cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Agus Tedyyana
Contact Email
agustedyyana@polbeng.ac.id
Phone
+6285289866666
Journal Mail Official
jurnaoinformatika@polbeng.ac.id
Editorial Address
Jl. Bathin alam, Sungai Alam Bengkalis-Riau 28711
Location
Kab. bengkalis,
Riau
INDONESIA
INOVTEK Polbeng - Seri Informatika
Published by Politeknik Negeri Bengkalis
ISSN : 25279866     EISSN : -     DOI : https://doi.org/10.35314
Core Subject : Science,
Computer Science & IT
The Journal of Innovation and Technology (INOVTEK Polbeng—Seri Informatika) is a distinguished publication hosted by the State Polytechnic of Bengkalis. Dedicated to advancing the field of informatics, this scientific research journal serves as a vital platform for academics, researchers, and practitioners to disseminate their insightful findings and theoretical developments. Scope and Focus: INOVTEK Polbeng - Seri Informatika focuses on a broad spectrum of topics within informatics, including but not limited to Web and Mobile Computing, Image Processing, Machine Learning, Artificial Intelligence (AI), Intelligent Systems, Information Systems, Databases, Decision Support Systems (DSS), IT Project Management, Geographic Information Systems, Information Technology, Computer Networks and Security, and Wireless Sensor Networks. By covering such a wide range of subjects, the journal ensures its relevance to a diverse readership interested in both the practical and theoretical aspects of informatics.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 558 Documents
 52   53   54   55   56 
Sentiment Analysis of Indonesia's Economic Acceleration Program 2025 Using Support Vector Machine Kamelia Lestari; Ermatita
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/r2tz5h34

Abstract

Indonesia's Economic Acceleration Program 2025 is a government policy to accelerate national economic growth in response to the global economic slowdown. The implementation of this programme has generated a variety of public responses on social media. This study aims to analyse public sentiment towards the Indonesian Economic Acceleration Program in the launch and implementation phases and identify differences in sentiment distribution in both phases. Data in the form of TikTok comments was collected through web scraping, then processed through preprocessing, lexicon-based sentiment labelling validated using manually labelled samples, TF-IDF feature representation, and classification using the Support Vector Machine. Model evaluation was carried out using 10-fold cross-validation. The results of the study showed that SVM provided superior performance to the comparison model. In the launch phase, SVM achieved an accuracy of 81%, while in the implementation phase it achieved an accuracy of 79.5% with superior performance in all evaluation metrics. The distribution of sentiment in the launch phase was dominated by neutral sentiment by 67.1%, while in the implementation phase the proportion of negative sentiment increased to 46.38%. These results show that there is a difference in the distribution of sentiment between the launch and implementation phases, so that it can be an input in understanding the public's response to the Indonesian Economic Acceleration Program
Implementation Of The Naïve Bayes Method For Skincare Product Recommendations According To Skin Type At Dermakila Clinic Afilda Maharani; Supriyono; Zainur Romadhon
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/krks4h07

Abstract

Advances in information technology have encouraged the implementation of recommendation systems in various fields, including beauty and skincare. Selecting skincare products that are not suitable for an individual's skin type and condition may reduce treatment effectiveness and potentially lead to skin problems. Dermakila Clinic offers a wide range of skincare products with diverse characteristics, creating a need for a system that can assist users in selecting products that best suit their skin needs. This study aims to implement the Naïve Bayes method in developing a skincare product recommendation system based on user characteristics, including age range, gender, skin type, and skin concerns. The research applies a data mining approach using the Naïve Bayes classification algorithm. The dataset consists of 960 skincare product records that have undergone preprocessing and data transformation stages. The system was developed as a web-based application to provide users with fast and accurate product recommendations. The experimental results demonstrate that the Naïve Bayes method achieved an accuracy of 88%, with a precision of 89%, a recall of 88%, and an F1-score of 88%. These findings indicate that the Naïve Bayes method is effective for implementing a skincare product recommendation system at Dermakila Clinic.
Random Forest and LightGBM Comparison for Acute Pain Diagnosis Using SMOTE on an Expert-Labeled Dataset Wayan Andre Pratama; I Made Gede Sunarya; Putu Hendra Suputra
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/x2getn56

Abstract

Limited healthcare personnel may delay early pain assessment and encourage self-medication, increasing medication error risk. However, evidence remains limited regarding whether bagging or boosting is more suitable for multiclass acute pain classification using imbalanced, expert-system-derived symptom data, and whether SMOTE improves performance. This study compared Random Forest as a bagging approach and LightGBM as a boosting approach for classifying nine acute pain diagnostic classes without SMOTE and with SMOTE using k_neighbours=1 and 5. The dataset comprised 2,722 records and 36 discrete symptom features. Of 125 representative symptom combinations reviewed by a medical expert, 115 were considered appropriate; the remaining records were synthetically generated using the same expert-system knowledge base and inference mechanism. Data were divided using stratified 80:20 sampling, while model configuration was evaluated using five-fold cross-validation. SMOTE was applied only to training data within each fold. LightGBM without SMOTE achieved the best performance, with 83.49% accuracy, a macro F1-score of 0.81, and a weighted F1-score of 0.83, compared with 80.18%, 0.77, and 0.80 for Random Forest. With SMOTE, Random Forest achieved 78.35% and 77.61% accuracy, while LightGBM achieved 81.10% and 82.39%. Thus, LightGBM without SMOTE performed best for this dataset. Validation using real clinical data and multiple experts is required.
Customer Lifetime Value Prediction Using Long Short-Term Memory with RFM-T Features Based on E-Commerce Customer Data Sabilla Laili Ramadhani Putri; Anik Vega Vitianingsih; Anastasia Lidya Maukar; Achmad Muzakki; Hewa Majeed Zangana
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/tp5rrp78

Abstract

CLV prediction plays an important role in e-commerce by helping companies identify valuable customers and develop effective retention strategies. However, predicting CLV remains challenging due to the sequential nature of customer purchasing behaviour. This study proposes a CLV prediction model using the LSTM algorithm with Recency, Frequency, Monetary, and Tenure features extracted from the Online Retail II dataset. The CLV target is calculated as the accumulated monetary value generated during the three months following the historical observation period. The proposed approach consists of data preprocessing, monthly RFM-T feature engineering, feature normalisation using min-max scaling, LSTM model training, denormalisation, and performance evaluation using MAE and RMSE. The LSTM model incorporates stacked LSTM layers, batch normalisation, dropout, and L2 regularisation to improve learning stability and generalisation. Experimental results indicate that the model was able to capture customer purchasing patterns based on sequential RFM-T features, with training and validation loss trends showing stable convergence. The proposed model achieved an MAE of 43.16 and an RMSE of 125.39 on the original monetary scale, reflecting the prediction performance obtained on the evaluated dataset. These findings suggest that the proposed LSTM model with RFM-T features provides an approach for CLV prediction in e-commerce.
POS System Success Evaluation at a Civil Servant Cooperative: DeLone-McLean Evidence and Perceived Paperless Environmental Benefits Wayan Hesadijaya Utthavi; Ni Luh Ayu Kartika Yuniastari Sarja; Kadek Nita Sumiari; I Ketut Parnata
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/79fvv418

Abstract

Information system success models define net benefits mainly in economic and operational terms, leaving the environmental implications of digitalization insufficiently addressed. This study evaluated a centralized Point of Sale (POS) system at the Civil Servants’ Cooperative of Politeknik Negeri Bali using the DeLone and McLean model and examined whether perceived paperless environmental benefit could qualify as an additional net-benefit dimension. A mixed-methods evaluative design involved customers (N = 78), tenants (N = 12), and managers (N = 7). Analyses included validity and reliability testing, correlation analysis, robust path analysis, mediation testing, and the Wilcoxon signed-rank test. Of eighteen stakeholder-specific scales, reliability was adequate for customer scales (α = 0.888–0.961) but unstable for tenant and manager scales, with confidence intervals extending to [0.271, 0.952]. Queue management and comfort were significantly associated with customer satisfaction (β = 0.683, p < 0.001; R² = 0.715), while satisfaction was associated with PPEB (β = 0.773, p < 0.001). Mediation evidence was inconclusive: the indirect path was significant under classical standard errors (Sobel z = 2.31) but not under heteroscedasticity-consistent errors (z = 1.59, p = 0.111), while the direct association remained strong. Sales declined after implementation, but differing measurement bases prevented causal interpretation.
Comparison of Hyperparameter Optimization Methods for LSTM-Based XAU/USD Forecasting and Web-Based System Implementation Irsad Nizarudin; Yudie Irawan; Anteng Widodo
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/1vywa204

Abstract

Unequal search budgets and single-seed experiments can confound comparisons of hyperparameter optimisation methods in financial forecasting. This study compares grid search, random search, and Bayesian optimisation for tuning a long short-term memory model to forecast the XAU/USD closing price for the next trading day. The dataset comprised 1,705 daily observations from January 2020 to July 2026 using open, high, low, close, and release-date-aligned United States inflation. Each method evaluated the same 32 configurations using three random seeds, resulting in 96 candidate-model evaluations per method. Performance was assessed on 37 independent testing dates and descriptively examined using a five-fold post-selection walk-forward diagnostic without repeating hyperparameter optimisation within each fold. All methods selected the same configuration and produced a mean testing MAPE of 2.785052% and an ensemble MAPE of 2.696161%. Grid Search reached the final-best configuration earlier, but naïve persistence achieved the lowest MAPE of 1.358325%. Thus, optimisation improved the LSTM relative to the predefined baseline but did not outperform persistence. The procedures were also implemented in a Streamlit application. The findings are limited to the examined dataset, search space, seeds, testing period, and computational environment.
Multi-Platform Healthcare Sentiment Analysis Using Kappa-Validated Lexicon Labelling and SMOTE-Enhanced Naive Bayes Fikri Hamdhan Dwi Saputra; Fajar Nugraha; Zainur Romadhon
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/bn99ce45

Abstract

This study develops an automated sentiment analysis system for classifying reviews of the RSI Sunan Kudus mobile application, collected from Google Play Store, Google Maps, and YouTube (N = 1,428). Sentiment labels were automatically assigned using a domain-adapted Indonesian lexicon (87 positive / 100 negative terms), with label reliability validated against a human-annotated gold-standard subset (n = 100, two annotators; κ = 0.900, almost perfect agreement), yielding 85.71% classifier accuracy against adjudicated labels. After excluding neutral reviews, a binary multinomial Naive Bayes classifier was evaluated via 5-fold stratified cross-validation, achieving 91.01 ± 1.13% accuracy and 89.20 ± 1.48% macro F1-score. Class imbalance (ratio = 2.39:1) was addressed using SMOTE within each training fold in feature-vector space. An ablation study across six model-vectoriser combinations identified LinearSVC with Bag-of-Words as best-performing (Macro F1 = 96.03 ± 1.34%); a preprocessing ablation showed the six-stage normalisation pipeline did not meaningfully improve Macro F1 over simpler variants. Cross-platform transfer experiments revealed substantial generalisation gaps (e.g., Macro F1 dropping from 81.1% to 26.8% for a Google-Maps-trained model applied to YouTube), underscoring the value of multi-platform data collection. Findings indicate three primary service pain points: OTP/login failures, long waiting times, and application connectivity issues.
Performance and User Satisfaction Analysis of Kerobokan Village’s SIPANDU Using IT Balanced Scorecard and EUCS Putu Ade Pranata; Gede Indrawan; I Made Gede Sunarya
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/g3w4mf09

Abstract

Information technology advancements push government agencies to utilise information systems to improve public services. Kerobokan Regional Office has utilised the Complaint Management Information System (SIPANDU) to manage citizen complaints digitally. However, a comprehensive evaluation aligning operational technical performance, organisational contribution, future readiness, and the psychological satisfaction of users has not been conducted. This study evaluates SIPANDU's overall performance and user satisfaction using the integration of the IT Balanced Scorecard (IT BSC) as a macro evaluation framework and End User Computing Satisfaction (EUCS) as a micro instrument focused on the user orientation perspective. This mixed-methods study involved 15 internal end users (village head, secretary, section heads, and neighbourhood heads) selected through saturated sampling. EUCS measures satisfaction based on content, accuracy, format, ease of use, and timeliness. The evaluation results show SIPANDU's performance is highly satisfactory across all IT BSC perspectives with an overall score of 0.918 (91.8%). Corporate Contribution scored 0.900, User Orientation scored 0.964, Operational Excellence scored 0.892, and Future Orientation scored 0.908. User satisfaction measured by EUCS is also very high, averaging 4.82 out of 5. Despite the excellent results, the integration of IT BSC and EUCS revealed gaps primarily in operational excellence and timeliness. Priorities for improvement and the strategic roadmap developed include enhancing system reliability, optimising server performance, and implementing real-time notification features for complaint status updates.  
UI/UX Optimization of an Android-Based Waste Management Application Using Design Thinking and the System Usability Scale Putri Amaliyah; Agung Wibowo
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/wws27k59

Abstract

Community-based waste management increasingly relies on mobile applications, whose success depends heavily on the quality of the user interface (UI) and user experience (UX). This study designed and evaluated the UI/UX of a high-fidelity prototype of the Resikel Android application for the Batam City context using the design thinking methodology (empathise, define, ideate, prototype, test). The contribution is context-specific rather than methodological: it presents a user-centred interface design and its perceived-usability evaluation for a community-based waste-management prototype situated in Batam. Usability was measured through unmoderated, cross-sectional testing on the Maze platform involving 100 respondents, followed by the System Usability Scale (SUS). Task-based metrics (success rate, completion time, and misclicks) were recorded, and the mean SUS score was 78.2 (SD = 6.70), indicating a good level of perceived usability within the Acceptable range. Because the artefact evaluated is a prototype rather than a functioning Android application, technical feasibility, performance, accessibility, and real-world task completion were not established. The findings provide an empirical usability reference for the future development of community-based waste-management applications and should be interpreted within the stated design and sampling limitations.
Implementation of the C4.5 Decision Tree Algorithm in a Decision Support System for Employee Payroll at PT Hesed Paulus Erwin Gulo; Abdul Rohman
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/9dgpf822

Abstract

Payroll management is a critical business process because it directly affects employee compensation and organisational administration. PT Hesed still encounters challenges in payroll verification, including calculation errors, limited visibility of payroll components, and sequential verification procedures. This study implements the C4.5 decision tree algorithm in a web-based payroll decision support system and evaluates both software functionality and classification performance. The study employed a design and creation strategy using qualitative analysis for system requirement identification and quantitative analysis for model evaluation. Historical payroll data consisted of 12 verified records from January to April 2026, with payroll period, attendance, years of service, employment status, and tardiness as predictor attributes and payroll recommendation as the class label. C4.5 attribute selection used entropy, information gain, split information, and gain ratio, while LOOCV evaluated predictive performance. Tardiness achieved the highest gain ratio (1.0000) and became the root node in the full dataset and in every LOOCV fold. LOOCV produced 7 correctly classified Appropriate records and 5 correctly classified Inappropriate records, yielding 100% accuracy, macro-precision, macro-recall, and macro-F1, compared with a 58.33% majority-class baseline accuracy. Black-box testing recorded outputs that matched the specified functions, while logic-level white-box verification reproduced the reference C4.5 calculations. Because the dataset is limited and no processing time, usability, payroll-error reduction, or field-impact study was conducted, these results should be interpreted as evidence of functional conformity and internal classification consistency rather than demonstrated operational efficiency or broad generalisability.

Page 55 of 56 | Total Record : 558

 52   53   54   55   56 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 11 No. 3 (2026): August Vol. 11 No. 2 (2026): May Vol. 11 No. 1 (2026): February Vol. 10 No. 3 (2025): November Vol. 10 No. 2 (2025): July Vol. 10 No. 1 (2025): March Vol. 9 No. 2 (2024): November