bougainvillea species.Keywords: Image Classification, Bougainvillea, Convolutional Neural Network, MobileNetV2, Android
A Hybrid IndoBERT-SERVQUAL Approach for Patient Satisfaction Evaluation in Hospital Services
Full text linkThe development of information and communication technology (ICT) provides opportunities for healthcare institutions to improve service quality through the digitisation of patient satisfaction evaluation processes. XYZ Hospital still uses manual methods to measure patient satisfaction, resulting in a slow and error-prone recapitulation process. This study aims to design and implement a sentiment analysis-based patient satisfaction system using the IndoBERT method integrated with quantitative Likert scale measurements based on the SERVQUAL dimensions. The IndoBERT model is used to classify positive and negative sentiments, while the Likert score provides a numerical representation of service quality. The study uses a hybrid approach by processing qualitative data in the form of 2,358 patient text reviews and quantitative data from the SERVQUAL questionnaire, which has been tested for validity and reliability. The IndoBERT model was trained and tested with an 80:20 data split and evaluated using accuracy, precision, recall, and F1-score metrics. The results show that the IndoBERT model is capable of classifying patient satisfaction sentiment with 91.10% accuracy and relatively balanced performance across both sentiment classes. The integration of sentiment analysis results and SERVQUAL scores is presented in an interactive dashboard to support decision-making at XYZ Hospital. This research contributes to the development of a more comprehensive, automated, and data-driven patient satisfaction evaluation system to support improvements in healthcare quality