cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
M. Miftach Fakhri
Contact Email
fakhri@unm.ac.id
Phone
+6282191045293
Journal Mail Official
irwansyahsuwahyu@unm.ac.id
Editorial Address
Kampus UNM Parangtambung, Jl. Daeng Tata Raya, Makassar, Sulawesi Selatan, Indonesia
Location
Kota makassar,
Sulawesi selatan
INDONESIA
Information Technology Education Journal
Published by Universitas Negeri Makassar
ISSN : 28097971     EISSN : 2809798X     DOI : -
Core Subject : Science, Education,
Computer Science & IT Education
INTEC Journal is published by the Informatics and Computer Engineering Education Study Program at Makassar State University. INTEC Journal is published periodically three times a year, containing articles on research results and / or critical studies in the field of Informatics and Computer Engineering Education from students, lecturers, and practitioners from universities or research institutions. The INTEC journal already has a print version ISSN with the number 2809-798X in 2022 and an online version ISSN with the number 2809-7971. INTEC Journal contains articles on informatics and computer engineering education in particular: learning multimedia e-learning/blended learning, information system, artificial intelligence and robotics, embedded expert system, big data and machine learning, software and network engineering
Arjuna Subject : Ilmu Sosial - Pendidikan
Articles 317 Documents
 28   29   30   31   32 
Designing Microservices for Small-Scale E-Commerce Systems: An Empirically Evaluated Domain-Driven Refactoring Approach Using Event-Driven Architecture Arina Manasikana; Lukman; Muh Faisal; Emil Agusalim Habi Talib; Muhammad Syafaat S. Kuba; Muhyiddin A.M Hayat; Andi Agung
Information Technology Education Journal Vol. 5, No. 4, November (2026)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/intec.v5i4.13430

Abstract

Purpose: This study proposes a practical, domain-driven design (DDD)-based refactoring approach to guide small-scale e-commerce systems transitioning from a monolithic to an event-driven microservices architecture. Design/methodology/approach – The research combines an applied case study with a controlled experimental evaluation using k6 load testing under a low-traffic, single virtual user scenario. The approach is built around clearly identified bounded contexts, a database-per-service pattern, independently deployable services, and asynchronous communication via Apache Kafka. Structural maintainability was assessed using a Change Impact Scope (CIS) metric, while latency and deployment time were measured for the monolithic baseline and refactored architecture, centred on the Order and Payment services. Findings: The refactored architecture reduced the estimated change impact scope from 100% to 50%, indicating a narrower potential scope of change. Under low-traffic conditions, the microservices architecture showed modestly higher latency than the monolithic baseline, at 10.81 ms against 9.21 ms for the order operation, converging at the 95th percentile, while the initial deployment time differed by more than an order of magnitude. Therefore, maintainability gains are not automatically accompanied by better performance or lower operational costs at low concurrency. Research limitations/implications – The evaluation covered only Order and Payment under a single-user load; fault isolation and reliability were not measured and remain open for future work under concurrent workloads. Originality/value – Unlike most literature, which focuses on enterprise-scale or cloud-native environments and assumes uniform performance gains, this study reports both the structural benefits and performance trade-offs of a DDD-based migration in a small-scale case study.
Clean Accuracy Versus Robustness: Rank Shifts in CNN and Vision Transformer Document Classifiers Asrul Azhari Muin; Izmy Alwiah Musdar
Information Technology Education Journal Vol. 5, No. 4, November (2026)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/intec.v5i4.13950

Abstract

Purpose – Archival systems select document classifiers from clean-accuracy tables; however, repositories receive scans that are blurred, noisy, compressed, skewed, and unevenly lit. Whether document-specific pre-training buys robustness as well as clean accuracy is untested: no study has compared convolutional networks, generic vision transformers, and document-specific transformers under one graded corruption protocol on all 16 RVL-CDIP classes. Design/methods/approach – ResNet-50, EfficientNet-B0, ViT-Base, and DiT-Base were fine-tuned on a balanced RVL-CDIP subset under an identical protocol, with only the learning rate tuned per architecture family, and then evaluated across nine archival corruptions at five severities. Retention is reported beside absolute drop, a 0.75 clean-accuracy gate confined the comparison to competent systems, and McNemar’s test supplied significance. Findings: All four cleared the gate (clean accuracy 0.7956–0.8706), yet the rankings diverged. DiT-Base was most accurate on clean input, while ViT-Base was most robust, retaining 0.9478 against 0.8673 and shedding 0.0430 accuracy points against 0.1155. Both ends of the reversal were significant (p = 5.30 × 10−8 clean; p = 4.99 × 10−108 under severe blur). Illumination and blur drove the gap; a supporting SHA-256 Merkle layer flagged every simulated tamper. Research implications/limitations – The findings rest on a single seed, a subsampled training set, and simulated rather than genuinely scanned degradation; therefore, the ranking describes the configuration evaluated here rather than the architecture families in general. Originality/value – The study answers an architecture-level question that earlier work could not reach: clean accuracy is an unsafe sole criterion for selecting classifiers in archival systems.
Beyond Flip Rate: A Multi-Criteria Comparative Benchmark of Counterfactual Explanation Methods for Indonesian Text Classification Farida Yusuf; Firmansyah Ibrahim
Information Technology Education Journal Vol. 5, No. 4, November (2026)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/intec.v5i4.13987

Abstract

Purpose – A counterfactual explanation for Indonesian text classification must simultaneously flip the classifier’s decision, remain a minimal and fluent edit, and preserve content that has no bearing on the label. This study asks whether a more powerful generator yields a better Indonesian counterfactual and benchmarks five generators under a single multi-criteria framework. Design/methods/approach – Five generators, a masked-language substitution baseline, two zero-shot LLM pipelines, a gradient-guided variant, and a second-family LLM, were evaluated on two Indonesian test sets across validity, edit quality, format compliance, and cost, combined into a single composite index, and tested for statistical significance. Findings: The masked-language baseline is the strongest and cheapest generator, leading on both flip rate and composite quality while running approximately 55 to 198 times faster than the LLM pipelines. The LLM pipelines are competitive on edit quality but not on validity, and the second-family model degenerates on roughly two-thirds of its outputs, a failure that a flip-rate-only evaluation would have masked. Research implications/limitations: For practitioners building trustworthy AI systems, the practical implication is that a cheaper, simpler generator can be a safer choice, and that generator selection should rest on multi-axis, cost-aware evidence rather than on flip rate or model size alone. All axes here are automated proxies evaluated on two tasks without human judgement. Originality/value – To the best of our knowledge, this study presents the first multicriteria counterfactual benchmark for Indonesian text classification, showing that generator size is a poor proxy for explanation quality and offering a reusable, cost-aware protocol for selecting trustworthy counterfactual methods in lower-resourced languages.
Fine-Tuning IndoBERT for Detecting AI-Generated Indonesian Text to Support Academic Integrity Fajar Irham Hakim; Khothibul Umam; Wenty Dwi Yuniarti
Information Technology Education Journal Vol. 5, No. 4, November (2026)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/intec.v5i4.14451

Abstract

Purpose: This study develops and evaluates a fine-tuned IndoBERT model for detecting ChatGPT-generated Indonesian text, addressing the gap left by AI-generated text detection systems built primarily for English. Design/methodology/approach – The M4 Indonesian dataset (5,774 samples after preprocessing, group-split by article source identifier into 4,619 training, 577 validation, and 578 test samples to keep matched human-written and ChatGPT-generated pairs from leaking across partitions) was used as the basis of this study. A fixed 1,000-sample subset of the training partition was used to fine-tune IndoBERT for binary text classification using PyTorch and Hugging Face Transformers (learning rate 2e-5, three epochs, AdamW) and to train the support vector machine and Naïve Bayes benchmarks under identical conditions. Performance was evaluated on the full 578-sample test set using accuracy, precision, recall and F1-score. Findings: On 578 held-out test samples, IndoBERT reached 95.85% accuracy, 92.57% precision, 100% recall, and an F1-score of 0.9614 (macro F1 = 0.9582), against 97.06% for SVM and 93.08% for Naive Bayes. An exact McNemar's test found no statistically significant difference between IndoBERT and SVM (p = .324), indicating that IndoBERT's advantage under an earlier, non-grouped split largely reflected data leakage rather than a genuine architectural advantage. Research implications/limitations – The dataset is limited to the news domain and to text generated by a single model (ChatGPT); generalisation to academic text, such as student essays, and to outputs from other LLMs, such as Gemini or LLaMA, requires further validation. Originality/value – This study demonstrates that language-specific fine-tuning of IndoBERT can support academic integrity efforts in Indonesia, offering a practical and reproducible detection pipeline that can be adapted and further validated to identify ChatGPT-generated text in educational settings.
From Sentiment to Pedagogical Insight: Comparing SVM, Random Forest, and Multi-Task IndoBERT for Joint Sentiment–Theme Classification of Indonesian Student Feedback Sri Mujiyono; Ucta Pradema Sanjaya
Information Technology Education Journal Vol. 5, No. 4, November (2026)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/intec.v5i4.14666

Abstract

Purpose – Student feedback in Indonesian higher education is a rich pedagogical resource that stays underused. Sentiment analysis under controlled conditions has rarely reached the Indonesian academic domain. This study compares three classification approaches on student feedback: Support Vector Machine, Random Forest, and IndoBERT.  Design/methods/approach – Unlike earlier work that splits sentiment and theme into two independent pipelines, we design a multi-task IndoBERT with one shared encoder and two classification heads, so that sentiment and instructional dimension are predicted jointly for the same response. We also build a preprocessing pipeline tuned to Indonesian academic discourse, with slang normalization and domain-specific stop-word filtering. Experiments run on a corpus of 800 annotated responses drawn from four study programs across three disciplinary clusters. Findings – Under repeated stratified 5-fold cross-validation, multi-task IndoBERT reached a mean sentiment accuracy of 77.9%, against SVM (72.8%) and Random Forest (70.1%); on the held-out test set its thematic macro F1 was 0.757. On the same test set, McNemar's test placed IndoBERT significantly ahead of both baselines at the 0.05 level (p = 0.008 against SVM and p = 0.012 against Random Forest); only the margin over SVM also clears the stricter 0.01 threshold.  Three thematic dimensions emerged: Instructional Clarity, Assessment Design, and Technological Access. Research implications/limitations – The joint model provides actionable insights for NLP research and targeted faculty development. However, the single-institution scope constrains cross-institutional generalization. Originality/value – The pedagogical contribution lies in that joint output: instead of reporting that feedback is negative, the model identifies which dimension of teaching the negativity concerns, so faculty-development programs can target where dissatisfaction actually concentrates rather than act on an aggregate satisfaction score.
Marker-Based Augmented Reality Learning Media for Introducing Professions and Occupational Tools to Elementary Students Haida Dafitri; Kalvin Chiuluto; Muhammad Irwan Padli Nasution
Information Technology Education Journal Vol. 5, No. 4, November (2026)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/intec.v5i4.14750

Abstract

Purpose: This study aimed to develop and preliminarily evaluate a marker-based augmented reality (AR) learning medium for introducing professions and occupational tools to elementary school students. Design/methodology/approach: An Android application was developed using Unity and Vuforia Engine following the six stages of the Multimedia Development Life Cycle (MDLC). The application presents three professions (doctor, police officer, and chef) and six occupational tools through three-dimensional (3D) objects, text, and audio narration. Black Box Testing was used to assess 14 application functions, each tested once. Marker detection was evaluated at distances of 10–80 cm using a 7 × 7 cm printed marker and a Samsung Galaxy S9 running Android 10, with three trials per distance. A descriptive questionnaire was completed by 40 respondents (20 teachers and 20 parents) after an application demonstration. Findings: All 14 tested functions produced their expected outputs. Marker detection succeeded in all trials at distances of 10–60 cm, in two of three trials at 70 cm, and in one of three trials at 80 cm. Teachers and parents reported positive perceptions across five aspects: ease of use, attractiveness of 3D objects, support for introducing professions and occupational tools, support for understanding occupational-tool functions, and perceived usefulness as a supplementary learning medium. For perceived usefulness, 65% of each respondent group selected Strongly Agree and 35% selected Agree. Research implications/limitations: The application may serve as a supplementary resource for teacher-guided observation and classroom discussion. However, the evaluation was limited to one device configuration and preliminary stakeholder perceptions. Respondents evaluated the application after a demonstration, the questionnaire was not formally validated, and students’ learning outcomes were not measured. Therefore, the study does not establish educational effectiveness. Future research should involve students directly, assess learning outcomes, and test the application across devices and environmental conditions.
Development and Preliminary Testing of a Moodle-Based Virtual Programming Laboratory for Programming Practice at Universitas Terbuka Dimas Agung Prasetyo; Fitria Amastini
Information Technology Education Journal Vol. 5, No. 4, November (2026)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/intec.v5i4.15325

Abstract

Purpose – This study aims to describe the development and preliminary testing of a Moodle-based Virtual Programming Lab (VPL) prototype designed to support programming practice in the undergraduate Information Systems program at Universitas Terbuka, Indonesia. Design/methods/approach – The study documents the configuration, implementation, and preliminary testing of a Moodle VPL prototype for two courses: Web-Based Programming and Data Structures. The prototype integrates browser-based code editing, program execution, and submission facilities. Two types of practical activities were developed: constructing source code from problem descriptions and identifying and correcting errors in existing programs. Preliminary testing involved 12 Information Systems students in Surabaya. Findings – The prototype provided a programming practice environment integrated with Moodle. Preliminary observations indicated that students could generally operate the VPL environment, although not all programming challenges were completed. The findings document initial operability and implementation requirements rather than measurable improvements in programming performance. Research implications/limitations – The study offers practical considerations for integrating programming laboratories into distance education. However, the limited preliminary trial and the absence of operational classroom testing restrict conclusions about learning effectiveness and scalability. Further evaluation is required to examine exercise difficulty, assessment procedures, server capacity, and operational costs. Originality/value – This study contributes a context-specific implementation of Moodle VPL that combines code-construction and debugging activities within an open and distance-learning environment. It identifies instructional and operational considerations for preparing programming practice before wider implementation.

Page 32 of 32 | Total Record : 317

 28   29   30   31   32 

Filter by Year

2022 2026


Reset
Filter By Issues
All Issue Vol. 5, No. 4, November (2026) Vol. 5, No. 3, August (2026) Vol. 5, No. 2, May (2026) Vol. 5, No. 1, February (2026) Vol. 4, No. 4, November (2025) Vol. 4, No. 3, August (2025) Vol. 4, No. 2, May (2025) Vol. 4, No. 1, February (2025) Vol. 3, No. 3, September (2024) Vol. 3, No. 2, Mei (2024) Vol. 3, No. 1, Januari (2024) Vol. 2, No. 3, September (2023) Volume 2, Issue 2, Mei 2023 Volume 2, Issue 1, Januari 2023 Volume 1, Issue 3, September 2022 Volume 1, Issue 2, Mei 2022 Volume 1, Issue 1, Januari 2022 More Issue