cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
edukomputika@mail.unnes.ac.id
Phone
-
Journal Mail Official
edukomputika@mail.unnes.ac.id
Editorial Address
Sekaran, Kec. Gn. Pati, Kota Semarang, Jawa Tengah 50229
Location
Kota semarang,
Jawa tengah
INDONESIA
Edu Komputika Journal
Published by Universitas Negeri Semarang
ISSN : -     EISSN : 2599297X     DOI : https://doi.org/10.15294/edukom
Core Subject : Education,
Education
Edu Komputika Journal uses Open Journal Systems (OJS) for online journal management in submission, review, copyediting, and publication. Submitted manuscripts are written in English and should follow the style of the Edu Komputika Journal. Manuscripts are original research results, or theoretical/literature study results that have never been published in other journals or are not considered for publication elsewhere. The author should follow all the provisions and processes. Accepted papers will be available online and will be charged a publication fee.
Arjuna Subject : Ilmu Sosial - Pendidikan
Articles 38 Documents
 1   2   3   4 
A Modified TAM-ECT Model for Evaluating User Satisfaction and Behavioral Intention in Community-Based Internet Services Khairul Imtihan; Ahmad Tantoni; Mardi
Edu Komputika Journal Vol. 12 No. 1 (2025): Edu Komputika Journal
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/edukom.v12i1.24142

Abstract

This study develops and validates a modified Technology Acceptance Model–Expectation Confirmation Theory (TAM-ECT) framework to evaluate user satisfaction and behavioral intention in the context of community-based internet services (RT/RW Net). Unlike prior TAM-ECT studies predominantly conducted in commercial ISP or e-service environments, this research explicitly focuses on decentralized, community-managed internet services characterized by informal governance structures, low switching barriers, and non-contractual user relationships. Addressing the lack of research on decentralized internet service models, this study integrates external factors service quality, cost-effectiveness, system quality, and customer support and moderating factors, namely digital literacy and switching cost. A quantitative survey approach was employed, collecting valid responses from 803 active users between January and March 2025. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) and Importance-Performance Map Analysis (IPMA). The results demonstrate that perceived ease of use strongly influences perceived usefulness and behavioral intention, while perceived usefulness significantly impacts both user satisfaction and behavioral intention. Notably, and contrary to the core assumption of Expectation Confirmation Theory, user satisfaction does not significantly predict behavioral intention, indicating a context-specific deviation in community-based digital services where pragmatic usability considerations outweigh affective satisfaction. External factors such as customer support and system quality significantly affect user perceptions, highlighting the importance of technical performance and user experience in decentralized service settings. Digital literacy positively moderates the relationship between perceived ease of use and behavioral intention. The IPMA findings reveal that ease of use, service usefulness, and customer support are the most critical areas for improvement. Theoretically, this study extends TAM-ECT by demonstrating that continuance intention in community-based internet services is driven more by usability and functional value than by satisfaction-driven confirmation mechanisms commonly observed in commercial platforms. This study offers practical insights for optimizing technical quality, service functionality, and user digital competencies to foster sustainable adoption in community-managed internet infrastructures.
Integration of Skyline Query with the PROMETHEE MCDM Method: A Case Study on Structural Official Selection Budiman Wijaya; Heri Wijayanto; Ida Bagus Ketut Widiartha
Edu Komputika Journal Vol. 12 No. 1 (2025): Edu Komputika Journal
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/edukom.v12i1.29049

Abstract

The selection of structural officials within higher education institutions is a strategic and complex process that demands objectivity, transparency, and a data-driven approach. However, the increasing number of candidates and the diversity of evaluation criteria, such as years of service, rank, education, age, and performance, pose significant challenges in ensuring fair and efficient decision-making. Addressing this gap, this study proposes a hybrid method by integrating Skyline Query with the Preference Ranking Organization Method for Enrichment Evaluations (PROMETHEE), offering a novel contribution to multi-criteria decision-making (MCDM) in public sector human resource selection. Skyline Query is employed as a preselection mechanism to eliminate 161 dominated candidates from an initial dataset of 228, allowing only the 67 most non-dominated candidates to advance to the ranking stage. PROMETHEE is then applied to generate rankings based on leaving and entering flow values. To evaluate the consistency and validity of this combined approach, the resulting rankings are compared with those from the pure PROMETHEE method using Spearman’s Rank Correlation. The analysis yields a high correlation coefficient of ρ = 0.967, indicating a very strong agreement between the two methods and confirming that the Skyline filtering does not distort ranking quality. The findings demonstrate that the Skyline+PROMETHEE integration significantly enhances the efficiency of the selection process by reducing computational complexity while preserving decision accuracy. Moreover, this approach strengthens the transparency and accountability of structural official selection, particularly in the context of the University of Mataram, and can be generalized to other institutional decision-making scenarios.
Weakly Supervised Sentiment Analysis of Indonesian Rural Tourism Reviews: A TF-IDF Baseline for Melung Tourism Village Zanuar Rifa’i; Bayu Priya Mukti
Edu Komputika Journal Vol. 12 No. 1 (2025): Edu Komputika Journal
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/edukom.v12i1.31893

Abstract

This study investigates sentiment classification of Indonesian-language tourist reviews from the rural destination of Melung Tourism Village. A total of 724 user-generated reviews from 546 unique users are preprocessed using Indonesian-specific text cleaning, stopword filtering, and stemming, then weakly labeled through a stemmed positive–negative lexicon. TF-IDF unigram–bigram features are extracted from the preprocessed texts and used to train three classical classifiers: Naive Bayes, linear Support Vector Machine (SVM), and Logistic Regression. To address class imbalance, RandomOverSampler is applied only to the training data, and model evaluation combines stratified 5-fold cross-validation with a held-out test set, using weighted F1-score as the primary metric. Logistic Regression achieves the best performance on the test set (weighted F1 = 0.8799, accuracy = 0.8828), closely followed by SVM, while Naive Bayes lags behind. The results show that, even with a modest, weakly supervised dataset, a carefully designed classical pipeline can yield reliable sentiment indicators to support data-driven management of rural tourism destinations.
Energy Supply Chain Optimization: Design of a Transportation Vendor Assessment System Using the Simple Additive Weighting Method Rendy Bagus Pratama; Ragil Nurhawanti
Edu Komputika Journal Vol. 12 No. 1 (2025): Edu Komputika Journal
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/edukom.v12i1.36054

Abstract

In the energy logistics sector, which demands high speed and efficiency, fuel transportation vendor selection is a strategic decision that significantly impacts operational smoothness. To transform the cumbersome manual selection process into digital precision, a study developed a Vendor Management Information System based on the Simple Additive Weighting (SAW) method. This system is designed to provide objective decision-making support by analyzing 2024 performance data through eight key evaluation criteria, including service quality, price, and fleet availability. After going through a normalization and weighting process in the decision matrix, the system determined Vendor A1 (PT. X) as the best provider with the highest score. The data is descriptive quantitative in nature, where the data collection process involved respondents from three departments within the company who are experts in the field of procurement, with proof of ownership of procurement certification for goods and services. A total of 23 respondents served as the basis for SAW data processing, and 5 people served as references for creating criteria for weighting in the method. This automation logic was then technically mapped through Data Flow Diagrams (DFDs) and Entity-Relationship Diagrams (ERDs) to ensure an integrated workflow. The implementation of this system marks a significant shift towards digital efficiency, which not only minimizes human error and increases transparency but also lays a strong foundation for the adoption of more sophisticated decision-making technologies in the future.
Development of Interactive Mobile Learning Based on Problem-Based Learning for Computational Thinking Material in High School Wahyu Nur Hidayat; Ellvina Pramitadewi Pramitadewi; Rahmana Ilmi Hakim; Fauziyatur Rohmah; Aldhy Sigma Lintang Pamungkas; Heri Cahyono; Moh. Asrori; Warsono Warsono; Dzulkifli Abdullah
Edu Komputika Journal Vol. 12 No. 1 (2025): Edu Komputika Journal
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/edukom.v12i1.22449

Abstract

This research was motivated by students’ low interest and motivation in learning computational thinking. Computational thinking material is still presented in the form of theory and is not based on case studies so that students find it difficult to understand its implementation in everyday life. This study aimed to develop KompuThink, a Problem-Based Learning (PBL)-based mobile learning application for computational thinking instruction. Research and Development using the ADDIE model, through the stages of analysis, design, development, implementation, and evaluation.  The research subjects were 35 class X students of SMA Negeri 6 Malang who were taking informatics subjects. Data were collected using expert validation questionnaires and user testing instruments and analyzed using descriptive quantitative methods. The results showed that media expert validation yielded an average feasibility score of 88% and material expert validation yielded 86%, both categorized as very feasible. Classroom trials resulted in an average student acceptance score of 92.27%, also categorized as very feasible. The novelty of this study lies in the development and feasibility evaluation of a PBL-based mobile learning application that explicitly targets core computational thinking topics (searching, sorting, stack, and queue) within the Indonesian high school context, a combination that has been rarely addressed in previous studies. These findings indicate that KompuThink is a highly feasible and well-accepted interactive mobile learning medium for computational thinking and can serve as a reference for future research and development in informatics education technology.
Integrating SERVQUAL and TAM to Evaluate Service Quality and User Acceptance of a Government Website Baiq Shilla Aryoningsih; Khairul Imtihan; Mardi
Edu Komputika Journal Vol. 12 No. 1 (2025): Edu Komputika Journal
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/edukom.v12i1.23814

Abstract

This study aims to evaluate the service quality and user acceptance of a government website by integrating the SERVQUAL model and the Technology Acceptance Model (TAM). The study addresses the limited empirical evaluation of regional government websites, particularly in capturing both service-oriented and technology-based user perceptions. A quantitative approach was employed using a structured questionnaire distributed to 569 respondents who had used the Satpol PP website of Central Lombok Regency. The data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) combined with Importance–Performance Map Analysis (IPMA). The results indicate that assurance and reliability significantly influence perceived usefulness and perceived ease of use, which in turn affect user satisfaction and behavioral intention. The dimensions of tangibles and empathy showed weaker influence, highlighting the importance of system functionality over aesthetic or emotional design elements. The IPMA findings identify perceived ease of use and assurance as strategic priorities for improvement due to their high importance and moderate performance. This study provides contextual and methodological insights by applying an integrated SERVQUAL, TAM, IPMA framework to evaluate a local government law-enforcement website in Indonesia, a setting that has been rarely examined in prior digital service quality studies. Practically, it offers actionable recommendations for enhancing user trust, system usability, and service responsiveness in digital public platforms. These insights are expected to support the broader agenda of inclusive and sustainable digital governance at the local government level.
Multisensor Integration in Early Fire and Gas Detection Based on Artificial Neural Network Khoirudin Fathoni; Alfa Faridh Suni; Nur iksan; Mohammad Sofyan Aziz
Edu Komputika Journal Vol. 12 No. 2 (2025): Edu Komputika Journal
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/edukom.v12i2.27436

Abstract

Fire detection systems commonly rely on a single variable, such as smoke or flame, to detect fires. However, using a single sensor or threshold-based method for early detection is prone to false alarms. To address this issue, this study proposes an early fire detection system using an artificial neural network based on the Radial Basis Function Network (RBFN) architecture. The aim of this research is to minimize false alarms by implementing an early fire detection system that not only detects flames but also hazardous gases, temperature, and humidity as potential sources of fire. A multisensor system comprising an IR flame sensor, gas sensors MQ-9, MQ-2, and MQ-4, as well as a DHT-11 temperature and humidity sensor, was integrated and processed using an RBFN-based ANN on a Raspberry Pi 3. The ANN processes a series of datasets trained to generate a model that determines fire conditions. Testing results showed that the proposed method did not produce any false alarms, with a response time of 2.1 seconds from the ignition of a fire source to the issuance of a warning.
Performance Evaluation of Machine Learning Methods for Real-Time Rainfall Classification Rahmi Hidayati; Kartika Sari
Edu Komputika Journal Vol. 12 No. 1 (2025): Edu Komputika Journal
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/edukom.v12i1.29322

Abstract

Reliable real-time rainfall intensity classification is essential for supporting early warning systems and disaster mitigation, particularly in regions vulnerable to hydrometeorological hazards. This study evaluates three machine learning algorithms SVM, Neural Network, and AdaBoost for multiclass rainfall intensity classification using real-time data collected from Internet of Things (IoT)-based sensors. Rainfall intensity is categorized into four classes: no rain, light rain, moderate rain, and heavy rain, based on threshold values defined by BMKG standards. The dataset is imbalanced and dominated by the no rain class, therefore, model performance is evaluated using imbalance aware metrics, including per-class precision and recall, macro F1-score, balanced accuracy, and overall accuracy. Experimental results show that SVM and Neural Network achieve very high overall accuracy of up to 99.46%, however, this performance is mainly influenced by accurate classification of the majority class, leading to low recall for minority rainfall classes. In contrast, AdaBoost provides a more balanced baseline performance, achieving an accuracy of 92.4% and a macro F1-score of 0.714 on the original dataset. To enhance minority class detection, the SMOTE is applied to the training data using an 80:20 train test split. After data balancing, AdaBoost demonstrates improved recall and macro F1-score for light and moderate rain classes, although overall accuracy decreases to 77.1%. These results are acceptable for early warning applications, where sensitivity to rainfall onset is prioritized over majority class dominance. Consequently, balanced AdaBoost, evaluated using time-based data partitioning and imbalance aware metrics, is considered an effective approach for real-time IoT-based rainfall classification.
Comparison of Machine Learning and Deep Learning Algorithms for Daily Retail Sales Forecasting Eko Purwanto; Bangun Prajadi Cipto Utomo; Hanifah Permatasari; Farahwahida Mohd
Edu Komputika Journal Vol. 12 No. 2 (2025): Edu Komputika Journal
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/edukom.v12i2.32773

Abstract

This study presents a comparative analysis of four machine learning (ML) and deep learning (DL) algorithms: Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) for predicting daily retail sales time series. The models were evaluated using key metrics, such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R²). Results show that RF and SVM outperformed both CNN and LSTM in terms of MAE (3500.28 and 3325.11, respectively) and RMSE (4660.60 and 4293.42, respectively). However, all models had negative R² values, indicating none could explain the variation in the data. LSTM, in particular, was the least efficient model, with an MAE of 54087.25, RMSE of 54257.51, and R² of -158.59. The poor performance of LSTM can be attributed to overfitting, improper model configuration, and misalignment with the nature of the data. The dataset used includes over 1,000 daily retail sales transaction records collected over one year, with key attributes like CustomerID, ProductID, Quantity, Price, TransactionDate, PaymentMethod, StoreLocation, ProductCategory, DiscountApplied, and TotalAmount. While the dataset is representative, its size and complexity may not have been sufficient for deep learning models like LSTM and CNN, which generally require larger datasets for optimal performance. This study highlights the challenges of using deep learning for retail forecasting and suggests future research should focus on refining models and incorporating external datasets to improve prediction accuracy.
Assessing Generative AI with Context-Augmented Zero-Shot Prompting for HOTS Question Generation Aligned with Bloom’s Taxonomy Saiful Ridlo; Ahmad Sehabuddin; Syahroni Hidayat; Taofan Ali Achmadi; Uswatun Hasanah; Indah Indi Afifah; Haikal Abror
Edu Komputika Journal Vol. 12 No. 2 (2025): Edu Komputika Journal
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/edukom.v12i2.34437

Abstract

This study investigates the use of HOTS-GenAI, a generative AI system employing context-augmented zero-shot prompting, to automatically generate multiple-choice questions aligned with higher-order thinking skills (HOTS) in Bloom’s taxonomy.  A dataset of 200 items for vocational high schools was validated by three experts. The ground truth data demonstrated good quality with an inter-rater reliability of 0.75 (Gregory’s Index). System performance across analysis (C4), evaluation (C5), and creation (C6) levels was evaluated using Content Validity Index (CVI), gap analysis, and confusion-matrix-based metrics. The findings revealed that HOTS-GenAI performed relatively well at the analytical level, where 70% of items met the HOTS threshold, supported by higher expert consensus. However, only 10% of items achieved the threshold for evaluation, and none for creation. CVI results indicated moderate validity overall, with stronger agreement for C4 than for C5 or C6. Confusion matrix analysis further confirmed this imbalance: accuracy and F1-scores were highest for analysis items but dropped sharply for evaluation and creation, where recall and precision were near zero. These results suggest that while HOTS-GenAI has potential in generating analytical questions, its capacity to model evaluative and creative tasks remains underdeveloped. Future research should involve larger datasets, refined prompt design, and more operational rubrics to enhance both validity and reliability in AI-generated HOTS assessments.

Page 3 of 4 | Total Record : 38

 1   2   3   4 

Filter by Year

2024 2025


Reset
Filter By Issues
All Issue Vol. 12 No. 2 (2025): Edu Komputika Journal Vol. 12 No. 1 (2025): Edu Komputika Journal Vol. 11 No. 2 (2024): Edu Komputika Journal Vol. 11 No. 1 (2024): Edu Komputika Journal