cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Salamun
Contact Email
salamun@univrab.ac.id
Phone
-
Journal Mail Official
Jurnal.ti@univrab.com
Editorial Address
Redaktur Jurnal RABIT Teknik Informatika Universitas Abdurrab: Gedung Universitas Abdurrab Pekanbaru Jl. Riau Ujung No. 73 Pekanbaru Riau - Indonesia
Location
Kota pekanbaru,
Riau
INDONESIA
RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
Published by Universitas Abdurrab
ISSN : 24772062     EISSN : 2502891X     DOI : https://doi.org/10.36341/rabit
Core Subject : Science, Engineering,
Computer Science & IT Engineering
This journal is called RABIT, where the name comes from two words namely, RAB which means Abdurrab University and IT which means information technology, it can be interpreted as a journal of this journal Journal of Informatics Engineering Study Program Pekanbaru Abdurrab University. This RABIT journal contains various sciences related to the world of computers especially information technology and information systems, namely, this journal is published twice a year where the initial publication is on January 10 while for the second issue which is on July 10.
Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi
Articles 696 Documents
 33   34   35   36   37 
HYBRID FINE-TUNING INDOBERT DAN ENSEMBLE TF-IDF LOGISTIC REGRESSION UNTUK ANALISIS SENTIMEN ULASAN APLIKASI ZALORA : HYBRID FINE-TUNING INDOBERT DAN ENSEMBLE TF-IDF LOGISTIC REGRESSION UNTUK ANALISIS SENTIMEN ULASAN APLIKASI ZALORA Al Ikhsan Faiq; M. Rudi Sanjaya Sanjaya; Dwi Rosa Indah; Endang Lestari Ruskan
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.6924

Abstract

Sentiment analysis of e-commerce app reviews is essential to capture user perception and guide service improvements. However, review datasets are typically imbalanced—especially for the neutral class—making accuracy-only evaluation inadequate. This study proposes a hybrid approach that combines IndoBERT fine-tuning with a TF–IDF + logistic regression ensemble, augmented with probability calibration via temperature scaling, a dedicated neutral threshold rule, and a rating-based prior for low-confidence predictions. To avoid data leakage, the dataset is first split using stratified sampling into 72% training, 8% validation, and 20% testing; oversampling is applied only on the training split. Training uses label smoothing and early stopping (patience=2). The best validation configuration achieves macro-F1 of 0.8158 (T=0.941; α=0.70; t_neu=0.55; γ=0.10; τ=0.60). On the test set, the proposed model reaches 86.77% accuracy, 81.71% macro-F1, and 86.76% weighted-F1. An ablation study shows consistent gains from the TF–IDF+LR baseline to the full hybrid model, with the most notable improvement in the neutral class.
ANALISIS SENTIMEN ULASAN APLIKASI MOBILE JKN MENGGUNAKAN NAÏVE BAYES, KNN, DAN SVM BERBASIS SMOTE: SENTIMENT ANALYSIS OF JKN MOBILE APPLICATION REVIEWS USING NAÏVE BAYES, KNN, AND SVM BASED ON SMOTE Octa Dwiansyah; Rizka Dhini Kurnia
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.6930

Abstract

Sentiment analysis of user reviews on the Mobile JKN application plays an important role in identifying user satisfaction levels and obstacles encountered when accessing BPJS Kesehatan’s digital services. This study aims to evaluate the performance of three classification algorithms Naïve Bayes, KNN, and SVM optimized using the SMOTE approach to address data imbalance. A total of 19,186 user reviews were used, which underwent preprocessing, TF-IDF weighting, and an 80:20 data split, resulting in 15,348 training data and 3,838 testing data. Each model was evaluated before and after SMOTE application to assess its impact on model performance. The results show that SMOTE improved model sensitivity toward minority classes without significantly reducing accuracy. The Naïve Bayes model achieved 93.56 % accuracy before SMOTE and 92.05 % after, KNN improved from 71.20 % to 87.96 %, while SVM maintained the highest performance with 93 % accuracy and an F1-score of 0.91–0.95. The highest AUC value was obtained by SVM (0.98), followed by Naïve Bayes (0.97) and KNN (0.93). Sentiment classification results revealed that most user reviews were positive, reflecting high satisfaction with the Mobile JKN service, while negative reviews were primarily related to technical issues. Overall, the SMOTE-based SVM model proved to be the most effective algorithm for sentiment analysis and can serve as a foundation for evaluating and improving the quality of BPJS Kesehatan’s digital services.
KLASIFIKASI JENIS JAMUR MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN) BERBASIS CITRA DIGITAL Luluk Elvitaria; Ira Puspita Sari; Lasiah Susanti; Zaerinisya Fitri
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.6933

Abstract

This reserach proposes a mushroom species classification method based on digital image processing using a Convolutional Neural Network (CNN). The EfficientNet-B4 architecture was adopted as the backbone model, employing a transfer learning approach followed by a fine-tuning process. The dataset consisted of 3,000 mushroom images categorized into 10 classes, with each class containing 300 images. The model implementation was carried out using Google Colab and the Python programming language. Model performance was evaluated using accuracy, precision, recall, and F1-Score metrics. Several model variations were examined by adjusting training parameters and data split ratios. The best-performing model, referred to as Model 1, utilized a customized freeze layer and applied an 80% training, 10% validation, and 10% testing data split, achieving the highest performance with 90.00% accuracy, 90.09% precision, 89.63% recall, and an 89.59% F1-Score. The findings indicate that applying a customized freeze layer effectively reduces the number of trainable parameters, leading to improved model accuracy. Furthermore, the selection of data split ratios contributes to performance differences during the training and testing phases.
PENERAPAN METODE TOPSIS PADA SISTEM PENDUKUNG KEPUTUSAN PEMILIHAN VENDOR KLINIK THAMRIN TIGA LIMA MADIUN: APPLICATION OF THE TOPSIS METHOD IN A DECISION SUPPORT SYSTEM FOR VENDOR SELECTION AT THAMRIN TIGA LIMA CLINIC, MADIUN Sandy Irawan; Retnowati Retnowati
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.6934

Abstract

In the era of intense business competition in the healthcare sector, selecting reliable vendors is a crucial foundation for the operational efficiency and service quality of the Thamrin Tiga Lima Clinic Madiun. The main challenge faced is the vendor selection process, which is still manual and subjective, potentially leading to operational risks. This research aims to develop, test, and implement an integrated Decision Support System (DSS) to enhance the objectivity, accuracy, and efficiency of the decision-making process. The research adopts the Agile approach and the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method. TOPSIS was chosen for its ability to handle multi-criteria simultaneously and provide comprehensive ranking results. In this case study, five assessment criteria are used: product quality (C1), price (C2), vendor reputation (C3) and delivery speed (C4). The User Acceptance Test (UAT) results indicate that the system is PASS and ready for implementation, with a user satisfaction level reaching 85.4%. The accuracy of the TOPSIS calculation was also verified at 100%. Based on the case study, the vendor PT. Bina San Prima (V1) ranks first with a preference value of 0,6527. Overall, the developed DSS has proven to be effective in the case study and provides measurable and structured vendor recommendations.
HYBRID WEIGHTED RANDOMIZATION UNTUK DISTRIBUSI PELANGGAN ADIL PADA WEBSITE DEALER OTOMOTIF Alvino Radyo Danisworo; Heru Lestiawan; MY Teguh Sulistyono
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.6935

Abstract

Automotive dealers with large sales teams face challenges in fairly distributing customer prospects. Round-robin methods ignore performance differences, while performance-based allocation causes overload and team demotivation. This study develops a Hybrid Weighted Randomization algorithm integrating fairness score (40%), performance score (40%), time decay (20%), and penalty factor. Design Science Research methodology is employed with evaluation through 9 factorial configurations (5, 10, 20 agents; 100, 500, 1000 assignments) measuring Jain's Fairness Index and Coefficient of Variation. The system is implemented using Python 3.13 with PostgreSQL. Results show 88.9% of configurations achieve Grade A+ (JFI ≥ 0.95). Optimal configuration: 10 agents @ 1000 assignments with JFI=0.9916 (0.84% gap from perfect fairness). Three empirical scaling laws are identified: (1) minimum 25 assignments per agent for Grade A+, (2) optimal agent count ≈ √(N_total/10), (3) improvement rate ∝ 1/n_sales². Linear time complexity O(n·m) with 257ms per assignment confirms production-readiness. The algorithm successfully achieves near-optimal fairness while accommodating performance recognition and temporal factors. Scaling laws provide actionable frameworks for team sizing and capacity planning, with theoretical contributions (novel algorithm) and practical ones (production-ready implementation with clear deployment guidelines).
EVALUASI USER ACCEPTANCE PLATFOR EVALUASI USER ACCEPTANCE PLATFORM TOKOPEDIA MELALUI FRAMEWORK UTAUT3 DAN ANALISIS KEPUTUSAN TOPSIS DENGAN IMPLEMENTASI RSTUDIO Muhammad Ravi Wijayanto Sanjaya; M. Rudi Sanjaya; bayu wijaya putra; Gabriel Ekoputra Hartono Cahyadi; Endang Lestari
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.6938

Abstract

This study aims to evaluate user acceptance of the Tokopedia e-commerce platform in Indonesia by applying the Unified Theory of Acceptance and Use of Technology 3 (UTAUT3) framework combined with the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) analysis implemented in RStudio. Data were collected through an online questionnaire distributed through social networks, generating responses from 200 Indonesian users. Each UTAUT3 construct (Performance Expectancy, Effort Expectancy, Social Influence, Facilitating Conditions, Hedonic Motivation, Price Value, Habit, and Personal Innovativeness) was measured using a five-point Likert scale. The TOPSIS method was then applied to determine the ranking and relative importance of each construct in shaping user acceptance. The results indicate that Effort Expectancy (EE) and Personal Innovativeness (PI) are the most influential factors, reflecting users' appreciation of Tokopedia's ease of use and their openness to adopting the digital platform. Conversely, Habit (HB) showed the lowest score, indicating that routine use is still limited among some users. These findings provide valuable insights for Tokopedia and other digital commerce platforms to improve user engagement and service optimization in Indonesia's rapidly growing online market. The findings of this study suggest that platform development should focus more on promotional programs to improve user habits in using Tokopedia as a primary e-commerce platform.
INTEGRASI EXTREME PROGRAMMING DAN PROTOTYPE DALAM PENGEMBANGAN SISTEM POS ACCOUNTING DENGAN PENGUJIAN BERBASIS ARTIFICIAL INTELLIGENCE: INTEGRATION OF EXTREME PROGRAMMING AND PROTOTYPING IN THE DEVELOPMENT OF A POS ACCOUNTING SYSTEM WITH ARTIFICIAL INTELLIGENCE BASED TESTING Nabela Putri Setiawan; Erba Lutfina; Galuh Wilujeng Saraswati; Resha Meiranadi Caturkusuma
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.6959

Abstract

Advancements in information technology have had a significant impact on various sectors, including the business sector, which requires efficiency and accuracy in data management. Fresh Market Pantai Klatak is one of the companies that requires such improvements, as it still relies on a manual transaction management system, resulting in delays in reporting and errors in calculations. The development of a web-based Point of Sale (POS) Accounting System is expected to support transaction management and financial reporting at Fresh Market Pantai Klatak. The system development employs the Extreme Programming (XP) method combined with the Prototype approach during the planning and design phases to accelerate the development process and better meet user requirements. The integration of Extreme Programming (XP) and Prototype, supported by Artificial Intelligence (AI) during the testing phase, enables the development of a system that is responsive to user needs while improving code quality and user interface through AI-based automated validation. Unit Testing results indicate that the system functions properly with a success rate of 100%. Furthermore, User Acceptance Testing (UAT) results show an average score of 97%, which falls into the “very good” category, indicating that the POS Accounting System meets user requirements. Therefore, the developed POS Accounting System is feasible for use and is expected to improve operational efficiency and the accuracy of financial reporting at Fresh Market Pantai Klatak.
INTEGRASI METODE RAPID APPLICATION DEVELOPMENT (RAD) DAN USER ACCEPTANCE TESTING (UAT) DALAM PENGEMBANGAN SISTEM INFORMASI PEMESANAN DIGITAL PRINTING: INTEGRATION OF RAPID APPLICATION DEVELOPMENT (RAD) AND USER ACCEPTANCE TESTING (UAT) METHODS IN THE DEVELOPMENT OF A DIGITAL PRINTING ORDERING INFORMATION SYSTEM Kenza Amelia Putri Anwarri; Galuh Wilujeng Saraswati; Wildan Mahmud; Erba Lutfina; Resha Meiranadi Caturkusuma
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.6960

Abstract

Advances in information technology have encouraged various business sectors to switch from manual systems to digital systems in order to improve efficiency and service quality. CV. Penanggungan 44, as a digital printing service provider, previously used a manual ordering system, resulting in inefficient transactions and susceptibility to recording errors. This study aims to design and develop a website-based Digital Printing Ordering Information System that can simplify the ordering process and assist in integrated data management. The system was developed using the Rapid Application Development (RAD) method combined with a User-Centered Design (UCD) approach and User Acceptance Testing (UAT) applied iteratively. UAT is not only used as a final testing stage, but also utilized since the interface design stage as a formative evaluation, so that user feedback can be directly integrated into the system design and construction improvement process. This approach ensures that rapid development remains in line with user needs and experiences. Black-box Testing shows that all system features function properly with a 100% success rate. Meanwhile, the User Acceptance Testing (UAT) results obtained an average score of 86.8% in the excellent category, indicating that the system is easy to use and well-received by users. Thus, the developed system is deemed suitable for use in improving operational efficiency and service quality at CV. Penanggungan 44
ANALISIS EVALUASI TINGKAT LITERASI KEAMANAN CYBER PENGGUNAAN MEDIA SOSIAL (STUDI KASUS SISWA SMK BUKIT ASAM) Ikhwan Amalsyah; M. Rudi Sanjaya; Endang Lestari Ruskan; Dwi Rosa Indah
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.6963

Abstract

This study aims to analyze the level of cyber security literacy among students of SMK Bukit Asam and classify it using the Random Forest algorithm. A quantitative approach was employed with a questionnaire covering four key indicators: knowledge, attitude, behavior, and overall cyber security literacy. A total of 192 students participated as respondents. The results show that 53.13% of students fall into the high literacy category, 35.94% into the medium category, and 10.94% into the low category. The Random Forest model achieved an accuracy of 97.44%, with SI2 and SI4 identified as the most influential features. Beyond describing the students’ generally good level of cyber security literacy, the use of Random Forest also provides an important methodological contribution by revealing attitude-related indicators as the main determining factors in the classification. These findings offer a clearer foundation for designing more targeted and effective digital security education programs in schools.
ANALISIS SISTEM PENDUKUNG KEPUTUSAN PENERIMAAN BANTUAN SOSIAL MENGGUNAKAN METODE WEIGHTED PRODUCT Lulu Monica Sari; M. Rudi Sanjaya; Dedy Kurniawan; Dwi Rosa Indah
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.6966

Abstract

Social assistance is one of the government’s efforts to reduce social inequality and achieve social justice for all Indonesian citizens. However, limited budget allocations necessitate the development of an objective selection system to determine eligible recipients. This study aims to apply the Weighted Product (WP) method in analyzing a Decision Support System for determining social assistance recipients in Tanjung Raja Village. Five criteria were used in this study, namely income amount, number of dependents, housing condition, employment status, and asset ownership. The data were obtained through questionnaires that were validated using the Content Validity Index (CVI), yielding a CVI value of 1, which indicates full expert agreement regarding the suitability of the criteria. The results show that the income criterion (C1) has the highest weight of 0.2461, followed by the number of dependents (C2) at 0.1936, employment status (C4) at 0.1907, housing condition (C3) at 0.1897, and asset ownership (C5) with the lowest weight of 0.1797. In the ranking results, alternative A5 obtained the highest vector V value of 0.2076, followed by A3 (0.2061), A4 (0.2024), A1 (0.1931), and A2 (0.1905), indicating that candidate A5 is the most eligible to receive social assistance. The strong validity of the criteria (CVI = 1) and the measurable ranking results demonstrate that the application of the Weighted Product method effectively supports an objective, fast, and accurate decision-making process.

Page 35 of 70 | Total Record : 696

 33   34   35   36   37 

Filter by Year

2016 2026


Reset
Filter By Issues
All Issue Vol 11 No 2 (2026): Juli Vol 11 No 1 (2026): Januari Vol 10 No 2 (2025): Juli Vol 10 No 1 (2025): Januari Vol 9 No 2 (2024): Juli Vol 9 No 1 (2024): Januari Vol 8 No 2 (2023): Juli Vol 8 No 1 (2023): Januari Vol 7 No 2 (2022): Juli Vol 7 No 1 (2022): Januari Vol 6 No 2 (2021): Juli Vol 6 No 1 (2021): Januari Vol 5 No 2 (2020): Juli Vol 5 No 1 (2020): Januari Vol 4 No 2 (2019): Juli Vol 4 No 1 (2019): Januari Vol 3 No 2 (2018): Juli Vol 3 No 2 (2018): Juli Vol 3 No 1 (2018): Januari Vol 3 No 1 (2018): Januari Vol 2 No 2 (2017): Terbitan Ke-4 Bulan Juli 2017 Vol 2 No 2 (2017): Juli 2017 Vol 2 No 1 (2017): Januari 2017 Vol 1 No 2 (2016): Juli 2016 Vol 1 No 1 (2016): Januari 2016 More Issue