Publication Search

This study conducts sentiment analysis of Indonesian user reviews of the CapCut application using IndoBERT and compares two evaluation schemes: a single 80/20 train–test split and stratified 5-fold cross-validation (k=5). A total of 1,048,575 reviews were collected from the Google Play Store through web scraping and labeled into three sentiment classes based on rating: negative (1–2), neutral (3), and positive (4–5). After preprocessing—cleaning, case folding, banned-word removal, normalization—and duplicate removal, 517,962 reviews were retained. IndoBERT Base P1 was fine-tuned using fixed hyperparameters (batch size 32, learning rate 2e-5, up to 4 epochs, early stopping patience 2), while undersampling was applied to the training set to address class imbalance. Performance was assessed using accuracy, precision, recall, F1-score, and ROC-AUC, supported by confusion matrix and ROC-curve visualizations. The single split achieved an accuracy of 0.756, whereas cross-validation produced a mean accuracy of 0.740. Across both schemes, the positive class achieved the best performance (F1-score 0.850; ROC-AUC 0.918–0.919), while the neutral class remained the most challenging (precision 0.198–0.206; F1-score 0.280–0.283). Overall, cross-validation is recommended for reporting because it reduces dependence on a single partition and provides a more representative estimate across multiple splits.

Parental involvement is widely acknowledged as a key factor in student academic success, particularly in second language acquisition. However, its impact at the university level, especially among pre-service English teachers, remains underexplored. This study investigates the relationship between parental involvement and English language achievement among first-year English Education students at Universitas Islam Kalimantan Muhammad Arsyad Al Banjari Banjarmasin (UNISKA). Employing a quantitative survey design, data were collected from 36 purposively selected participants using a structured Likert-scale questionnaire. The instrument measured both the forms and frequency of parental involvement and students’ self-reported performance in English-related subjects. Data were analyzed using descriptive statistics and Pearson Product-Moment Correlation via SPSS 26. Findings indicate that students generally perceive moderate to high levels of parental involvement, especially in providing academic resources, financial support, and attending university-related events. However, involvement in educational decision-making and career discussions was notably low. A significant positive correlation was found between parental involvement and students' academic performance, particularly in aspects such as discipline, assignment completion, and encouragement. Emotional impacts such as increased motivation or reduced anxiety showed more mixed responses. These findings highlight the enduring influence of parental support in higher education and suggest further exploration of its emotional dimensions.

The rapid development of the Internet of Vehicles (IoV) has introduced new security challenges, particularly in protecting Controller Area Network (CAN Bus) communications from cyberattacks such as Denial of Service (DoS) and spoofing attacks. This study proposes the implementation of the Extreme Gradient Boosting (XGBoost) algorithm combined with Information Gain feature selection to improve intrusion detection performance in IoV environments. The CICIoV2024 dataset, which represents both benign and malicious traffic, is used as the primary data source. The research process includes data integration, preprocessing, feature selection, data splitting, and model training using a 5-fold cross-validation approach. Experimental results demonstrate that the proposed model achieves outstanding performance, with accuracy, precision, recall, and F1-score exceeding 99.99%, and an Area Under Curve (AUC) value approaching 1.00. Furthermore, Information Gain successfully identifies the most influential CAN payload features, enhancing model efficiency without sacrificing accuracy. These findings confirm that the combination of Information Gain and XGBoost is highly effective for developing a fast, accurate, and efficient intrusion detection system in IoV networks.

Flower disease detection is a significant challenge in modern agriculture, particularly with factors such as changes in leaf color, petal shape and structure, and environmental conditions affecting the accuracy of conventional models. These factors make it difficult to achieve optimal results using traditional methods. Transfer learning is an effective solution to improve image detection performance, especially when data is limited. This study used several pre-trained models, namely VGG16, ResNet50, and EfficientNet-B0, to detect three types of flower diseases: black spot on roses, white powdery mildew, and leaf rust. The research process included data processing, increasing the data volume using augmentation techniques, model training, and evaluation of the results. Experimental results showed that the EfficientNet-B0 model produced the highest accuracy of 97.2%, significantly better than the CNN model built from scratch with an accuracy of 85.1%. This study demonstrates that transfer learning is highly effective in improving the accuracy of flower disease detection, making it a more reliable alternative to methods that do not utilize pre-trained models, especially for agricultural applications that require high levels of accuracy in disease detection.

This study examines the factors that cause fraud in financial reporting. The study analyzed 195 data points from 39 financial institutions listed on the Indonesia Stock Exchange (IDX) during the period 2019 to 2023 using a purposive sampling technique. The research applied multiple linear regression analysis to analyze the impact of governance independence and performance variables on the likelihood of fraudulent financial reporting. The independent variables include financial targets assessed by profitability (return on assets [ROA]), financial stability measured by changes in assets, external pressure measured by the debt-to-equity ratio (DER), and the proportion of independent commissioners as a measure of good corporate governance. The study proves that financial targets affect fraudulent financial reporting, while financial stability, external pressure, and independent commissioners do not influence fraudulent financial reporting. The findings of this study provide valuable insights for regulators, investors, and management to enhance oversight and reduce the risk of fraud in the banking sector.

The increasing demand for interactive web applications has encouraged the adoption of server-driven approaches such as Livewire as an alternative to building Single Page Applications (SPAs) without complex client-side JavaScript. However, the performance implications of this approach compared to conventional methods remain insufficiently explored. This study presents an empirical comparison between Laravel Blade with AJAX and Livewire in an academic attendance system scenario. Performance evaluation was conducted using k6 on the same web server, complemented by manual browser-based testing to observe actual communication patterns. The results indicate that Livewire exhibits approximately 2.7× higher average response time and up to 6× greater bandwidth consumption than Laravel Blade, primarily due to its snapshot mechanism and state synchronization process. Conversely, Livewire demonstrates better stability, reflected by lower maximum response times and a 0% error rate. These findings highlight a clear trade-off between resource efficiency and development convenience, where Livewire favors stability and developer productivity, while Laravel Blade provides superior efficiency in terms of latency and bandwidth usage.

This study aims to examine the effect of investment in fixed assets, financial performance, and thin capitalization on tax avoidance in non-financial companies listed on the Indonesia Stock Exchange (IDX) in 2023. The research utilizes 431 company samples and employsAmultiple linear regression analysis. A descriptive quantitative method with a purposive sampling technique is applied, ensuring that only companies meeting specific criteria are included in the study. The findings.indicate that, simultaneously, the three independent variables have a significant influence on tax avoidance. However, when tested individually, more detailed results emerge. The variable of.investment in fixed assets does not show a significant effect on tax avoidance, suggesting that the size of fixed assets does not necessarily determine a company’s level of tax avoidance. In contrast, financial performance demonstrates a positive effect, indicating that companies with.stronger performance tend to have a greater ability to engage in tax planning. Meanwhile, thin capitalization has a negative effect, meaning that a higher proportion of certain types of debt tends to reduce the level of tax avoidance. These findings provide a more comprehensive understanding of the factors influencing tax avoidance behavior in Indonesia.

The increasing volume of online hotel reviews provides valuable insights into customer perceptions but poses challenges for manual analysis due to its unstructured nature. This study aims to compare the performance of Recurrent Neural Network (RNN) and Bidirectional Encoder Representations from Transformers (BERT) in hotel review sentiment analysis. A total of 20,491 TripAdvisor hotel reviews were classified into three sentiment categories: negative, neutral, and positive. The research methodology includes text preprocessing, stratified data splitting, class imbalance handling using Random Over-Sampling, tokenization, and supervised model training. Model performance was evaluated using a confusion matrix and classification metrics. The results indicate that BERT outperforms RNN, achieving an accuracy of 80.54%, while RNN reached 62.21%. BERT demonstrated superior capability in capturing contextual and semantic information in hotel reviews. These findings suggest that transformer-based models are more effective for sentiment analysis of complex textual data in the hospitality domain and can support data-driven service improvement strategies.    

This study explores how the organizational culture of Sanggar Kartika Budaya strengthens local artistic values through identity building, leadership, training strategies, and adaptive creativity. Rooted in a commitment to traditional arts, the sanggar positions local cultural expression not only as heritage but also as a living space for innovation. The research aims to uncover how these cultural elements shape member behavior, sustain artistic traditions, and support the regeneration of young artists. Using a qualitative approach with document analysis, this study examines official profiles, program descriptions, and relevant scholarly sources. The findings reveal that the sanggar’s cultural identity centered on the motto “Pegang Teguh Seni Tradisi Siap Berkreasi”serves as the backbone of its learning system and creative ecosystem. Leadership plays a central role in directing artistic vision while safeguarding cultural authenticity. Structured training, literacy activities, and collaborative performances effectively embed traditional values in new members. The sanggar also demonstrates an ability to evolve with modern trends through creative choreography, multimedia integration, and active participation in contemporary festivals, all while maintaining strong roots in local heritage. These findings highlight how a well-structured organizational culture can act as a powerful engine for cultural preservation and artistic resilience. The implications suggest that cultural institutions can remain relevant in a fast-changing era by blending heritage with innovation, ensuring that tradition continues to live meaningfully in the hands of future generations.

Gestational Diabetes Mellitus (GDM) is a pregnancy-related metabolic disorder that poses health risks to both mother and fetus if not detected early, requiring accurate prediction methods for early screening and clinical decision-making. This study applies the Random Forest algorithm to detect GDM risk using clinical data from the Pima Indian Dataset. Data preprocessing included handling missing values, standardization, feature engineering, and a 70:30 train–test split. Two models were developed: a baseline and an optimized model using GridSearchCV hyperparameter tuning, validated with 5-fold cross-validation. Performance was assessed using a classification report, confusion matrix, and ROC–AUC. Results show that the optimized model outperforms the baseline, achieving 88% accuracy, an AUC of  93%, and average recall of 81%–85%. Compared to previous studies, this approach demonstrates improved predictive performance. The findings indicate that combining Random Forest with comprehensive preprocessing, feature engineering, and model optimization is effective and feasible for developing a medical decision support system for early GDM risk screening.

This study aims to analyze the application of accounting according to PSAK 65 concerning consolidated financial statements to assess the company's financial performance at PT Warung Begok Indonesia. The object of this study is a company in the field of processed livestock manufacturing for the period 2023-2024. The data in this study are primary data sourced from the annual financial reports of the head office and branches. The total sample in this study was 3 company financial reports. Data collection techniques used interviews and documentation. The hypothesis in this study was tested using descriptive analysis techniques. Based on the data analysis carried out in this study, it shows that the financial statements before and after consolidation have an effect on the assessment of the company's financial performance. This study contributes to increasing knowledge and understanding of the head office and branch consolidated reports according to PSAK 65, and can assess the company's financial performance. Although the consolidated report has been carried out, it is hoped that the company will continue to apply controls and policies in its implementation, because this can affect the assessment of the company's financial performance so that it will be useful in decision making.

Diseases in primary health services exhibit complex spatial-temporal dynamics due to urbanization and population mobility. Conventional surveillance approaches are difficult to capture these patterns adaptively. Machine learning (ML) based on spatio-temporal modeling offers a solution with the ability to detect disease clusters automatically and with high precision. Research Objectives: This research aims to develop a machine learning model to detect disease hotspots from primary service data in Indonesia, with a focus on improving prediction accuracy, interpretability, and relevance of health policies. Methodology: The primary service dataset for 2024 (5,343 entries) was analyzed using three ML models Gradient Boosting Machine (GBM), Temporal Random Forest (TRF), and Multi-EigenSpot with spatial (village) and temporal (week, month) features. Performance evaluation includes predictive (AUC, F1-score) and spatial (Moran's I, Spatio-Temporal Correlation Index) metrics. Results: The results showed that Multi-EigenSpot achieved the best performance (AUC=0.91; F1=0.86), with the detection of dominant hotspots in Sungai Asam and Beringin Villages. Moran's I value of 0.63 indicates a strong spatial autocorrelation, while STCI=0.57 indicates moderate temporal stability. Conclusions: ML-based spatio-temporal models are effective in identifying hidden disease patterns and have the potential to be integrated into national digital surveillance systems. This approach supports precision public health by providing a scientific basis for real-time location- and time-based intervention policies.

Micro, Small, and Medium Enterprises (MSMEs) play a strategic role in Indonesia's economic development, particularly in developing products based on local wisdom. Toko Jayabaru is an MSME that markets Maumere's signature souvenirs made from traditional ikat woven fabric, facing various challenges and opportunities amid business and tourism dynamics. This study aims to identify internal and external factors affecting Toko Jayabaru's performance and formulate appropriate business development strategies through SWOT analysis. The research employs a qualitative descriptive approach with data collection through in-depth interviews with the owner and management of Toko Jayabaru. Data analysis uses the SWOT framework (Strengths, Weaknesses, Opportunities, Threats) to identify the business's strategic position and formulate alternative development strategies. Toko Jayabaru's main strengths lie in strong local cultural identity, authentic product quality, and adequate business experience. Weaknesses include limited digital marketing, restricted production capacity, and lack of derivative product variations. Opportunities encompass Flores tourism sector growth, increasing interest in local products, and potential strategic collaborations. Main threats are competition from similar products, influx of imitation products, and dependence on tourism sector fluctuations. Recommended development strategies include strengthening branding through storytelling, diversifying woven derivative products, optimizing digital marketing, strategic collaboration with tourism stakeholders, enhancing human resource capacity, and implementing customer loyalty programs. Implementation of these strategies is expected to increase MSME competitiveness while preserving Maumere's local culture.

End-to-end autonomous driving has emerged as a promising paradigm in which deep neural networks directly map raw visual inputs to continuous control actions. Despite its effectiveness, this approach suffers from limited transparency, posing significant challenges for deployment in safety-critical driving scenarios. This study addresses the lack of interpretability in vision-based end-to-end autonomous driving systems and aims to analyze model decision-making behavior under critical conditions such as sharp steering maneuvers and abrupt control transitions. To this end, an explainable end-to-end autonomous driving framework is proposed, combining a convolutional neural network trained via imitation learning with gradient-based visual attribution techniques, including Grad-CAM. The model predicts continuous steering, throttle, and braking commands directly from front-facing camera images, while explainability mechanisms are applied to reveal input regions influencing each control decision. Model performance is evaluated using both prediction accuracy and safety-oriented behavioral metrics. Experimental results show that the proposed explainable model achieves lower control prediction errors compared to a baseline end-to-end CNN, reducing steering mean squared error from 0.034 to 0.031, throttle error from 0.021 to 0.019, and brake error from 0.018 to 0.016. Moreover, safety-oriented analysis indicates improved driving stability, with steering variance reduced from 0.087 to 0.072 and abrupt control changes decreased from 14.6 to 10.3 events. Visual explanations consistently highlight road surfaces and lane-related structures during complex maneuvers, indicating reliance on semantically meaningful cues. In conclusion, the results demonstrate that integrating explainability into end-to-end autonomous driving not only preserves predictive performance but also correlates with smoother and more stable driving behavior. This framework contributes to the development of transparent and trustworthy autonomous driving systems suitable for safety-critical applications

The issue of street vendors (PKL) in Sidoarjo Regency, particularly in the Gading Fajar area, has become a significant concern as it relates to public order, the use of public space, and the economic dynamics of small communities. To address these challenges, the Sidoarjo Regency Government enacted Regional Regulation Number 3 of 2016 as the legal basis for structuring and empowering PKL. This study examines how the regulation is implemented in practice and evaluates its effectiveness using a qualitative descriptive method through interviews, observations, and documentation, analyzed with Leo Agustino’s policy evaluation model, which assesses five key aspects: administrative resources, institutional coordination, infrastructure and technology, financial support, and regulatory adequacy. The findings show that the implementation of the regulation has not yet reached optimal performance, as limited socialization, insufficient personnel, weak coordination among agencies, inadequate supporting facilities, and low compliance with zoning rules hinder the achievement of policy objectives. These issues are reflected in the continued presence of PKL operating in non-designated areas despite clear regulatory provisions. Therefore, strengthening institutional capacity, improving facilities, enhancing enforcement consistency, and developing more operational technical guidelines are essential to ensure more effective and sustainable management and empowerment of street vendors in Sidoarjo Regency.

Physical fitness is a fundamental determinant of athletic performance and is strongly influenced by dietary intake and lifestyle behaviors. Adequate protein consumption is essential for muscle development and energy metabolism, whereas smoking has detrimental effects on lung function and aerobic capacity. This study aimed to explore the relationship between protein intake and smoking habits with physical fitness, measured by maximal oxygen uptake, among athletes of Persela Football Academy under-eighteen. A quantitative approach with a cross-sectional design was applied, involving adolescent male athletes. Protein intake was assessed using a semi-quantitative food frequency questionnaire, smoking habits were obtained through structured interviews, and maximal oxygen uptake was measured using the multistage fitness test. Findings revealed that the average daily protein intake of athletes was relatively high, while the mean maximal oxygen uptake score fell within the good category. Correlation analysis demonstrated a significant association between protein intake and aerobic fitness, as well as between smoking habits and aerobic fitness. The results indicate that lower protein intake and higher smoking frequency are linked to reduced physical fitness capacity. This study highlights the importance of nutritional interventions and healthy lifestyle promotion as integral components in the development of youth athletes to optimize performance and prevent decline in fitness.

This article examines the limitation of transparency within the Indonesian House of Representatives (DPR) during the formulation of the Job Creation Act (Law No. 11 of 2020) and its implications for legislative performance and public participation. Transparency represents a fundamental requirement in a democratic legal system as it ensures accountability, public oversight, and the legitimacy of legal products. However, the legislative process of the Job Creation Act demonstrated significant procedural issues, including inconsistent draft versions, restricted access to essential documents, accelerated deliberation, and the marginalization of meaningful public participation. This study highlights how these limitations hinder the public’s constitutional rights, weaken legislative oversight, and create asymmetrical power relations that enable elite dominance in policymaking. The lack of transparency also led to procedural defects acknowledged by the Constitutional Court, reflecting a systemic decline in democratic legislative practices. Using a normative juridical method supported by legislative analysis and doctrinal studies, this paper argues that the absence of transparency not only reduces the quality of participation but also erodes the legitimacy and accountability of the DPR. The findings emphasize the urgent need for open access to legislative documents, inclusive public consultation, and strengthened accountability mechanisms to ensure democratic and lawful policy making.  

This study aims to analyze the influence of Innovative Work Behaviour, Upskilling, and Work Ethic on the Health Workers Performance with Intention to Stay as an intervening variable at RSUD Sumberrejo. The background of this research stems from challenges in improving service quality, high workload, and the need to strengthen competency and retention among health workers. The study employs a quantitative approach using a survey method through the distribution of questionnaires, with data analyzed using Partial Least Squares–Structural Equation Modeling (PLS-SEM) through SmartPLS version 4.0. The population consists of 216 employees, and the sampling technique used is non-probability sampling, resulting in 140 respondents. The findings reveal that Innovative Work Behaviour, Work Ethic, and Intention to Stay have a significant positive effect on the performance of health workers. In addition, Innovative Work Behaviour and Work Ethic significantly influence Intention to Stay. However, Upskilling shows a positive but non-significant effect on both Intention to Stay and Performance, indicating that skill enhancement requires managerial support and motivation to contribute effectively to employee performance. Intention to Stay serves as a mediating variable in several relationships among the constructs. Strengthening innovative behaviour, work ethic, and competency development, accompanied by appropriate retention strategies, is essential for improving the performance of health workers in regional hospitals. Future studies are recommended to develop the research model by incorporating additional variables that may have stronger effects on Intention to Stay and Performance.

This study aims to determine the relationship between learning motivation and learning outcomes in SMAW welding engineering among eleventh-grade students at SMKN 2 Solok. This research employed a quantitative method with a correlational approach. The population consisted of all students from classes XI TPM 1 and XI TPM 2, totaling 51 students, using a total sampling technique. Learning motivation data were collected through a validated and reliable questionnaire, while learning outcome data were obtained from post-test scores in the SMAW welding subject. Data were analyzed using the Pearson Product Moment correlation test with the assistance of SPSS software. The results showed a correlation coefficient of r = 0.783 with a significance value of 0.000 < 0.01, indicating a strong, positive, and statistically significant relationship between learning motivation and students’ learning outcomes. These findings suggest that higher learning motivation leads to better learning outcomes in SMAW welding engineering. Therefore, learning motivation plays an important role in improving students’ academic performance. This study is expected to provide useful insights for teachers and schools in developing instructional strategies that enhance students’ motivation and learning outcomes.

This study investigates the impact of board characteristics on the financial performance of non-financial companies listed in the JII70 index in Indonesia. Motivated by the ongoing debate on the effectiveness of corporate governance mechanisms in enhancing firm outcomes, particularly within Sharia-compliant markets, this study focuses on three key board attributes: board size, board independence, and female representation on the board. Using a quantitative causal approach and panel data from 25 companies over the period 2020–2023, the study employs a fixed effect model to evaluate the relationship between board structure and financial performance measured by Return on Assets (ROA). The results show that board size has a positive and significant effect on firm performance, indicating that larger boards may enhance oversight capacity and provide broader resources beneficial to strategic decision-making. Conversely, board independence and board female representation do not exhibit significant effects on financial performance, suggesting that their roles may be more symbolic or constrained by institutional and contextual factors in the sampled companies. These findings highlight the importance of understanding corporate governance not merely in structural terms, but in relation to functional effectiveness and contextual maturity. The study offers implications for regulators, companies, and governance reform initiatives, particularly regarding strengthening substantive roles of independent and female commissioners in improving firm performance within Sharia-compliant markets.