Article Per Year (5 Year)
p-Index From 2021 - 2026
5.004
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) ComEngApp : Computer Engineering and Applications Journal Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Bulletin of Electrical Engineering and Informatics Jurnal sistem informasi, Teknologi informasi dan komputer Jurnal Informatika dan Teknik Elektro Terapan ICON-CSE Khazanah Informatika: Jurnal Ilmu Komputer dan Informatika Sinkron : Jurnal dan Penelitian Teknik Informatika JURNAL MEDIA INFORMATIKA BUDIDARMA Dinamisia: Jurnal Pengabdian Kepada Masyarakat International Journal of New Media Technology INTECOMS: Journal of Information Technology and Computer Science Jurnal Linguistik Komputasional Journal of Information Systems and Informatics Indonesian Journal of Electrical Engineering and Computer Science JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Journal of Intelligent Computing and Health Informatics (JICHI) Sriwijaya Journal of Informatics and Applications Jurnal Generic Jurnal Altifani Penelitian dan Pengabdian kepada Masyarakat Malcom: Indonesian Journal of Machine Learning and Computer Science Jurnal Pengabdian Kolaborasi dan Inovasi IPTEKS JuTISI (Jurnal Teknik Informatika dan Sistem Informasi)
Abdiansah, Abdiansah
Universitas Sriwijaya
Religion Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Library & Information Science Mathematics Medicine & Pharmacology Nursing Public Health Social Sciences Other

Published : 38 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 38 Documents
Search

 1   2   3   4 
Analisis Perbandingan Klasifikasi Intent Chatbot Menggunakan Deep Learning BERT, RoBERTa, dan IndoBERT Dwiyono, Aswin; Abdiansah, Abdiansah; Fachrurrozi, Muhammad
Journal of Information System Research (JOSH) Vol 6 No 1 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i1.6051

Abstract

A chatbot is a software application to designed handle user inputs and generate appropriate replies based on those inputs, which are then communicated back to the user. In able to provide accurate responses, the chatbot must be able to understand the intent of the user accurately. An issue in the development of chatbots is how to accurate classify user intent. Incorrectly understanding user intent can result in irrelevant responses. In order to have a conversation with the user, the intent of the user needs to be classified correctly. This paper compares three state-of-the-art transformer-based models BERT (Bidirectional Encoder Representations from Transformers), RoBERTa (Robustly Optimized BERT Pretraining Approach), and IndoBERT (Indonesia Bidirectional Encoder Representations from Transformer) for the task of intent classification in chatbot systems. Various performance metrics, including accuracy, F1-score, precision, and recall, were analyzed to determine which model performs more effectively in the same parameter conditions. Performance metrics like accuracy and F1-score were compared to assess model BERT, RoBERTa and IndoBERT performs better in a University Chatbot Dataset in Indonesian language. The BERT model achieved an accuracy of 0.89, RoBERTa model achieved 0.84 and IndoBERT model achieved an accuracy of 0.94. The better performance of IndoBERT compared to BERT and RoBERTa is caused by more language-specific training, more relevant pretraining, and more effective adaptation to Indonesian context and structure.
Prediksi Gender Berdasarkan Nama Bahasa Indonesia Menggunakan Long Short Term Memory Arya Mulya Kusuma; Harisatul Aulia; Muhammad Alfaris Oktavian; Muhammad Rizky Akbar; Putri Patricia; Abdiansah Abdiansah
Jurnal Teknik Informatika dan Sistem Informasi Vol 9 No 2 (2023): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v9i2.6404

Abstract

Gender prediction is a form of prediction programme that outputs a gender type. In the research conducted in this case study, we used input in the form of text names of Indonesian people. Nowadays, there are many names of people that sometimes sound quite ambiguous and make us confused whether this person is MEN or WOMEN. From this case study we are looking for ways to use the Long short term memory method to predict and classify the names of Indonesian people to find out their gender based only on the name with the aim of improving science and looking for new innovations to support future research. The research limitations are the names used are Indonesian names because the dataset used is a dataset of Indonesian names and also the gender we classify is only 2 types of gender, namely MEN and WOMEN. The accuracy comparison of the training results of the baseline programme and the modified programme is the accuracy for the baseline programme of around 0.93, while the accuracy for the modified programme is around 0.90. The results showed an increase in accuracy after experimenting with testing data on the modified programme, which was 0.96.
ANALISIS KOMPARATIF BILSTM DAN BIGRU DENGAN WORD EMBEDDING GLOVE TERHADAP SENTIMEN PUBLIK TENTANG COVID-19 DI TWITTER Yudoyono, Vellanindhita Noorprameswari; Maulana, Jimmy; Alfath, Ahmad Riyo; Melati, Risma; Sihaloho, Mutiara Anastasya; Abdiansah, Abdiansah
Jurnal Informatika dan Teknik Elektro Terapan Vol. 13 No. 3 (2025)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v13i3.6588

Abstract

Pandemi COVID-19 telah memicu perdebatan publik di Twitter, yang dapat dijelaskan melalui analisis sentimen menggunakan pemrosesan bahasa alami. Karakter informal dan tak terstruktur cuitan Twitter menjadi tantangan tersendiri. Penelitian ini membandingkan kinerja arsitektur BiLSTM dan BiGRU dalam mengklasifikasikan sentimen publik terkait COVID-19. Model BiGRU dirancang dengan dua lapisan, disertai dengan implementasi GloVe embedding Twitter.27B.200d untuk representasi kata lebih baik dan dilengkapi dengan dilengkapi dropout, batch normalization, dan regularisasi L2, serta dioptimasi dengan AdamW, sedangkan BiLSTM menggunakan satu lapis standar. Hasil eksperimen menunjukkan BiGRU dua lapis mencapai validasi akurasi 86.78% dengan pelatihan yang lebih stabil dibandingkan BiLSTM 84.91% yang cenderung overfitting. Temuan ini mengindikasikan bahwa arsitektur double layer BiGRU lebih efektif memahami konteks dari cuitan yang tidak terstruktur Twitter, sehingga direkomendasikan untuk sistem analisis sentimen publik dan pengembangan pemrosesan bahasa alami di masa depan.
Improving the transfer learning for batik besurek textile motif classification Marissa Utami; Utami, Marissa; Ermatita, Ermatita; Abdiansah, Abdiansah
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 4: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i4.pp3172-3181

Abstract

This proposed research discussion is a new combination model for classifying batik besurek fabric from the implementation transfer learning with mixed contrast enhancement, activation function, and optimizer method. The size of the batik besurek fabric motif image as an input image is 250×250 with three channels consisting of red, green, and blue totaling five classes, namely kaligrafi, rafflesia, burung kuau, relung paku and rembulan. All images in the dataset will be divided into train data (1540 images), validate data (380 images), and test data (480 images) that are taken directly from the batik store in Bengkulu. The division method used is stratified random sampling to take all the data, shuffles it, and divides the data sets for each class. Based on the experiment results, ResNet50 obtained the best performance compared to MobileNetV2, InceptionV3, and VGG16, with a training accuracy of 99.60%, a validation accuracy of 97.44%, and a testing accuracy of 98.12%. In the improvement experiment phase, the ResNet50 model with Adam optimizer, rectified linear unit (ReLU) activation function and contrast limited adaptive histogram equalization (CLAHE) as the contrast enhancement method obtained the highest test accuracy (98.75%), showing that CLAHE was very effective in improving performance on batik besurek data.
Handwritten Kaganga script classification using deep learning and image fusion Dwika Putra, Erwin; Ermatita, Ermatita; Abdiansah, Abdiansah
Bulletin of Electrical Engineering and Informatics Vol 14, No 2: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i2.8747

Abstract

Classification of traditional handwriting script and to preserve many cultures have been developed in some parts of the world, including image classification of handwriting Kaganga script. This study aims to propose a new combination model by implementing top-hat transform (THT) and contrast-limited adaptive histogram equalization (CLAHE) with discrete wavelet transform (DWT) to support the performance of the convolutional neural network (CNN) in Kaganga script classification. The top-hat transform and contrast-limited adaptive histogram equalization with discrete wavelet transform Fusion L2 convolutional neural network (DWT-THCL L2 CNN) models get the best accuracy from the CNN with L1 regularization, CNN with dropout regularization, CNN with L2 regularization and CNN with L2 regularization and CLAHE models. Based on the experimental results, the DWT-THCL L2 CNN model successfully increased training accuracy by 7.76%, validation accuracy by 5.11%, and testing accuracy by 3.73% from the CNN L1 model. The DWT-THCL L2 CNN model received a training accuracy of 99.87%, validation accuracy of 82.61%, and testing accuracy of 82.61%, while the CNN model with L1 regularization (L1 CNN) only received a training accuracy of 92.11%, validation accuracy of 77.50%, and testing accuracy of 78.88%.
Pengembangan Sistem Informasi Penomoran Surat Berbasis Web untuk Digitalisasi Administrasi Kelurahan Plaju Darat Bayu Wijaya Putra; Lulu Usni Dwi Putri; Nabila Nabila; Aprillia Syafitri; Ezanovia Ezanovia; Yesinta Florensia; Muhammad Ali Buchari; Hasnan Afif; Rusdi Efendi; Dewi Sartika; Anna Dwi Marjusalinah; Sri Turatmiyah; Abdiansah Abdiansah; Karen Nazzua Putri Pratami
Jurnal Altifani Penelitian dan Pengabdian kepada Masyarakat Vol. 6 No. 2 (2026): Maret 2026 - Jurnal Altifani Penelitian dan Pengabdian kepada Masyarakat
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/altifani.v6i2.1028

Abstract

Pengelolaan surat di Kelurahan Plaju Darat sebelumnya masih manual sehingga sering terjadi ketidakteraturan penomoran, keterlambatan pencarian arsip, dan rendahnya akurasi administrasi. Kegiatan pengabdian ini bertujuan menerapkan Sistem Informasi Penomoran Surat berbasis web untuk meningkatkan efisiensi dan akuntabilitas pelayanan. Pendekatan Participatory Action Research (PAR) digunakan melalui tahapan identifikasi masalah, analisis kebutuhan, pengembangan sistem, pengujian, pelatihan, dan evaluasi. Sistem dikembangkan menggunakan CodeIgniter dan MySQL, kemudian diuji dengan Black Box Testing serta User Acceptance Testing. Hasil pre-test menunjukkan rata-rata nilai 51 dan meningkat menjadi 86,13 pada post-test, atau peningkatan 68,88% setelah pelatihan. Evaluasi kepuasan pengguna menunjukkan skor sangat baik, berada pada rentang 4,35–4,65, dengan nilai tertinggi pada efisiensi pencarian arsip dan akurasi penomoran otomatis. Program ini berhasil meningkatkan kompetensi aparatur dan efektivitas administrasi, serta mendukung transformasi digital kelurahan.
LoTQA: Local Benchmarking of Large Language Models for Table Question Answering Muhammad Arya All Fajri; Muhammad Ikhsan Rizki Pratama; Firdaus Firdaus; Abdiansah Abdiansah
Computer Engineering and Applications Journal Vol. 15 No. 2 (2026)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/comengapp.v15i2.1350

Abstract

TableQA memainkan peran penting dalam mendukung pengambilan keputusan berbasis data dan meningkatkan efisiensi pencarian informasi. Penggunaan Large Language Models (LLM) melalui layanan cloud atau API eksternal memungkinkan sistem untuk secara otomatis memahami struktur tabel dan konteks pertanyaan, melakukan generalisasi, penalaran kontekstual, dan memahami hubungan semantik antar entitas dalam tabel untuk menghasilkan jawaban yang lebih relevan dan akurat. Pendekatan ini mengakibatkan peningkatan signifikan dalam biaya komputasi, potensi risiko keamanan data, dan keterbatasan dalam pengembangan, kustomisasi, dan pengujian model. Penelitian ini mengusulkan LoTQA untuk tugas TableQA. LoTQA adalah pendekatan yang memanfaatkan eksekusi lokal untuk mengevaluasi dan membandingkan metode LLM dalam menghasilkan jawaban dari data tabel terstruktur. Evaluasi kinerja pada LoTQA (Qwen3:4b, LoRA Fine-tuned) memperoleh nilai SacreBLUE sebesar 8,613, BLEU-1 sebesar 35,623, BLEU-2 sebesar 26,592, BLEU-3 sebesar 22,723, ROUGE-1 sebesar 0,364, ROUGE-2 sebesar 0,177, ROUGE-L sebesar 0,311, dan METEOR sebesar 0,317. Hasil ini menunjukkan bahwa metode LoTQA cukup baik dalam menyediakan kalimat yang bermakna secara semantik untuk prediksi, bahkan dengan sumber daya yang rendah. Hasil evaluasi kinerja untuk setiap model LLM yang digunakan menunjukkan bahwa model Qwen3:4b mencapai skor tertinggi untuk SacreBLEU, ROUGE-1, ROUGE-2, ROUGE-L, dan METEOR. Studi ini menunjukkan bahwa LoTQA berkinerja cukup baik pada tugas TableQA, meskipun dengan sumber daya yang rendah.
Sentiment Analysis of E-Commerce Mobile Application Reviews for Digital Product Development Insights Balqis, Rugaiyah; Ermatita, Ermatita; Abdiansah, Abdiansah
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 3 (2026): MALCOM July 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i3.3045

Abstract

This paper presents a systematic sentiment analysis framework for Indonesian-language e-commerce reviews, designed for scalable extraction of insights for digital product development. The system applies a Support Vector Machine (SVM) classifier with a Radial Basis Function (RBF) kernel and TF-IDF bigram feature extraction to the PRDECT-ID dataset comprising 5,400 product reviews from Tokopedia across 29 categories. To ensure reliable classification under realistic class conditions, the proposed pipeline integrates multi-stage text preprocessing (case folding, slang normalization, stopword removal, and Sastrawi-based stemming) and stratified 80:20 train-test splitting without artificial resampling. The experimental evaluation confirmed a test-set accuracy of 92.04%, a weighted F1-score of 0.92, and an AUC-ROC of 0.9741. These results validate the efficacy of the proposed SVM-TF-IDF architecture for reliable, interpretable sentiment classification. Furthermore, category-level negative sentiment profiling identifies Computers and Laptops, Automotive, and Toys and Hobbies as priority intervention domains (negative rate ?60%), while keyword-level TF-IDF analysis reveals critical user concerns regarding delivery services, product specification mismatches, and quality disappointment, providing tangible guidance for product development teams. Future work should explore transformer-based architectures (BERT, IndoBERT) for contextual sentiment capture, investigate cross-marketplace generalizability, and address real-time deployment scalability.
Co-Authors Abidullah, M. Dzawil Fadhol Adi Kurniawan Ahmad Fali Oklilas Ahmad Gustano Aidil Putrasyah Al Farissi Alfath, Ahmad Riyo Ali Ibrahim Alvi Syahrini Utami Amalia, Syavira Anna Dwi Marjusalinah Anny K. Sari Aprillia Syafitri Ari Firdaus Ari Wedhasmara Arrasyid, Muhammad Raihan Aruda, Syechky Al Qodrin Arya Mulya Kusuma Astero Nandito Audytra, Hastie Azzahra, Firna Fatima Balqis, Rugaiyah Bayu Wijaya Putra Buchari, Muhammad Ali Dahlan, Bulan Fitri Dewi Sartika Dian Palupi Rini Dian Palupi Rini Dian Palupi Rini Dwiyono, Aswin Edi Winarko Elza Fitriana Saraswita Elza Fitriana Saraswita Ermatita - Erwin, Erwin Ezanovia Ezanovia Fathan, Fathir Fathoni - Febrian, Evan Firdaus Firdaus Frendredi Muliawan Hallatu, Nathania Calista Harisatul Aulia Hasnan Afif Hidayahni, Putri Julian Supardi Kanda Januar Miraswan Karen Nazzua Putri Pratami Kusuma, Arya Mulya Lulu Usni Dwi Putri Marcellino, Fernanditho Marissa Utami Mastura Diana Marieska Maulana, Jimmy Megah Mulya Melati, Risma Mira Afrina Muhammad Alfaris Oktavian Muhammad Arya All Fajri Muhammad Fachrurrozi Muhammad Ikhsan Rizki Pratama Muhammad Qurhanul Rizqie Muhammad Rizky Akbar Muwafa, Fadhil Zahran Nabila Nabila Noprisson, Handrie Novi Yusliani Novran, Novran Plakasa, Gerald Primanita, Anggina Putra, Erwin Dwika Putri Patricia Rabani, Diaz Dafa Ridho Putra Sufa Rizka Dhini Kurnia Rusdi Efendi Saputra, Danny Mathew Saputra, Danny Matthew Satrio, Bagus Sihaloho, Mutiara Anastasya Siti Annisa, Siti Soraya, Atika Sri Hartati Sri Turatmiyah Yadi Utama Yesinta Florensia Yudoyono, Vellanindhita Noorprameswari Zanzabili, Muhammad Reyhan