JSAI (Journal Scientific and Applied Informatics)

Development of a Mobile-Web-Based Cultural and Tourism Information System for the City of Bima with a Usability Evaluation Using the System Usability Scale (SUS)

Ian Moh. Rohmad Nuryanto — 2026-06-01

This study aims to develop a mobile-web-based Cultural and Tourism Information System for Bima City and evaluate its usability using the System Usability Scale (SUS) method. The system development process consisted of requirement identification, system design, implementation, and usability testing stages. The developed system provides several features, including cultural catalogs, interactive tourism maps, tourism destination information, and an administration panel accessible through mobile and desktop devices. Usability testing was conducted involving 25 respondents using a SUS questionnaire distributed through Google Forms. The results showed that the system was successfully implemented with a responsive and user-friendly interface. Based on the SUS calculation, the system achieved an average score of 81.24, which falls into the Excellent category. These results indicate that the system has a very good level of usability and is capable of providing effective, efficient, and satisfying user experiences. This research is expected to support digital tourism promotion and cultural preservation in Bima City through an integrated information system.

Comparison of Classification Algorithms for Digital Business Students’ Academic Performance: SVM, Random Forest, XGBoost, and LightGBM with Class Imbalance Handling Using SMOTE

Lili Indah Sari — 2026-06-01

This study aims to compare the performance of classification algorithms, namely Support Vector Machine (SVM), Random Forest, XGBoost, and LightGBM, in predicting the academic performance of Digital Business students at ISB Atma Luhur by handling class imbalance using the Synthetic Minority Oversampling Technique (SMOTE). The dataset consisted of 326 student records with 55 questionnaire-based Likert-scale features, GPA, and semester data classified into two academic performance classes. The research stages included data preprocessing, normalization, SMOTE implementation, feature selection using feature importance, model training, and evaluation using accuracy, precision, recall, F1-score, F1 Macro, AUC-ROC, and training time metrics. The results showed that the XGBoost algorithm achieved the best performance with an accuracy of 0.8621, an F1 Macro score of 0.85, and an AUC value of 0.91. LightGBM produced performance close to XGBoost while providing faster training time. The implementation of SMOTE successfully improved minority class classification performance across all algorithms, particularly in terms of F1-score. The findings indicate that the combination of boosting algorithms and class imbalance handling techniques is effective for machine learning-based academic performance prediction systems.

A Recommendation System for College Majors for High School Students Using a Hybrid Random Forest and K-Nearest Neighbors Method Based on Alumni Profiles

Dzaky Abdur Razaq — 2026-06-02

Choosing a higher education field of study remains a challenge for senior high school students because decisions are often influenced by personal assumptions, social environment, and study trends without measurable academic and interest-based mapping. This study developed a field-of-study recommendation model based on alumni profiles using a Hybrid Random Forest and K-Nearest Neighbors approach. The dataset consisted of 2,440 records, 16 variables, and eight field-of-study categories. The research stages included data collection, data curation, preprocessing, 80:20 data splitting, Random Forest and K-Nearest Neighbors model training, probability fusion with weights of 0.6 and 0.4, and evaluation using confusion matrix, accuracy, precision, recall, and F1-score. The results showed that the hybrid model achieved the best performance with an accuracy of 98.77%, precision of 0.99, recall of 0.99, and F1-score of 0.99. This result was higher than Random Forest with an accuracy of 98.36% and K-Nearest Neighbors with an accuracy of 96.31%. Feature importance analysis indicated that interest-related variables contributed the most to the recommendation process. These findings show that the hybrid model can be used as a basis for developing a web-based field-of-study recommendation system.

Optimizing the Search for the Nearest Coffee Shop Using the Haversine Algorithm in a Mobile Recommendation System

Muhammad Abiyaca Alma'aarij — 2026-06-02

This study aims to optimize the search for nearby coffee shops using the Haversine algorithm in a mobile recommendation system based on Location-Based Filtering (LBF). The system was developed by utilizing GPS, OpenStreetMap, and Firebase to provide real-time coffee shop recommendations according to the user’s location. The research methodology consisted of problem identification, coffee shop location data collection, implementation of the Haversine algorithm for geographic distance calculation, application of the Location-Based Filtering method to sort recommendations based on the nearest distance, and system evaluation using User Acceptance Testing (UAT) and distance accuracy comparison with Google Maps. The results showed that the system was able to calculate location distances with an average accuracy rate of 98.86% compared to Google Maps, with a distance difference ranging only from 0.03 to 0.05 km. In addition, the system successfully provided fast and relevant coffee shop recommendations based on the user’s real-time location. These findings indicate that the combination of the Haversine algorithm and Location-Based Filtering method is effective for implementation in a mobile-based coffee shop recommendation system to improve location search efficiency in real time.

Development of an Indonesian NLP-Based ESG Media Intelligence System Using TF-IDF and IndoBERT

Lukman Hakim Moeslich — 2026-06-03

Monitoring Environmental, Social, and Governance (ESG) issues in Indonesia’s nickel mining industry has become increasingly important due to growing demands for transparency and sustainability. However, automated ESG media analysis for Indonesian-language news remains limited. This study aims to develop an ESG media intelligence system based on Natural Language Processing (NLP) to analyze media perception toward PT Indonesia Weda Bay Industrial Park (IWIP) and PT Weda Bay Nickel (WBN). The proposed system employs an eight-stage pipeline consisting of automated news collection, Indonesian text preprocessing, ontology-based ESG labeling, text classification using TF-IDF + LinearSVC and IndoBERT, as well as sentiment and ESG risk trend analysis. A total of 1,693 news articles published between January 2020 and May 2026 were collected, with 1,320 articles successfully labeled using an ontology-based weak supervision approach. Experimental results show that the best TF-IDF configuration achieved a Macro-F1 score of 0.7693, while IndoBERT achieved 0.7698. The findings indicate that TF-IDF remains competitive with transformer-based models on limited Indonesian ESG datasets. Media analysis revealed that IWIP received predominantly negative media perception on environmental and social issues, while WBN showed relatively more positive governance-related coverage. This research contributes to the development of Indonesian-language ESG media intelligence for the mining industry.

Integration of Role-Based Access Control and First-In, First-Out in an Android-Based Point-of-Sale System to Optimize Transaction and Inventory Management for Small and Medium-Sized Automotive Repair Shops

Lilo Puji Pratama — 2026-06-03

This study aims to develop an Android-based Point of Sales (POS) system to improve transaction and inventory management in automotive repair shop SMEs. The main problem identified was that transaction recording and inventory management were still performed manually, resulting in delays and inventory data inconsistencies. The research employed the Waterfall method, which includes requirement analysis, system design, implementation, testing, and system evaluation stages. The system was developed using Kotlin and Firebase Realtime Database by implementing Role-Based Access Control (RBAC) for user access security and the First In First Out (FIFO) method for inventory management. System evaluation was conducted using black-box testing, System Usability Scale (SUS), operational efficiency analysis, and security testing. The results showed that all system features functioned properly. Usability evaluation involving 40 respondents through Google Forms obtained an SUS score of 82.5%, categorized as “Excellent.” The system also improved operational efficiency by reducing transaction recording time by 80% and increasing item search speed by 83% compared to the manual method. The implementation of RBAC and FIFO successfully improved access security and inventory management consistency in automotive repair shop SMEs.

A Comparison of FTK Imager and MOBILedit Forensic Express Pro in Instagram Cyberbullying Investigations Using the ACPO Framework

Anisa Nur Hidayah — 2026-06-05

Cyberbullying is one of the most common forms of cybercrime occurring on social media platforms, including Instagram through the Direct Message (DM) feature. This study aims to conduct a digital forensic investigation of Cyberbullying cases on Instagram using the Association of Chief Police Officers (ACPO) framework and to compare the performance of FTK Imager and MOBILedit Forensic Express Pro in obtaining digital evidence from Android devices. The research method was carried out through the stages of plan, capture, analysis, and presentation based on the ACPO framework. The investigation process included data acquisition, data extraction, digital artifact recovery, and digital evidence integrity validation using MD5 and SHA1 hashing methods. The results showed that FTK Imager successfully recovered text messages and voice messages with a recovery success rate of 50%, while MOBILedit Forensic Express Pro successfully recovered photos and videos with a recovery success rate of 50%. The integrity validation results indicated that the digital evidence remained valid and unchanged throughout the investigation process. Based on the comparison results, both tools demonstrated different capabilities in recovering specific digital artifacts. Therefore, the combined use of FTK Imager and MOBILedit Forensic Express Pro can improve the effectiveness of digital forensic investigations and provide more comprehensive digital evidence in Cyberbullying cases on Instagram.

A Comparison of FTK Imager and Autopsy in Investigating Telegram Cyberbullying Using the DFRWS Framework

Arinaa Manaasika — 2026-06-05

This study aims to investigate cyberbullying cases on the Telegram application using the Digital Forensic Research Workshop (DFRWS) framework by comparing the performance of FTK Imager and Autopsy forensic tools. The investigation process consisted of identification, preservation, collection, examination, analysis, and presentation stages to obtain digital evidence from Android devices. The results showed that FTK Imager successfully recovered text chats, voice notes, and metadata with a 100% success rate for text-based artifacts, but failed to recover multimedia files such as photos and videos. Meanwhile, Autopsy successfully recovered chats, photos, videos, metadata, and deleted files with a 100% success rate for multimedia artifacts and deleted file recovery. Overall, FTK Imager achieved a digital evidence recovery rate of 58.3%, while Autopsy achieved 83.3%. Digital evidence integrity validation using MD5 and SHA1 hashing produced identical hash values before and after the investigation process, indicating that the integrity and authenticity of the evidence were successfully maintained. The findings demonstrate that the combined use of FTK Imager and Autopsy provides a more effective, systematic, and comprehensive digital forensic investigation process for handling cyberbullying cases on Telegram.

Implementation of the VASignature Fashion Brand E-Commerce Platform Using Laravel and Midtrans, with a Usability Evaluation Using the USE Questionnaire

imam — 2026-06-10

The rapid development of information technology has encouraged businesses to transform conventional sales processes into digital-based systems to improve operational efficiency and service quality. VASignature, a local fashion brand, faces challenges in managing product data, sales transactions, and reporting processes due to the use of manual procedures. This study aims to implement an e-commerce system based on the Laravel framework integrated with the Midtrans Payment Gateway to support a more structured and automated sales process. The system was developed using the Software Development Life Cycle (SDLC) Waterfall model, which consists of requirements analysis, system design, implementation, testing, and evaluation stages. System testing was conducted using Black-box Testing to evaluate functional performance and the USE Questionnaire to assess usability based on four dimensions: Usefulness, Ease of Use, Ease of Learning, and Satisfaction. The results indicate that the developed system was successfully implemented, with all Black-box Testing scenarios achieving a 100% success rate. The usability evaluation produced scores of 88.40% for Usefulness, 90.13% for Ease of Use, 91.20% for Ease of Learning, and 89.47% for Satisfaction, resulting in an overall average score of 89.80%, which falls into the excellent category. These findings demonstrate that the proposed system not only functions effectively from a technical perspective but also provides a positive user experience and high user acceptance. Therefore, the developed e-commerce system is considered suitable for supporting digital sales operations and business management at VASignature.