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:Equivalency education is one of the nonformal education services that plays an important role in expanding educational access for individuals who are unable to complete formal education. The success of equivalency education…
ion programs is determined not only by the availability of educational access but also by learners’ participation in the learning process. This study aims to analyze the strengthening of educational access and learner participation through the equivalency education program at PKBM Minda Utama, Bandung City. The study employed a qualitative approach using a case study method. Data were collected through in-depth interviews, observations, and document analysis involving PKBM managers, tutors, and learners. Data analysis was conducted using the interactive model of Miles, Huberman, and Saldaña, consisting of data condensation, data display, and conclusion drawing. The findings indicate that educational access was strengthened through flexible learning schedules, simplified administrative requirements, and continuous program socialization to the community. Learner participation was reflected in active engagement during learning activities, supported by communicative, contextual, and needs-based learning approaches. The success of the program was supported by managerial commitment, tutor competence, and increasing public awareness of the importance of education, while economic constraints, work demands, and limited facilities remained challenges. The study concludes that educational access and learner participation are interrelated dimensions that determine the success of equivalency education programs. Therefore, strengthening both dimensions should be viewed as an integrated effort to improve the effectiveness of equivalency education and support lifelong learning
Abstract:Non-formal education plays an important role in providing educational services to communities unable to complete formal education. One form of non-formal education that serves as an alternative education is the Package C…
Equivalency Education Program. This study aims to analyze the implementation of the community empowerment management function through the Package C Equivalency Education Program at PKBM Buana Mekar Baleendah using the POAC (Planning, Organizing, Actuating, and Controlling) management approach. The study used a descriptive qualitative method with the research location at PKBM Buana Mekar, Bandung Regency. The research subjects consisted of PKBM managers, tutors, and Package C learners. Data collection techniques were carried out through observation, interviews, and documentation. Data analysis used the stages of data reduction, data presentation, and drawing conclusions. The results of the study indicate that the planning function has been carried out through identifying community needs and preparing flexible learning programs. The organizing function is seen from the division of tutor tasks and a clear organizational structure. The implementation function is carried out through andragogy-based learning with lectures, discussions, questions and answers, and skills practice methods. Meanwhile, the supervisory function is carried out through learning evaluation, attendance monitoring, andsupervision of skills practice. Although the program's implementation has been quite successful, several obstacles remain, such as limited digital learning media, unstable student attendance rates, and suboptimal utilization of practical facilities. Overall, the Package C Program at Buana Mekar Community Learning Center (PKBM) has systematically implemented management functions to support the community empowerment process through equivalency education
Abstract:Digitalization in education continues to increase, particularly in the use of learning media. However, various challenges associated with the emergence of eras based on birth years often lead to differing perspectives on…
improving the quality of education today. The process of integrating Powtoon learning media with a sense of responsibility in Gen Z students requires a comprehensive effort, considering that the assessment indicators for this attitude are crucial for learners in the modern era. Gen Z students (born 1997-2012) are digital natives who are pragmatic, creative, and highly dependent on technology for learning and personal branding. They favor visual-interactive methods, care about mental health/the environment, and focus on practical career outcomes (side hustles), but are prone to distraction and anxiety. Meanwhile, types of student attitude assessments generally include direct observation by lecturers, self-assessment, peer assessment, and daily journal entries. Aspects assessed include discipline, responsibility, honesty, cooperation, politeness, and initiative. This technique often uses a Likert scale or descriptive rubric. Therefore, it is crucial to pay attention to these items in the learning process at university. Powtoon is a web-based online animation and presentation creation platform that allows users to create engaging visual content, such as explainer videos, without requiring advanced graphic design skills. This application uses drag-and-drop features, ready-to-use templates, animated characters, and is supported by AI-based tools. This research uses a descriptive method, namely a research approach that aims to describe, explain, or map the characteristics of a phenomenon, situation, or population systematically, factually, and accurately based on data collected during the study. The results show the successful integration of Powtoon learning media with the responsible attitude of Gen Z students, evidenced by the existence of an orderly, understandable learning process and a high quality of understanding.
Abstract:The aim of this research was to investigate: (1) the application of the Community Language Learning (CLL) model on students’ speaking competence, (2) the students’ speaking competence before and after the implementation…
ion of the CLL model, and (3) whether there is a significant effect of the CLL model on students’ speaking competence. The population of this study consisted of 248 tenth-grade students at SMA Negeri 5 Padangsidimpuan. Using systematic sampling, a total of 35 students were selected as the sample. This research employed an experimental method. Data were collected through observation and speaking tests, and the results were analyzed using a paired-sample t-test. The findings revealed that the application of the CLL model on students’ speaking ability scored 3.6, categorized as “Very Good”. The students’ mean speaking score before the implementation of CLL was 78.51 (“Good”), which increased to 83.42 (“Very Good”) after the treatment. The t-test calculation yielded a t-value of 7.15, which exceeds the critical t-value of 2.03 at a 5% significance level (df = 35). Therefore, it is concluded that there is a statistically significant effect of the Community Language Learning model on students’ speaking competence among tenth-grade students at SMA Negeri 5 Padangsidimpuan.
Abstract:This study aimed to examine the effect of the group résumé method on tenth-grade students’ ability to write recount texts at SMA Negeri 6 Padangsidimpuan. Specific objectives were to describe students’ writing ability before…
ity before and after implementing the group résumé method and to determine whether the method produced a significant improvement. The population consisted of 124 tenth-grade students, and a systematic sampling procedure yielded a sample of 27 students. The study used an experimental design; data were collected with observation sheets and writing tests. The mean score after applying the group résumé method was 3.5, which falls into the “Very Good” category according to the study’s scoring criteria. A t-test was used to analyze the results: tcomputed = 6.73, while ttable = 2.06. Because ttest> ttable, the findings indicate that the group résumé method had a statistically significant positive effect on students’ recount writing ability.
Abstract:This study examines how core marching band structures can be adapted for Indonesian early childhood education through developmentally appropriate practice and performance theory. The study responds to concerns that preschool…
hool marching band activities may reproduce discipline-oriented rehearsal models designed for older learners. A one-group pre-test and post-test mixed-methods design was used with twenty Indonesian preschool children aged four to five years. Over six weeks, children participated in twelve adapted marching band sessions that combined simplified rhythmic patterns, child-scaled instruments, neat but developmentally adjusted formations, cooperative music-making, visual-motor activities, and responsive teacher facilitation. Quantitative data were collected using a four-point developmental observation rubric covering rhythmic competence, motor coordination, and socio-emotional engagement. Qualitative data were obtained from teacher reflective journals and post-intervention interviews. Paired-sample analysis showed higher post-test scores across the three developmental domains. The largest observed improvement appeared in socio-emotional engagement, followed by rhythmic competence and motor coordination. However, because the study did not include a control group, the findings should be interpreted as developmental changes observed after participation rather than definitive causal effects of the intervention. Qualitative findings indicated that children participated more confidently when teachers simplified rhythmic tasks, used clear and neat formations with reduced technical pressure, provided child-scaled instruments, supported safe movement, and acted as co-players and emotional co-regulators. The study reconceptualizes marching band routines not as rigid disciplinary scripts, but as adaptable performative frames that may support social participation, emotional regulation, rhythmic learning, motor coordination, cooperation, and creative agency when aligned with children’s developmental readiness.
Abstract:Traditional Arabic linguistic studies often fall into a dichotomy that separates Nahwu (syntax) and Sharf (morphology), causing learners to lose the functional orientation of the language. This research aims to formulate…
a new direction in Arabic morphosyntactic studies through the integration of classical theory, modern linguistics, and pedagogical applications. Using a qualitative-descriptive approach with a library research method, data were analyzed comparatively and integratively from various reputable scientific literatures. The research results show that the integration of Al-Jurjani's Nazhm theory with systemic functional and generative-transformational linguistic perspectives is capable of providing a more logical explanation of Arabic language structures. Furthermore, digitalization through corpus analysis and computational linguistics enables empirical mapping of language patterns to support AI development. Pedagogically, the implementation of an integrative approach that unites the teaching of Nahwu and Sharf, alongside the utilization of data-based media, has proven to be more effective in enhancing students' communicative skills compared to conventional methods. This research concludes that strengthening morphosyntactic studies is a crucial step in modernizing Arabic language learning in the global era.
Abstract:This study aims to analyze the effectiveness of gamified learning environments in improving literacy skills among primary school students. Gamification, which incorporates game elements such as points, badges, levels, and…
d challenges into the learning process, is considered capable of enhancing motivation and student engagement—particularly in literacy learning, which young learners often perceive as less appealing. This research employed a mixed-methods design involving students from both lower and upper primary grades as research subjects. Quantitative data were collected through literacy tests and motivation questionnaires, while qualitative data were gathered through observations and interviews. The findings reveal that gamified learning environments significantly improve students’ reading comprehension, vocabulary mastery, and reading interest. Moreover, game elements such as challenges and rewards positively influence students’ learning motivation and persistence in completing literacy tasks. These results highlight gamification as an effective and innovative approach to enhancing literacy skills, making it a valuable strategy for integration into primary school instruction.
Abstract:The rapid advancement of Artificial Intelligence (AI) presents both opportunities and challenges for elementary education. Teachers play a strategic role in preparing young learners to understand and adapt to technology…
critically, creatively, and ethically. This study aims to analyze the role of elementary school teachers in integrating AI concepts through simple coding activities, as well as to identify the strategies and challenges encountered during implementation. The research employed a qualitative descriptive approach, using interviews, classroom observations, and document analysis as data collection techniques.
The findings reveal that teachers serve as digital learning facilitators, innovators in designing coding-based learning activities, and ethical guides who help students use technology responsibly. Simple coding activities effectively foster students’ logical thinking, creativity, and digital collaboration skills. However, limited technological infrastructure and insufficient teacher training remain major obstacles to sustainable implementation. Therefore, systemic support through educational policy, professional development, and adaptive curriculum design is essential.
Integrating AI concepts through simple coding in elementary schools not only enhances digital literacy but also cultivates ethical awareness and social responsibility toward technology. With collaborative support from educators, institutions, and policymakers, elementary education can become a foundational stage for shaping a generation that is intelligent, creative, and morally grounded in the era of artificial intelligence