Article Per Year (5 Year)
p-Index From 2021 - 2026
2.957
P-Index
This Author published in this journals
All Journal Transmisi: Jurnal Ilmiah Teknik Elektro JurTI (JURNAL TEKNOLOGI INFORMASI) Journal of Information Systems and Informatics Abdimasku : Jurnal Pengabdian Masyarakat Jurnal Ekonomi dan Teknik Informatika Abdi Wina : Jurnal Pengabdian Kepada Masyarakat Universitas Kristen Wira Wacana Sumba
Hery Oktafiandi
Politeknik Sawunggalih Aji
Agriculture, Biological Sciences & Forestry Computer Science & IT Earth & Planetary Sciences Economics, Econometrics & Finance Education Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Medicine & Pharmacology Public Health Social Sciences Veterinary

Published : 19 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 19 Documents
Search

 1   2 
Implementasi LDA untuk Pengelompokan Topik Twitter Bertagar #Mypertamina Oktafiandi, Hery
Jurnal Ekonomi dan Teknik Informatika (JNETI) Vol 11 No 1 (2023): JURNAL EKONOMI DAN TEKNIK INFORMATIKA
Publisher : Politeknik Sawunggalih Aji

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37601/jneti.v11i1.222

Abstract

Abstract Twitter social media is widely used by users as a medium of communication and information. Apart from being a communication tool, Twitter is used to obtain the required research data. The use of the twitter hashtag becomes a reference for trending news or issues that are developing in the community. The trend that is currently being discussed is the Mypertamina application. This study takes data from twitter with the hashtag #Mypertamina with a lot of twitter data as many as 149 tweets, from the data obtained it will be clustered using topic modeling with the Latent Dirichlet Allocation (LDA) method. The advantage of the LDA method is that it can cluster, summarize, and link large amounts of data. This study resulted in 3 data clusters with the largest coherence value of 0.4618 Keywords: 3-5 keywords; Mypertamina, Twitter, LDA
Perbandingan Algoritma untuk Analisis Sentimen Terhadap Google Play Store Menggunakan Machine Learning Oktafiandi, Hery; Winarnie, Winarnie; Olajuwon, Sayyid M. Raziq
Jurnal Ekonomi dan Teknik Informatika (JNETI) Vol 11 No 2 (2023): JURNAL EKONOMI DAN TEKNIK INFORMATIKA
Publisher : Politeknik Sawunggalih Aji

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37601/jneti.v11i2.234

Abstract

Banyaknya aplikasi yang tersedia pada google playstore memudahkan para pengguna untuk memiilih aplikasi yang sesuai dengan kebutuhannya. Pengguna aplikasi pada google playstore memiliki sedikit kesulitan dalam memilih aplikasi mana saja yang baik performancenya karena terlalu banyaknya pilihan aplikasi yang tersedia. Para pengembang aplikasi menyediakan kolom komentar untuk review para pengguna aplikasi. Dengan review ini para calon pengguna aplikasi dapat memutuskan apakah menggunakan atau tidak, sedangkan untuk pengembang, review sangat dibutuhkan karena dapat melihat pencapaian kinerja dari aplikasi yang telah dibuat. Pada penelitian ini dilakukan untuk membandingkan tiga algorima machine learning yaitu : naives bayes, k-nearest neighbors dan radom forest untuk membandingkan nilai akurasi pada setiap algoritma berdasarkan sentimen pengguna. Pada penelitian ini dataset didapat dari scraping langsung dari aplikasi yang tersedia pada google play. Data kemudian diseleksi dan diberi label/klas. Pada penelitian ini dilakuakan percobaan dengan menggunakan jumlah dataset yang berbeda yaitu 40 dataset, 100 dataset dan 1000 dataset. Hasil akurasi yang didapar pada penggunaan dataset 1000 data diperoleh hasil akurasi untuk algoritma naïve bayes sebesar 79%, algoritma k nearest neighbors sebesar 77% dan algoritma random forest sebesar 75%.
Chatbot AI Platform Sebagai Media Peningkatan Kemampuan Belajar Siswa Ayuningtyas, Pratika; Oktafiandi, Hery
Jurnal Ekonomi dan Teknik Informatika (JNETI) Vol 12 No 1 (2024): Jurnal Ekonomi dan Teknik Informatika
Publisher : Politeknik Sawunggalih Aji

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37601/jneti.v12i1.246

Abstract

Pesatnya perkembangan teknologi Artificial Intelligence di dunia pendidikan dengan penggunaan AI sebagai media pembelajaran yang dapat diakses siswa tanpa batas waktu. Chatbots merupakan teknologi kecerdasan buatan yang dapat digunakan. Penggunaan chatbots sebagai media pembelajaran terbukti memberikan banyak dampak positif dalam pembelajaran. Perancangan chatbot dirancang untuk memenuhi kebutuhan siswa agar dapat menyadari manfaat penggunaan chatbots sebagai media pembelajaran dalam peningkatan kemampuan belajar siswa. Dalam perancangan dan pengembangan chatbot, digunakan template smojo.ai yang dilengkapi dengan media gambar, audio, video dan link website. Dengan kelengkapan media pendukung tersebut, siswa dapat belajar mandiri dengan media yang menarik dan inovatif. Chatbot AI juga dapat proses belajar interaktif yang dapat membuat suasana belajar lebih menyenangkan sehingga siswa mendapatkan banyak manfaat dan pengalaman belajar baru dengan chatbot AI.
Sistem Pelayanan Surat Pengantar Pada Desa Bedono Karangduwur Kemiri Berbasis Website Ardiansyah, Difta; Oktafiandi, Hery
Jurnal Ekonomi dan Teknik Informatika (JNETI) Vol 11 No 1 (2023): JURNAL EKONOMI DAN TEKNIK INFORMATIKA
Publisher : Politeknik Sawunggalih Aji

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37601/jneti.v12i1.289

Abstract

Sistem ini bertujuan untuk membantu memberikan pelayanan yang lebih optimal kepada masyarakat khususnya pada proses pembuatan surat menyurat agar lebih cepat dan mudah. Penilitian menggunakan metode pengumpulan data pengamatan secara langsung (observasi), penelitian langsung diobjek penelitian yaitu di desa Bedono Karangduwur Kemiri. Jenis data yang dipakai adalah data Kuantitatif atau data yang dapat diukur dalam skala angka, seperti jumlah penduduk, dan data kualitatif atau data yang dinyatakan dalam bentuk kata, seperti hasil wawancara dengan petugas atau masyarakat. Kesimpulan penilitian dari Tugas Akhir ini menunjukan bahwa sistem hanya dapat dijangkau oleh warga dengan usia produktif dan sistem hanya mencakup pada pembuatan surat pengantar saja.
Perbandingan Algoritma Machine Learning Untuk Sentimen Analisis Game Bus Simulator Indonesia Oktafiandi, Hery; Winarnie, Winarnie
JurTI (Jurnal Teknologi Informasi) Vol 8, No 2 (2024): DESEMBER 2024
Publisher : Universitas Asahan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36294/jurti.v8i2.4666

Abstract

This study aims to perform sentiment analysis on user reviews of the Bus Simulator Indonesia (BUSSID) application, developed by Maleo from Surabaya and released in 2017. A total of 10,000 reviews were collected from the Google Play Store using web scraping techniques and labeled based on ratings; reviews with ratings above 3 were considered positive, while those with ratings of 3 or below were considered negative. The reviews were then processed through case folding, cleaning, tokenizing, stopword removal, and stemming, and their features were extracted using the TF-IDF method. The data was split into 70% for training and 30% for testing. Three machine learning algorithms were applied: Naive Bayes Classifier (NBC), Stochastic Gradient Descent (SGD), and Support Vector Machine (SVM). The results showed that SVM had the highest accuracy at 79%, followed by SGD at 77%, and NBC at 76%. Evaluation using metrics such as accuracy, precision, recall, and f1-score indicated that this analysis provides valuable insights for BUSSID developers to improve the application’s quality. sentiment analysis, 
Evaluation of Machine Learning Models for Sentiment Analysis in the South Sumatra Governor Election Using Data Balancing Techniques Panjaitan, Febriyanti; Ce, Win; Oktafiandi, Hery; Kanugrahan, Ghanim; Ramdhani, Yudi; Putra, Vito Hafizh Cahaya
Journal of Information System and Informatics Vol 7 No 1 (2025): March
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v7i1.1019

Abstract

Sentiment analysis is crucial for understanding public opinion, especially in political contexts like the 2024 South Sumatra gubernatorial election. Social media platforms such as Twitter and YouTube provide key sources of public sentiment, which can be analyzed using machine learning to classify opinions as positive, neutral, or negative. However, challenges such as data imbalance and selecting the right model to improve classification accuracy remain significant. This study compares five machine learning algorithms (SVM, Naïve Bayes, KNN, Decision Tree, and Random Forest) and examines the impact of data balancing on their performance. Data was collected via Twitter crawling (140 entries) and YouTube scraping (384 entries), and text features were extracted using CountVectorizer. The models were then evaluated on imbalanced and balanced datasets using accuracy, precision, recall, and F1-score. The Decision Tree and Random Forest models achieved the highest accuracies of 79.22% and 75.32% on imbalanced data, respectively. However, they also exhibited overfitting, as indicated by their near-perfect training performance. Naïve Bayes, on the other hand, demonstrated the lowest accuracy at 54.55% despite achieving high precision, suggesting frequent misclassification, particularly for the minority class. SVM and KNN also struggled with imbalanced data, recording accuracies of 58.44% and 63.64%, respectively. Significant improvements were observed after applying data balancing techniques. The accuracy of SVM increased to 71.43%, and KNN improved to 66.23%, indicating that these models are more stable and effective when class distributions are even. These findings highlight the substantial impact of data balancing on model performance, particularly for methods sensitive to class distribution. While tree-based models achieved high accuracy on imbalanced data, their tendency to overfit underscores the importance of balancing techniques to enhance model generalization.
Pelatihan Dasar Artificial Intelligence : Membangun Chatbot dengan Python untuk Siswa SMA/SMK di Kota Palembang Panjaitan, Febriyanti; Oktafiandi, Hery; Permai, Antika
ABDIMASKU : JURNAL PENGABDIAN MASYARAKAT Vol 8, No 2 (2025): MEI 2025
Publisher : LPPM UNIVERSITAS DIAN NUSWANTORO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/ja.v8i2.2957

Abstract

Workshop AI untuk Pemula: Membangun Chatbot dengan Python bagi Siswa SMA/SMK di Kota Palembang diselenggarakan sebagai respons terhadap antusiasme siswa dalam program Jelajah Jurusan terkait kecerdasan buatan (Artificial Intelligence/AI). Kegiatan ini bertujuan untuk memberikan pemahaman dasar mengenai AI dan chatbot serta melatih keterampilan pemrograman Python menggunakan Google Colab. Workshop ini diikuti oleh 40 siswa dari SMKN 4 Palembang dan SMA Xaverius 2 Palembang yang dibagi ke dalam dua sesi. Hasil evaluasi melalui pretest dan post-test menunjukkan adanya peningkatan pemahaman siswa terhadap konsep AI dan chatbot. Rata-rata nilai pretest pada sesi pertama sebesar 68 meningkat menjadi 89 pada post-test, sedangkan sesi kedua meningkat dari 69 menjadi 90. Hal ini menunjukkan bahwa siswa mampu memahami dan mengimplementasikan chatbot dengan lebih baik setelah mengikuti workshop. Penggunaan Google Colab juga terbukti efektif dalam memfasilitasi pembelajaran tanpa kendala instalasi perangkat lunak. Workshop ini memberikan wawasan bagi siswa mengenai potensi AI dalam berbagai bidang serta mendorong minat mereka untuk mendalami teknologi ini lebih lanjut. Ke depannya, diharapkan pelatihan serupa dapat diperluas ke lebih banyak sekolah dan disertai dengan sesi lanjutan untuk memperdalam pemahaman serta implementasi teknologi AI dalam skala yang lebih luas
Sentiment Analysis on Coretax Data Using SVM and Random Forest with SMOTE and Tomek-Link Oktafiandi, Hery; Winarnie, Winarnie; Ramadhan, M. Fajar; Panjaitan, Febriyanti
Journal of Information System and Informatics Vol 7 No 3 (2025): September
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v7i3.1279

Abstract

This study is motivated by the increasing adoption of digital tax platforms in Indonesia, particularly Coretax, which enables online tax reporting and payment. Understanding user sentiment is crucial for evaluating system effectiveness and identifying areas for improvement. However, sentiment data is often imbalanced, making it challenging to detect the sentiments of the minority class. This research evaluates the performance of Support Vector Machine (SVM) and Random Forest (RF) in classifying sentiment from Coretax related reviews collected between March and September 2025 from Twitter, YouTube, and the DJP application. Lexicon-based labeling and preprocessing were applied, followed by class balancing using Tomek-Link, SMOTE, and SMOTE-Tomek techniques. On the original data, SVM achieved an accuracy of 98.56%, while Random Forest reached 98.43%, both performing strongly on the majority class. However, minority class detection was improved through SMOTE and SMOTE-Tomek, albeit with a slight decrease in overall accuracy due to the risk of overfitting. The novelty of this study lies in its focus on Coretax 2025 data and a comparative analysis of multiple resampling techniques, providing practical insights into improving sentiment analysis performance on imbalanced digital tax data.
Machine Learning Classification of SCD, CHF, and NSR Using 15-Minute ECG-Derived HRV Features Panjaitan, Febriyanti; Ce, Win; Ramadhan, M. Fajar; Winarnie; Oktafiandi, Hery
Journal of Information System and Informatics Vol 8 No 2 (2026): April
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i2.1557

Abstract

Heart disease remains one of the leading causes of mortality worldwide, making early detection essential for effective intervention. Heart Rate Variability (HRV) is widely used as a non-invasive marker for assessing cardiac conditions, and machine learning has shown potential in classifying heart diseases such as Sudden Cardiac Death (SCD) and Congestive Heart Failure (CHF). This study evaluates the performance of Support Vector Machine (SVM), Decision Tree (DT), and K-Nearest Neighbors (KNN) using 15-minute ECG signals comprising three 5-minute segments. The dataset consists of 53 subjects, generating 159 segments, including SCD, CHF, and Normal Sinus Rhythm (NSR). To prevent data leakage, a subject-wise split (80:20) is applied for training and testing. Two evaluation scenarios are considered: per-segment classification and combined 15-minute classification. Results indicate that SVM and DT achieve consistently high, stable performance with near-perfect accuracy, precision, recall, and F1-score, whereas KNN shows lower, more variable performance, particularly in segment-based analysis. The combined 15-minute approach provides more stable results, suggesting improved HRV representation and class separability. Although the results are promising, further validation with larger, more diverse datasets is required to ensure robustness and generalizability. This study highlights the potential of HRV-based machine learning while emphasizing the importance of appropriate temporal representation and rigorous evaluation design.
Co-Authors Aghus Sofwan Agung Budi Prasetijo Ardiansyah, Difta Ari Indra Indra Widyawan Ayuningtyas, Pratika Ce, Win Febriyanti Panjaitan Hafizh Cahaya Putra, Vito Kanugrahan, Ghanim Lutfi Ashar Mauludin, Lutfi Ashar Mukti Setiono Olajuwon, Sayyid M. Raziq Permai, Antika Pratika Ayuningtyas Ramadhan, M. Fajar Sayid M. Raziq Olajuwon Winarnie Winarnie Yudi Ramdhani