Article Per Year (5 Year)
p-Index From 2021 - 2026
8.303
P-Index
This Author published in this journals
All Journal Computatio : Journal of Computer Science and Information Systems JIKO (Jurnal Informatika dan Komputer) JUTIK : Jurnal Teknologi Informasi dan Komputer JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI Jurnal Sisfokom (Sistem Informasi dan Komputer) Jurnal Teknik Informatika UNIKA Santo Thomas JUTIM (Jurnal Teknik Informatika Musirawas) Kurawal - Jurnal Teknologi, Informasi dan Industri Progresif: Jurnal Ilmiah Komputer Jurnal Ilmiah Betrik : Besemah Teknologi Informasi dan Komputer Teknomatika (Jurnal Teknologi dan Informatika) Syntax: Journal of Software Engineering, Computer Science and Information Technology JTECS : Jurnal Sistem Telekomunikasi Elektronika Sistem Kontrol Power Sistem dan Komputer Jurnal Ilmu Komputer dan Informatika Bulletin of Information Technology (BIT) Jurnal Teknik Informatika Unika Santo Thomas (JTIUST) Algoritme Jurnal Mahasiswa Teknik Informatika Informatics and Enginering Dedication Jurnal Teknologi Sistem Informasi Jurnal Nasional Teknik Elektro dan Teknologi Informasi Arcitech: Journal of Computer Science and Artificial Intelligence DEVICE : JOURNAL OF INFORMATION SYSTEM, COMPUTER SCIENCE AND INFORMATION TECHNOLOGY Insand Comtech : Information Science and Computer Technology Journal Buletin Ilmiah Informatika Teknologi JOINTECOMS (Journal of Information Technology and Computer Science) MDP Student Conference Journal of Embedded Systems, Security and Intelligent Systems Software Development Digital Business Intelligence and Computer Engineering Journal Information & Computer (JICOM) Jurnal Software Engineering and Computational Intelligence Computing Insight: Journal of Computer Science Applied Information Technology and Computer Science (AICOMS) JISCOMP (Journal of Information System and Computer) Journal of Informatics and Computer Engineering Research INOVTEK Polbeng - Seri Informatika JuTISI (Jurnal Teknik Informatika dan Sistem Informasi)
Hafiz Irsyad
Universitas Multi Data Palembang
Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Mechanical Engineering Social Sciences Other

Published : 86 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 86 Documents
Search

 5   6   7   8   9 
Analisis Komparatif Pemodelan Topik Promosi Judi Online pada Komentar YouTube Menggunakan Latent Dirichlet Allocation dan BERTopic Nur Aisyah Wahyuni; Hafiz Irsyad
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 6 No. 1 (2026): June 2026
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v6i1.16764

Abstract

This study aims to analyze topics in YouTube comments related to online gambling using Latent Dirichlet Allocation (LDA) and BERTopic, as well as to compare the performance of both methods. The dataset consists of 6,350 YouTube comments obtained from Kaggle. The analysis process includes preprocessing, topic modeling, and evaluation using topic coherence and topic diversity metrics. The results show that LDA achieves a topic coherence score of 0.511 and a topic diversity score of 1.0, while BERTopic achieves a topic coherence score of 0.667 and a topic diversity score of 0.449. These findings indicate that BERTopic produces more semantically coherent topics compared to LDA, although it has a higher level of overlap between topics. Furthermore, the interpretation results reveal that several identified topics are related to online gambling promotion, while others are influenced by noise in the comment data. Therefore, BERTopic is considered more effective for analyzing short and unstructured text data.
Implementation of a Convolutional Neural Network Using VGG19 for Ogan Malay Script Recognition Steven Liem; Hafiz Irsyad
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/annm4j49

Abstract

Regional languages and scripts, including the Melayu Ogan script, face the threat of extinction due to declining usage and limited digital documentation in the modern era. While current Indonesian script research primarily focuses on popular scripts, research addressing the Ogan Malay script remains severely limited. To address this gap, this study provides one of the earliest implementations of the Convolutional Neural Network (CNN) VGG-19 architecture specifically designed for Ogan Malay script classification. This research utilises a primary dataset provided by the Language Center of South Sumatra Province, consisting of 185 distinct character classes, with each class initially containing one original image. The VGG-19 architecture is applied and supported by data augmentation techniques to enrich spatial variability, followed by evaluation using k-fold cross validation. Evaluation results demonstrate excellent classification performance. The model achieved maximum convergence without any indications of overfitting at an optimal configuration of 30 epochs with a learning rate of 0.0001. This configuration successfully resulted in an accuracy of 99.14%, a precision of 0.9870, a recall of 0.9914, and an F1-score of 0.9885. The success of this classification model provides a strong foundation for future real-time regional script recognition applications to support cultural preservation.
KEYWORD EXTRACTION KOMENTAR TERHADAP KONFLIK INDIA-PAKISTAN PADA PLATFORM YOUTUBE MENGGUNAKAN TF-IDF DAN COSINE SIMILARITY Nicholas Edison; Kristian Fernando; Hafiz Irsyad; Abdul Rahman
Syntax : Journal of Software Engineering, Computer Science and Information Technology Vol 6, No 2 (2025): Desember 2025
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/syntax.v6i2.6638

Abstract

Konflik antara India dan Pakistan merupakan isu geopolitik yang sering menjadi perhatian global dan menimbulkan diskusi luas di media sosial, termasuk platform YouTube. Penelitian ini bertujuan untuk mengekstraksi kata kunci dari komentar-komentar pengguna YouTube mengenai topik konflik India-Pakistan, serta menganalisis kemiripan makna seluruh komentar antar video menggunakan metode TF-IDF dan Cosine Similarity. Data diperoleh dari kolom komentar tiga video YouTube yang relevan dan diproses melalui tahapan pra-pemrosesan teks, perhitungan bobot kata menggunakan TF-IDF, serta pengukuran similaritas menggunakan Cosine Similarity. Hasil ekstraksi kata kunci menggunakan TF-IDF menunjukkan terdapat 20 kata kunci dengan frekuensi tertinggi, dengan 3 kata kunci tertinggi adalah “india”, “pakistan” dan “perang”. Hasil perhitungan Cosine Similarity menunjukkan bahwa tingkat kemiripan antar komentar video berkisar antara 0,544 hingga 0,695, dimana nilai similarity tertinggi terdapat pada perbandingan Video 1 dan Video 3 (0,695), Video 1 dan Video 2 (0,653), sementara Video 2 dan Video 3 (0,544). Hasil ini menunjukkan bahwa kombinasi metode ini efektif dalam mengidentifikasi topik dominan serta hubungan semantik antar komentar. Visualisasi kata kunci dengan WordCloud juga memperjelas representasi opini publik yang berkembang. Penelitian ini memberikan kontribusi dalam pemetaan diskursus digital secara kuantitatif dan efisien.
KLASIFIKASI OPINI MASYARAKAT TERHADAP VIDEO DOKUMENTER DIRTY VOTE DENGAN ALGORITMA KNN(K-NEAREST NEIGHBOR) DAN NAÏVE BAYES Jendraja Husein Kotan; Andreas Andreas; Silvi Mutia; Hafiz Irsyad
Syntax : Journal of Software Engineering, Computer Science and Information Technology Vol 5, No 1 (2024): Juni 2024
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/syntax.v5i1.4575

Abstract

Penelitian ini menggabungkan 2 algoritma yaitu algoritma K-Nearest Neighbor (KNN) dan Naïve Bayes dalam mengklasifikasikan opini masyarakat terhadap video dokumenter "Dirty Vote". KNN mengklasifikasikan data berdasarkan kemiripan dengan data yang ada, sementara Naïve Bayes menggunakan pendekatan probabilistik dengan asumsi independensi antar fitur. Tujuan penelitian ini adalah mengevaluasi efektivitas dan akurasi kedua algoritma dalam analisis sentimen. Hasil menunjukkan Naïve Bayes lebih mendapatkan tingkat akurasi sebesar 0.76. Kesimpulannya, Klasifikasi  Opini Masyarakat terhadap Video Dirty Vote dengan menggunakan Algoritma KNN dan Naïve Bayes sangat penting dan bermanfaat untuk meningkatkan edukasi masyarakat mengenai pentingnya integritas pemilu dan mendorong partisipasi aktif dalam proses demokrasi, sehingga memperkuat sistem demokrasi dan memastikan suara masyarakat didengar dalam pengambilan keputusan politik. Kata Kunci— KNN, Naïve Bayes, Sentimen, Dirty Vote. ABSTRACTThis research combines 2 algorithms, namely the K-Nearest Neighbor (KNN) algorithm and Naïve Bayes in classifying public opinion on the documentary video "Dirty Vote". KNN classifies data based on similarity to existing data, while Naïve Bayes uses a probabilistic approach with the assumption of independence between features. The aim of this research is to evaluate the effectiveness and accuracy of the two algorithms in sentiment analysis. The results show that Naïve Bayes has a higher accuracy rate of 0.76. In conclusion, Classification of Public Opinion on Dirty Vote Videos using the KNN and Naïve Bayes Algorithms is very important and useful for increasing public education regarding the importance of election integrity and encouraging active participation in the democratic process, thereby strengthening the democratic system and ensuring that people's voices are heard in political decision making. Keywords— KNN, Naïve Bayes, Sentiment, Dirty Vote.
Relevansi Berita terhadap Kasus Korupsi Dana Iklan Bank BJB Menggunakan TF-IDF dan Cosine Similarity Rizki Ambarwati; Cindy Meilani; Hafiz Irsyad
Journal of Information Technology and Computer Science Vol. 5 No. 2 (2025): JOINTECOMS : Journal of Information Technology and Computer Science
Publisher : Universitas Palangka Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47111/jointecoms.v5i2.21053

Abstract

Kasus korupsi dana iklan Bank BJB menjadi perhatian publik karena menyangkut penyalahgunaan dana yang melibatkan institusi keuangan milik pemerintah daerah. Banyaknya pemberitaan dari berbagai media membuat informasi yang tersebar sulit untuk disaring berdasarkan relevansinya terhadap inti kasus. Penelitian ini bertujuan untuk menganalisis dan mengukur relevansi berita-berita yang beredar terhadap kasus korupsi dana iklan Bank BJB dengan memanfaatkan metode Term Frequency-Inverse Document Frequency (TF-IDF) dan Cosine Similarity. Data yang digunakan berupa kumpulan artikel berita daring dari berbagai sumber media yang membahas topik terkait. Tahapan penelitian dimulai dengan preprocessing teks, seperti pembersihan data, tokenisasi, stopword removal, dan stemming. Dokumen yang memiliki tingkat kemiripan tinggi dianggap relevan terhadap berita acuan utama kasus korupsi ini. Hasil pengujian TF-IDF dan Cosine Similarity menunjukan tingkat accuracy sebesar 71%, precision sebesar 100%, recall 71 % dan hasil F1 score 83 % sehingga dengan metode tersebut dapat mengelompokkan berita secara efektif berdasarkan tingkat relevansinya.
Keyword Extraction Abstrak Jurnal Ilmiah Menggunakan Metode TF-IDF dan KeyBERT Rayvin Suhartoyo; Valen Julyo Armando Davincy Lin; Hafiz Irsyad; Abdul Rahman
Applied Information Technology and Computer Science (AICOMS) Vol 4 No 2 (2025)
Publisher : Pengelola Jurnal Politeknik Negeri Ketapang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58466/aicoms.v4i2.1814

Abstract

Keyword extraction is a significant technique in natural language processing (NLP) that serves to summarize the essence of a document, such as a scientific journal summary. This study aims to analyze the effectiveness of two keyword extraction methods, namely Term Frequency-Inverse Document Frequency (TF-IDF) and KeyBERT, in finding significant keywords from a collection of scientific journal abstracts. The dataset used consists of several scientific journal abstracts accompanied by manual keywords as a basis for assessment. The TF-IDF method relies on the frequency of words in the document, while KeyBERT utilizes a cosine similarity approach based on the BERT transformer model to determine the most meaningful keywords. The research findings show that the KeyBERT method and the TF-IDF method have a moderate level of similarity with semantic similarity values ​​of 0.578 for the KeyBERT method and 0.469 for the TF-IDF method, respectively. These results show significant potential for the use of machine learning and deep learning-based models with both methods for topic classification systems, especially in the fields of information retrieval and text mining.
Opini Publik terhadap Isu Pengoplosan Pertamax di Youtube Menggunakan Metode Naive Bayes Adikara Alif Nurrahman; Earlando Moza; Ramanda Md; Muhamad Rizvi Roshan; Ahmad Rizky; Hafiz Irsyad
Applied Information Technology and Computer Science (AICOMS) Vol 4 No 2 (2025)
Publisher : Pengelola Jurnal Politeknik Negeri Ketapang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58466/aicoms.v4i2.1990

Abstract

This study aims to explore public perceptions regarding the issue of Pertamax fuel adulteration, a topic that has sparked widespread discussion on YouTube, by employing sentiment analysis techniques based on the Naive Bayes algorithm. This issue has attracted significant public attention and become a trending topic on social media, particularly on the YouTube platform. The data analyzed in this research consist of user comments responding to the issue. The Naive Bayes algorithm is used to classify sentiments in the comments into three categories: positive, negative, and neutral. To address the imbalanced distribution of data, the Synthetic Minority Over-sampling Technique (SMOTE) is applied. The results show that before applying SMOTE, the model achieved an accuracy of only 48%, with a precision of 0.48, recall of 0.36, and an F1-score of 0.41 for the negative category, as well as a precision of 0.48, recall of 0.56, and an F1-score of 0.52 for the positive category. After implementing SMOTE, the model's accuracy increased significantly to 88%, with a precision of 0.91, recall of 0.93, and an F1-score of 0.92 for the negative category. For the positive category, precision improved to 0.80, although recall decreased to 0.75, yielding an F1-score of 0.77. The average precision, recall, and F1-score (macro average) after applying SMOTE reached 0.85, 0.84, and 0.85, respectively, representing a substantial improvement compared to the results before SMOTE. This study highlights the importance of using SMOTE to enhance sentiment analysis accuracy, particularly in addressing class imbalance issues within the dataset.
Klasifikasi Kerusakan Uang Rupiah Menggunakan CNN Dengan Arsitektur VGG16 Muhamad Rizvi Roshan; Hafiz Irsyad
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 5 No. 2 (2025): December 2025
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v5i2.15125

Abstract

This study developed a deep learning model using a Convolutional Neural Network (CNN) architecture with VGG16 to classify the level of damage to rupiah banknotes. Previous studies have focused more on recognizing denominations and detecting counterfeit money using CNN and transfer learning, while the classification of physical damage to rupiah banknotes is still limited, both locally and internationally, and often relies on special acquisition devices or template registration. The dataset used consists of images of rupiah banknotes grouped into three damage categories: >20%, >40%, and >50%. This dataset is divided into 80% for training data (537 images) and 20% for test data (135 images). To enrich the data variety, this study applied on-the-fly data augmentation techniques with rotation, zoom, and flipping during the training process. The experimental results show that this model achieves an accuracy of 93.33%, with excellent precision, recall, and F1-score values, especially in the >50% damage category. The use of the ADAM optimizer with a learning rate of 1e-3 proved to provide more stable and efficient training. Overall, this study shows that the application of CNN with the VGG16 architecture is effective in classifying rupiah currency damage and can contribute to the development of image processing technology, particularly for evaluating currency feasibility in real-world scenarios.
Perancangan UI/UX dan Evaluasi Usability Sistem Cerdas Prediksi Titik Api Sumatera Selatan Hotspot Monitor Muhammad Rizky Pribadi; Dedy Hermanto; Hafiz Irsyad
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 4 No 2 (2024): April 2024 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v4i2.17243

Abstract

South Sumatra faces recurring forest and land fires, yet hotspot information remains difficult for lay users to interpret. This study designs and evaluates the user interface (UI/UX) of Sumsel Hotspot Monitor, accommodating a representation of AI-based wildfire hotspot prediction via the Design Thinking method (Empathize, Define, Ideate, Prototype, Test). Interviews with residents, disaster officers, and meteorological operators revealed a need for plain language and color-coded indicators, translated into a map prototype displaying illustrative output from LightGBM (spread probability) and ConvLSTM (movement direction) models, adopted as design references; their training and quantitative validation against real historical data are planned for future research. Usability testing (SUS) with 24 respondents yielded an average score of 78.54 (Grade B+, "Good"), indicating the prototype is acceptable for use. This research bridges AI-based hotspot prediction with user-centered UI/UX design, offering practical recommendations for an accessible mitigation application; empirical validation of the AI component remains necessary before full adoption by disaster agencies.
Pengembangan Model Matematika Penyebaran Api Berbasis Vektor dan Filter Titik Panas Industri untuk Sistem Peringatan Dini Karhutla Muhammad Rizky Pribadi; Dedy Hermanto; Hafiz Irsyad
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 5 No 2 (2025): April 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v5i2.17244

Abstract

Forest and land fires (karhutla) in the tropical peatland ecosystem of South Sumatra pose recurring ecological threats and transboundary haze disasters during every dry season. Existing early warning systems generally rely on satellite hotspot detections without accounting for the direction and rate of fire spread, and remain vulnerable to false alarms caused by persistent industrial heat sources such as refineries, palm oil mill flare stacks, and power plants. This study develops a deterministic, vector-based mathematical model to predict the direction, rate, and hazard-zone geometry of fire spread in near real-time, complemented by a spatial-temporal filtering algorithm that eliminates industrial heat sources. The model derives a propagation bearing from wind direction, a base rate of spread from four environmental factors, and constructs three risk zones as cone-shaped polygons in geospatial coordinates. The model was implemented in the Sumsel Hotspot Monitor system, processing VIIRS and MODIS data from NASA FIRMS. Evaluation using Intersection over Union (IoU) and Dice Similarity Coefficient against real satellite ground truth shows that model performance degrades as the prediction time horizon increases. These results confirm that the model can run at low computational cost and is suitable as an early prediction baseline, although its accuracy still requires further parameter calibration before full adoption by the regional disaster management agency.
Co-Authors Abdul Rahman Abdul Rahman Adi Saputra Adikara Alif Nurrahman Adrian Suparto Agnes Anastasia Putri Ahmad Rizky Akhsani Taqwiym Akhsani Taqwiym Akhsani Taqwiym Akhsani Taqwiym Andreas Andreas Angel Kelly Antony, Felix Arta Tri Narta Arta Tri Narta Aurelia, Reni Busdin, Rusdie Candra candra Chandra Wijaya Chandra, Kelvin William Chandra, Yeremia Agung Christian Bautista Christofer Evan Setiawan Christy, Christy Cindy Meilani Clement, Michael Joy Daniel Wijaya Dedy Hermanto Derry Alamsyah Devella, Siska dewa Dicko David K Dina Lestari Putri Dina Mariana Dwifa_Sophian, Muhammad Agus Earlando Moza Edward Pratama Eka Puji Widiyanto Fareza, Ivan Farisi, Ahmad Farisi, Ahmad Fariz Prasetya Ferdi Jiranda Sinaga Ferdilian, M Lazuardi Fernando Sugianto Putra Franko, Billy Fujianto Graciela, Michelle Hansen, Hansen Hartati, Ery Hartono, Jeremy Allegrato Hendra Nata Niko P Hidayat, Muhammad Syahrizal Hidayat, WIlliam Immanuel Bunawan Ivander Destian Luis Jeason Lie Jendraja Husein Kotan Jennifer Jocelyn Jennifer Velensia Santoti Jeremy Allegrato Hartono Jolyn Lucretia jonathan stanly Jonathan Wijaya Juliana Nasution Kamilah, Nyimas Nisrinaa Kevin kevin Kevin Kevin Kristian Fernando Kurniawan, Calvin Laksana, Jovansa Putra Leonardo Leonardo Lestari, Yehezekiel Gian levid, Jonathan Felix Lin, Jimmi Meiriyama, Meiriyama Michael Gunawan Michael Joy Clement Michael Wijaya michael Wijaya Molavi Arman Muhamad Rizvi Roshan Muhammad Bemby Putra Mansyah Muhammad Ezar Al Rivan Muhammad Ishaq Maulana Muhammad Rizky Pribadi Muhammad Tri Setianto Muhdhor, Umar Narta, Arta Tri Nicholas Edison Novan Wijaya Nur Aisyah Wahyuni Ong, Jesen Patrisius Satria Hendrawan Pribadi, M Rizky Ramanda Md Rayvin Suhartoyo Renaldo, Florence Reynald Dwika Prameswara Rikky, Rikky Rizki Ambarwati RR. Ella Evrita Hestiandari Russel Wijaya Safeti Intan Pratiwi Samuel Effendi pratama Sanu, Intan Saputra, M Reynaldi Setiawan, Christofer Evan Shela, Shela Silvi Mutia Steven Liem Tanuwijaya, William Taqwiym, Akhsani Taqwiym, Akhsani Taqwiym, Akhsani Tinaliah, Tinaliah Triana Elizabeth, Triana Valen Julyo Armando Davincy Lin Verrino Adityya Virginia, Callista Wati, Retiana Krisna Wati, Risha Ambar Wijang Widhiarso Wijaya, Christian Richie William Tanuwijaya Willyanto, Aldo Wilyanto, Nicholas Wong, Jeovanni Yeremia Agung Chandra Yohannes, Yohannes Yunarto Yunarto, Yunarto