Publication Search

The rapid expansion of e-commerce in Indonesia has resulted in a significant rise in the number of customer reviews, which serve as a valuable source of insight for understanding consumer satisfaction. This study aims to classify or identify sentiments from product reviews on the Tokopedia platform into three categories, using the Support Vector Machine algorithm. The classification method data were ethically collected through web scraping and include review text, ratings, and the number of “likes.”  The preprocessing stage involved several NLP techniques such as pre-procesesing data representation was generated using the Term Frequency–Inverse Document Frequency method, while the issue of class imbalance was addressed using the Synthetic Minority Over-sampling Technique.  Based on the test results, the SVM model achieved an accuracy of 79.48% on the test data using a linear kernel, showing the best performance in classifying positive sentiments. However, the classification of neutral and negative sentiments still requires improvement. This study demonstrates that the combination of the TF-IDF method, additional numerical features, and data balancing techniques can produce an an efficient sentiment analysis model within the e-commerce domain.

The growing demand for energy-efficient and intelligent thermal systems has driven significant advancements in adaptive compressor design. This paper presents a comprehensive literature review on the development of AI-based compressor systems, with a specific focus on enhancing efficiency under partial-load conditions and optimizing the utilization of residual energy. Through the synthesis of five recent high-impact studies (2020–2025), we examine the application of deep reinforcement learning (DRL), hybrid evolutionary algorithms, and neural network surrogate modeling in compressor optimization. Key findings indicate that model-based DRL combined with surrogate CFD can achieve up to 8% efficiency gains at off-design conditions. Hybrid approaches integrating Genetic Algorithms (GA) with DRL reduce optimization time by 30% while improving pressure ratios. Neural network surrogates provide high-speed, real-time performance predictions with less than 1% error, enabling mass iterative design. Furthermore, intelligent load classification using radial basis function networks (RBFN) allows adaptive response to varying operating conditions with over 95% accuracy. Collectively, these methods form a framework for intelligent, self-optimizing compressor systems capable of real-time adaptation and energy recovery. The results suggest that AI-enhanced adaptive compressors represent a transformative direction for energy-sensitive sectors, including HVAC, power generation, and sustainable industry.

This study examines the relationship between market efficiency and digital financial innovation in the context of global financial transformation over the past decade, when fintech, cryptocurrency, and Decentralized Finance (DeFi) have significantly altered price formation and information dissemination mechanisms. The main issue raised is whether the Efficient Market Hypothesis (EMH) theory remains relevant in the face of digital market dynamics characterized by high volatility, speculative behavior, and regulatory uncertainty. The objective of this study is to assess the impact of digital innovation on information efficiency, price transparency, and the stability of modern financial markets. The study used the Systematic Literature Review (SLR) method, examining 15 scientific articles published between 2015 and 2025 from various academic databases. The findings indicate that digital technology increases access and speed of information distribution, but does not always result in consistently efficient markets. Crypto and DeFi markets have been shown to exhibit fluctuating efficiency due to price anomalies, information asymmetry, and weak regulation. Overall, the literature synthesis confirms that market efficiency in the digital era is dynamic and influenced by the interaction between technology, investor behavior, and governance quality. This study concludes that the EMH remains relevant as a basic framework, but needs reinterpretation to suit the complex and rapidly changing characteristics of digital markets.

PT Mandiri Banana Indonesia still requires further development and arrangement of its layout and facilities to enhance the efficient and optimal use of land. This study aims to determine whether the existing layout at PT Mandiri Banana Indonesia is effective in supporting operational flow and the uninterrupted progression of the production process. The research adopts a quantitative descriptive approach, which is used to measure the correlation between activities through the Activity Relationship Chart (ARC) and Total Closeness Rating (TCR) methods. These methods enable the analysis to be presented in a measurable and objective manner as a basis for improving the facility layout. This study proposes a new layout design for the main production area and supporting facilities. The proposed layout is based on the results of ARC and TCR analyses, which indicate several critical spatial interrelationships among the facilities. Based on the findings and discussion regarding the application of the Activity Relationship Chart (ARC) and Total Closeness Rating (TCR) in designing the facility layout at PT Mandiri Banana Indonesia, it may be inferred that layout improvement exerts a significant impact on enhancing workflow efficiency and the overall work environment. The proposed alternative layout is expected to achieve a safer, more hygienic, and more productive spatial arrangement by establishing a clear separation between the production zone, administrative zone, and supporting areas.

This study aims to analyze multiple-choice questions related to phase e elements, namely the Principles and Basic Concepts of Accounting and Basic Banking, using the Anates program. The study involved 20 participants, consisting of college students and vocational high school students. The Anates application program serves as a tool to process academic evaluation data accurately and efficiently. The method used in this study is quantitative and is described descriptively, resulting in analytical findings including weighted data scores, test reliability, discriminative power, difficulty level, validity level, and distractor quality. The results from the Anates program make it easier for teachers to evaluate the quality of learning and develop more focused, innovative, and student-centered teaching plans. This research is expected to provide benefits in improving students' accounting knowledge, and teachers are expected to be able to adjust their teaching methods and strategies dynamically, thereby supporting the optimal improvement of students' learning outcomes in this digital era.

This study analyzes the gap in the implementation of Information Technology IT service management at an internet service provider in Purwokerto using the ITIL V4 Service Value System SVS framework. The company faces a number of major problems, such as delays in incident handling, data fragmentation between operational applications, low automation in network monitoring, and suboptimal coordination between the technical and customer service divisions. The purpose of this study is to evaluate the level of compliance of current service practices with ITIL V4 SVS best practices and to formulate recommendations for improvements that can increase operational efficiency and service reliability. The research uses a qualitative descriptive method with a case study approach, with data collected from interviews and observations in the technical and customer service divisions, then analyzed based on the five main components of ITIL V4 SVS. The results show that the company has implemented several ITIL principles, particularly in terms of customer value focus and process simplicity, but the implementation of iterative feedback, data integration, and automation is still at a low level of maturity. This study concludes that strengthening the real-time monitoring system, increasing cross-divisional visibility, and establishing a Continual Improvement Register are important steps towards realizing more efficient, responsive, and sustainable IT service management.

Zinc (Zn) is one of the most common heavy metal contaminants found in industrial wastewater and solid residues such as slag, electroplating waste, and metal ash. At excessive concentrations, Zn can cause environmental disturbances, including toxicity to aquatic organisms, disruption of microbial activity, and groundwater contamination. Long-term exposure may also lead to bioaccumulation and potential health risks to humans. This article presents a comprehensive literature review that discusses the chemical properties of Zn, its environmental behavior, and the development of recent treatment technologies within the last five years. Several techniques, including adsorption using modified or composite materials, biosorption utilizing microalgae and agricultural biomass, as well as solidification–stabilization with amendment agents such as biochar or iron-sulfide compounds, are evaluated and compared. The literature indicates that no single treatment method is universally effective for all waste types; therefore, hybrid or integrated treatment systems are considered more efficient and sustainable. Based on the reviewed evidence, this study proposes an engineering concept that emphasizes environmental safety, cost-effectiveness, and industrial applicability.

This community service activity aims to strengthen teachers' capacity to manage deep learning through the utilization of artificial intelligence (AI) in elementary school classrooms. The rapid development of AI technology provides opportunities for teachers to design more personalized learning, conduct assessments efficiently, and make data-driven learning decisions. The program is implemented in three stages: preparation, execution, and evaluation. The preparation stage includes the development of training modules and mapping relevant AI applications to support deep learning. The execution stage consists of workshops, hands-on practice using AI applications, and collaborative development of teaching materials by teachers. Evaluation is conducted through reflective assessments, task performance evaluations, and follow-up interviews. The results of the activity show significant improvements in teachers' understanding of AI-based deep learning management, including the ability to use AI for lesson planning, formative assessment, and analyzing students' learning progress. Teachers also reported increased confidence in integrating AI into teaching activities and recognized the benefits of AI in promoting students' higher-order thinking skills. This program demonstrates that strengthening teachers' competencies in utilizing AI can enhance the quality of deep learning management in elementary schools.

The study aims to improve the passion fruit syrup production system at Harisma Home Industry, which has been hindered by an inefficient facility layout and complicated raw material flow. These issues lead to longer processing time, higher operator workload, and reduced production capacity. To solve this, the research uses the Activity Relationship Chart (ARC) and Total Closeness Rating (TCR) to evaluate and redesign the layout. TCR results show that the Raw Material Warehouse has the highest priority with a score of 119, requiring an Absolutely Important (A) relationship with the Production Room. The Parking Area and Waiting Room also fall into the Absolutely Important category, as they support smooth movements of materials and visitors. Meanwhile, the Toilet has a Very Important (E) relationship with the Waiting Room due to comfort and accessibility needs. Based on these proximity requirements, a new layout was designed by placing the Raw Material Warehouse next to the Production Room to create a faster and more efficient material flow. Other facilities were rearranged to minimize unnecessary movement. This new layout is expected to streamline processes, reduce congestion, and enhance overall capacity and operational performance.

Innovation is the process of optimizing various resources to produce more efficient and sustainable solutions. This study aims to examine the relationship between resources and innovation strategies in supporting sustainable entrepreneurship through a Systematic Literature Review (SLR) approach. A total of 25 scientific articles were analyzed using PRISMA guidelines to examine the role of resources such as human, technological, information, financial, and physical resources in the context of product, process, and managerial innovation. The research findings indicate that the success of innovation is strongly influenced by the organization's ability to utilize and synergize its resources, especially in the development of internal capabilities such as tacit knowledge, research and development activities, and digital technology. Human resource creativity is the main driver of product innovation, while process innovation is strengthened by the application of technology and a learning culture. Managerial innovation is heavily influenced by entrepreneurial orientation and dynamic capabilities in responding to change. The implementation of sustainable innovation strategies such as green, digital, and social innovations also increases business competitiveness through cross-sector collaboration. This study emphasizes the importance of integrated resource management and innovative strategies to achieve sustainability, especially in the small and medium enterprise sector.

The Innovation Development Program conducted by Group 2 in Gunung Sari Ulu Village consisted of a structured series of mentoring activities designed to strengthen the financial literacy and marketing capabilities of local UMKM. The program focused on guiding participants in recording simple cash flow using the Monly AI application, which helped them understand how Artificial Intelligence can support more accurate and organized financial management. In addition, participants were taught how to properly separate incoming and outgoing transaction notes so that their business finances could be monitored more clearly and systematically. The program also introduced strategies for promoting products through digital marketing, enabling UMKM to expand their market reach by utilizing online platforms and creating more appealing promotional content. Overall, this activity aimed to broaden the participants’ knowledge of AI-based financial recording while also equipping them with practical marketing skills needed to increase visibility and attract consumer purchasing power. By integrating technology with improved marketing practices, the program sought to empower UMKM to operate more efficiently, enhance their competitiveness, and strengthen the sustainability of their business activities within the local community.

The increase in the population of Medan City has a direct impact on the increasing demand for housing and settlements, which is not always in line with environmental carrying capacity and the fulfillment of livable housing standards. Residential buildings contribute significantly to energy and water consumption, as well as environmental degradation, thus requiring a sustainable design approach. This study aims to formulate criteria and principles for the design of simple, livable houses by applying the concept of green buildings. The research method used is descriptive qualitative with a focus on the design of class 1a residential buildings. The study was conducted through a review of relevant regulations and standards, including the Ministry of Public Works and Public Housing's Green Building principles, the GREENSHIP Homes assessment system by the Green Building Council Indonesia, and livable housing indicators from the North Sumatra II Housing Provision Implementation Center. The results of the study show that the application of green building concepts in Small Houses can be realized through proper site management, optimization of natural lighting and ventilation, efficient use of energy and water, sustainable waste and wastewater management, and the selection of environmentally friendly building materials. The application of these principles can produce Small Houses that not only meet livable standards but also contribute to environmental sustainability.

Electronic Medical Record (EMR) is an essential component of hospital digital transformation aimed at improving administrative efficiency and service quality. This study aims to analyze the factors influencing the implementation of EMR in outpatient registration at a private hospital in North Jakarta. A mixed-methods design was employed, combining quantitative data collected from questionnaires completed by 30 registration staff with qualitative data obtained through structured interviews and direct observation. The logistic regression analysis revealed that Training and Staff Competence (X2) had a significant positive effect on outpatient registration (OR 30.663; p=0.040), while System Integration and Data Security (X4) also showed a significant effect (OR 15.121; p=0.047). In contrast, Technological Infrastructure Readiness (X1) was positive but not significant (p=0.112), and Organizational Culture and Managerial Support (X3) was negative and not significant (p=0.954). Simultaneously, the model explained 72.1% of the variation in registration effectiveness (Nagelkerke R²=0.721) with a classification accuracy of 93.3%. Qualitative findings supported the quantitative results, highlighting insufficient staff training, persistent technical issues in BPJS system bridging, and difficulties faced by elderly patients in adapting to digital registration. Elderly patients still required staff assistance and simple educational media such as tutorial videos displayed in hospital waiting areas. This study concludes that staff competence and system integration are the key determinants of successful EMR implementation in outpatient registration. It is recommended that hospitals strengthen continuous training programs, improve network and server stability, and expand patient education initiatives to ensure effective, efficient, and patient-friendly digital services.

In today's digital era, the freight forwarding industry has become one of the fastest-growing sectors. The rapid growth of the digital economy has increased the need for fast, safe, and efficient delivery services. However, intense market competition in this industry has pushed companies to build a strong brand image. This is related to the increasingly fierce competition in the freight forwarding sector, such as JNE, SPX Standard, Tiki, and Pos Indonesia. This research is useful for companies and academics: it can serve as a shared reference for examining the influence of brand image on service usage decisions, in the development of theories and concepts in marketing and Islamic economics. The purpose of this study is to analyze the influence of brand image on the decision to use J&T Express's freight forwarding services. The research method used was quantitative, with a survey approach. A questionnaire was distributed to 117 respondents who were active users of J&T Express services. Data analysis was conducted using multiple linear regression with the help of SPSS version 26 software. The results showed that brand image had a positive and significant effect on the decision to use services, with a significance value of 0.015 (<0.05).

The student admission process in many educational institutions is still conducted manually, leading to issues such as data duplication, input errors, and delays in reporting. This study designs and implements a desktop-based student registration information system using VB.NET and MySQL, equipped with an admission-status checking feature and an automated quota-management module. The system was developed using the waterfall model, consisting of requirement analysis, system design using UML, implementation, and black-box testing. Two user roles are supported: admin and student. Admin users can manage applicant data, configure program quotas, open or close the registration period, and generate reports, while student users can create accounts, complete registration forms, and independently check their admission results. The implementation results show that all core functions operate validly based on testing involving two respondents. The quota-management feature successfully restricts the number of applicants according to predetermined capacities, and the admission-status module automatically displays pass or fail results. The system improves administrative efficiency, enhances data accuracy, and reduces reliance on manual record-keeping. Therefore, this desktop application serves as an effective solution for schools requiring a reliable and efficient admission management system without depending on stable internet connectivity.

The rapid growth of online commerce in Indonesia has significantly transformed the way people fulfill their daily needs by providing easier, faster, and more flexible access to goods and services through digital technology. Despite these advantages, the development of e-commerce also presents serious challenges, including rising cases of online fraud, discrepancies between advertised and delivered products, failed transactions, and personal data breaches that threaten consumer privacy. These issues create imbalances in digital contractual relationships, undermining trust and legal certainty for buyers. This study aims to analyze the implementation of the principle of fairness for consumers in e-commerce practices in Indonesia, while also identifying regulatory weaknesses and existing dispute resolution mechanisms. Using a normative legal research approach supported by case studies, the study examines the effectiveness of relevant legal frameworks, particularly the Consumer Protection Law (UUPK) and the Electronic Information and Transactions Law (UU ITE). The findings reveal that although these regulations provide a legal basis for consumer protection, their implementation remains inadequate. Weak supervision of online business actors, limited accountability of platform providers in ensuring transaction security, and complex, costly compensation procedures continue to hinder consumer rights protection. These conditions highlight the urgent need to strengthen consumer protection systems that are more adaptive, efficient, and oriented toward public interest. The study emphasizes the importance of improving online dispute resolution mechanisms, enhancing transparency and responsibility of digital platforms, and expanding digital literacy among consumers. Such measures are essential to ensure that fairness in e-commerce is not only guaranteed normatively, but also effectively realized in everyday digital transactions.

Information system security faces serious challenges due to increasingly complex cyber attacks. Intrusion Detection Systems (IDS) require efficient approaches to handle high-dimensional data such as the NSL-KDD dataset with 41 features. This study aims to implement the Genetic Algorithm (GA) for feature selection on the NSL-KDD dataset to improve the efficiency and accuracy of network attack detection. The method used is computational experimental research, involving data preprocessing, GA implementation for feature selection, building a classification model using Random Forest, and performance evaluation based on accuracy, precision, recall, F1-score, and computation time. The results show that GA successfully reduced features from 41 to 12 features (70.7% reduction), significantly improving computational efficiency. However, model accuracy slightly decreased from 0.4973 to 0.4951, indicating that while GA is effective for feature selection, the elimination of certain features may reduce classification capability. The implication of this study is that GA can be used as a tool to simplify intrusion detection models, but it should be combined with parameter optimization and data imbalance handling to achieve more optimal performance.  

Efficient and integrated public transportation services are a strategic need in sustainable urban development. The Surabaya City Government through the Transportation Department initiated the Wira-Wiri Feeder service on the Bratang-Pasar Turi route (FD07) as a feeder mode that connects densely active areas in the east and west of the city. This study aims to evaluate the implementation and performance of FD07 services using the public policy evaluation framework of William N. Dunn (2003) which includes the dimensions of effectiveness, efficiency, adequacy, justice, responsiveness, and policy accuracy. The research uses a descriptive qualitative approach with data collection techniques through field observations, in-depth interviews, and documentation studies. The results of the study show that the implementation of FD07 services has been running according to operational procedures with an average of 651 passengers per day, supported by field supervision and the Surabaya Integrated Urban Transport System (SIUTS) digital system. However, there are still obstacles in the form of limited fleet numbers, non-professional drivers, limitations of senior mechanics, and inadequate system development budgets. Dunn's six-dimensional evaluation shows that the effectiveness and efficiency of the service are in the medium category, with the main challenges being the accuracy of schedules and the accessibility of bus stop facilities for people with disabilities. This study concludes that improving the quality of human resources, adding fleets, strengthening digital systems, and massive public socialization are strategic steps to realize effective, inclusive, and sustainable feeder services in the city of Surabaya.

This study aims to analyze the effectiveness of human resource (HR) governance in improving employee performance at the Serang City Cooperatives and SMEs Office in 2025. The research method used is a quantitative approach with a survey design, involving 100 employees as respondents. Data were collected through questionnaires and analyzed using multiple linear regression to test the effect of HR governance variables, which include planning, organizing, implementing, and supervising, on employee performance. The results of the study indicate that HR governance has a positive and significant influence on improving employee performance at the Serang City Cooperatives and SMEs Office. Specifically, clear HR planning, efficient organization, structured implementation, and effective supervision have been shown to increase employee productivity and work quality. The implication of this study is the importance of improving and strengthening HR governance as a strategy to improve employee performance, which ultimately can increase productivity, efficiency, and effectiveness in carrying out the duties and responsibilities of local government agencies.

Digitalization demands the MSME sector, including barbershops, to adopt technology in reservation management and marketing. Many barbershops still use manual systems, causing problems such as irregular queues, service delays, and suboptimal promotions. This study formulates how to design an information system that can integrate reservation and marketing functions into a single web-based platform. The objective is to produce an efficient, secure, and user-friendly information system design for both barbershop managers and customers. The method used is the Design Science Research approach with a waterfall system development model, involving needs analysis, system design, database design, and user interface design. The design results were validated by experts and users with a satisfaction rate of over 85%, indicating that the designed system aligns with the operational needs of barbershops. The conclusion is that the developed information system can enhance operational efficiency and customer experience, and is suitable for implementation in the barbershop service sector of SMEs.