Article Per Year (5 Year)
p-Index From 2021 - 2026
0.702
P-Index
This Author published in this journals
All Journal Teika METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Indonesian Journal of Educational Development (IJED) Journal of Artificial Intelligence and Engineering Applications (JAIEA)
Sumarlin
STIKOM Uyelindo Kupang
Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Languange, Linguistic, Communication & Media

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Klasifikasi Judul Berita Online Menggunakan BERT dan IndoBERT Diorrani Katemba; Franki Bisilisin; Heni; Sumarlin
TeIKa Vol 16 No 1 (2026): Jurnal TeIKa
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/3sqzca39

Abstract

Perkembangan berita online di wilayah Nusa Tenggara Timur (NTT) semakin pesat. Meningkatnya volume berita yang dipublikasikan setiap hari menimbulkan tantangan dalam proses pengelompokan dan analisis konten yang selama ini masih dilakukan secara manual. Oleh karena itu, diperlukan suatu sistem yang mampu mengklasifikasikan judul berita secara otomatis dan akurat agar pengelolaan informasi dapat dilakukan dengan lebih efisien. Penelitian ini menggunakan pendekatan berbasis deep learning dengan menerapkan model Bidirectional Encoder Representations from Transformers (BERT) dan IndoBERT sebagai teknologi utama dalam sistem klasifikasi berita online berbahasa Indonesia. Bahasa pemrograman yang digunakan adalah Python dengan dukungan pustaka transformers. Dataset yang digunakan dikumpulkan melalui teknik web scraping dari beberapa portal berita lokal di wilayah NTT, kemudian dibagi menjadi 80% data latih dan 20% data uji untuk mengukur performa model. Model BERT dan IndoBERT diterapkan untuk mengenali konteks serta makna semantik dari setiap judul berita guna menghasilkan representasi teks yang lebih bermakna. Hasil pengujian menunjukkan bahwa model dasar BERT mencapai tingkat akurasi sebesar 69%, dengan nilai precision 70,2%, dan recall 66,9%. Sementara itu, penerapan model IndoBERT memperoleh performa yang lebih tinggi dengan tingkat akurasi mencapai 80%, nilai precision 78,2%, dan recall 79%. Kesimpulannya, pemanfaatan model IndoBERT terbukti secara signifikan lebih akurat dan optimal dibandingkan BERT dalam melakukan klasifikasi teks judul berita lokal NTT.
Prediction of Clean Water Quality Using K-Nearest Neighbor (KNN) and Naïve Bayes at PDAM Kupang City Haliim Wila Supardi; Sumarlin
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 2 (2026): February 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i2.1892

Abstract

Kupang City faces significant challenges in providing clean water due to its dry geographical conditions and extreme climate. Although it has various potential water sources such as watersheds and bore wells, clean water distribution remains suboptimal. This study aims to predict clean water quality using two machine learning algorithms, namely K-Nearest Neighbor (KNN) and Naïve Bayes, based on the Water Quality Dataset which includes parameters such as pH, hardness, total dissolved solids, and turbidity. The process involves data preprocessing, algorithm implementation, and model evaluation using classification metrics. The KNN model achieved an accuracy of 56%, with an F1-score of 0.67 for the “unsafe” class and 0.36 for the “safe” class. Meanwhile, the Naïve Bayes model achieved a higher overall accuracy of 61% but failed to detect the “safe” class, showing a precision and recall of 0.00. Overall, KNN performed more balanced across classes despite its moderate accuracy, while Naïve Bayes was biased toward the majority class. These findings highlight the importance of selecting appropriate algorithms and tuning parameters for water quality prediction. The implementation of predictive models is expected to assist PDAM Kupang in making data-driven decisions to improve clean water management sustainably.
Web-based knowledge sharing in Indonesian higher education to enhance students’ and lecturers’ knowledge capacity Dewi Anggraini; Sumarlin
Indonesian Journal of Educational Development (IJED) Vol. 7 No. 2 (2026): August 2026
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) Universitas PGRI Mahadewa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59672/ijed.v7i2.6671

Abstract

This research aims to develop and evaluate a web-based knowledge sharing model designed to increase the knowledge capacity of students and lecturers. Effective knowledge sharing is essential to support collaborative learning and improve access to information in academic environments. The study employed the Research and Development (R&D) method with the ADDIE model to design and evaluate a platform integrating a content management system (CMS), discussion forums, a question and answer feature, and project collaboration spaces, while analyzing user interaction data to identify usage patterns and content preferences. Results show that the platform successfully increased user engagement, expanded access to information, and strengthened connections between students and lecturers. Functionality testing achieved an 86.7% success rate, system uptime reached 98%, and average user satisfaction was 4.2 out of 5. Expert validation confirmed a "very valid" rating across all dimensions. Paired sample t-test analysis revealed a significant difference between pre-test and post-test scores (Sig. 0.000 < 0.05), with a gain score of 0.56 (medium category). These findings confirm that the model effectively enhances users' knowledge capacity and academic collaboration, and is recommended as a reference for higher education institutions in developing more effective, technology-based collaborative learning strategies.
KLASIFIKASI SURAT MASUK DI KANTOR PENGADILAN MILITER III-15 KUPANG MENGGUNAKAN (LSTM) LONG SHORT TERM-MEMORY Asmawati Tuto; Sumarlin; Yohanis Malelak
METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Vol. 12 No. 2 (2026): Volume 12 Nomor 2 Tahun 2026
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/mtk.v12i2.5924

Abstract

The increasing volume of incoming correspondence at the Kupang Military Court III-15 Office has made the conventional letter classification process complex and time-consuming. Purpose: this study aims to develop an incoming letter classification system that categorizes letters into four classes (regular letters, circulars, decrees, and orders) using the Long Short-Term Memory (LSTM) method; the main contribution of this study is the application of LSTM to a local military-court correspondence dataset that has not been widely studied, together with a replicable preprocessing pipeline and K-Fold evaluation protocol, providing practical implications for accelerating correspondence administration in military judicial offices. Methods: the dataset consists of 500 incoming letter records in Excel format that underwent a preprocessing stage including cleaning, case folding, normalization, stopword removal, stemming, tokenizing, encoding, and padding, and was then divided into 80% training data and 20% testing data, evaluated using 5-Fold Cross Validation with accuracy, precision, recall, and F1-score as performance metrics. Results: the average model performance results were Accuracy 42.04%, Precision 42.39%, Recall 42.04%, and F1-Score 39.93%, with the highest accuracy obtained in Fold 2 (56.44%) and the lowest in Fold 5 (32.00%), while the model's main difficulty lay in distinguishing between the Circular and Decree categories, which share similar text patterns. Conclusion: the LSTM method is capable of recognizing textual patterns in letters and performing classification; however, its performance remains variable and relatively low on this dataset, so the developed system has the potential to improve the efficiency of incoming letter management at the Kupang Military Court III-15 Office, although further optimization is still needed before independent deployment.
Co-Authors Asmawati Tuto Dewi Anggraini Diorrani Katemba Franki Bisilisin Haliim Wila Supardi Heni Yohanis Malelak