Article Per Year (5 Year)
p-Index From 2021 - 2026
3.75
P-Index
This Author published in this journals
All Journal Khazanah Informatika: Jurnal Ilmu Komputer dan Informatika Jurnal Teknologi dan Sistem Komputer Jurnal Abdimas BSI: Jurnal Pengabdian Kepada Masyarakat Jurnal Informatika Swabumi (Suara Wawasan Sukabumi) : Ilmu Komputer, Manajemen, dan Sosial Jurnal Pilar Nusa Mandiri Jurnal Sains dan Informatika Jurnal Nasional Komputasi dan Teknologi Informasi JURSIMA (Jurnal Sistem Informasi dan Manajemen) Journal of Applied Data Sciences Jurnal Responsif : Riset Sains dan Informatika Djtechno: Jurnal Teknologi Informasi Jurnal Media Informatika Jurnal Teknik Informatika dan Teknologi Informasi JURSIMA Jurnal Sistem Informasi dan Manajemen Journal of Deep Learning, Computer Vision and Digital Image Processing Jurnal Teknik Informatika dan Teknologi Informasi
Asti Herliana, Asti
Universitas Adhirajasa Reswara Sanjaya
Aerospace Engineering Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Library & Information Science Mathematics Neuroscience Social Sciences Transportation

Published : 37 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 37 Documents
Search

 1   2   3   4 
KOMPARASI OPTIMASI ANALISIS SENTIMEN CYBERBULLYING PADA INSTAGRAM BERBASIS PARTICLE SWARM OPTIMIZATION Herliana, Asti; Muawiyah, Shofiyah Siti
Jurnal RESPONSIF: Riset Sains & Informatika Vol 6 No 1 (2024): Jurnal Responsif : Riset Sains dan Informatika
Publisher : LPPM Universitas Adhirajasa Reswara Sanjaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51977/jti.v6i1.1419

Abstract

Sejak masa pandemi covid-19 melanda dunia, sekitar 78,19% manusia di Indonesia mengandalkan media internet sebagai penunjang utama kegiatan sehari-hari. Hal ini membuat aktivitas manusia mayoritas dilakukan melalui dunia maya, salah satunya adalah sebagai bentuk eksistensi. Media sosial seperti Instagram, menjadi pilihan dari banyak manusia di dunia utamanya Indonesia untuk menyalurkan segala macam bentuk aspirasinya. Efek dari meningkatnya postingan di media sosial ini juga berimbas kepada tingginya tingkat perundungan melalui dunia maya yang sering dikenal dengan istilah cyberbullying. Salah satu bentuk cyberbullying yang marak terjadi adalah melalui ujaran kebencian dan kata-kata yang tidak baik terhadap postingan yang diunggah. Pada penelitian kali ini akan dilakukan optimasi untuk mengetahui analisis sentimen terhadap berbagai tindak cyberbullying yang ada pada media sosial Instagram agar dapat ditindak lebih lanjut dengan menggunakan metode Particle Swarm Optimization (PSO). Sedangkan untuk metode klasifikasi dari analisis sentiment pada penelitian kali ini dilakukan komparasi dengan menggunakan algoritma support vector machine (SVM) dan naïve bayes. Dari hasil penelitian diketahui bahwa performa metode PSO memberikan hasil yang lebih baik jika dikombinasikan dengan metode SVM yang mencapai nilai akurasi 78,60% dengan dukungan 100% class precission. Sedangkan hasil naïve bayes hanya mencapai nilai akurasi 78,00% dengan dukungan class precission sebesar 99,74%.
PERBANDINGAN KEEFEKTIFAN ALGORITMA BACKTRACKING DAN SOFT COMPUTING DALAM MEMECAHKAN PERMAINAN PAPAN NONOGRAM Muhammad Ali Zafar Sidiq; Aldi Supriyadi; Asti Herliana
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 3 No. 1 (2023): April: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v3i1.2069

Abstract

Solving logic puzzles using specific algorithms presents an intriguing challenge where the efficiency of the approaches is crucial. One such puzzle involves solving nonograms, where the task is to fill in board fields according to the conditions specified for each row and column. The availability of various methods allows for comparing their efficiency and effectiveness. This study aimed to evaluate the effectiveness of two algorithms from different categories. We selected a modified Depth-First Search (DFS) method and a soft computing method based on permutations generation to solve a set of chosen nonograms. The research was conducted using four different board sizes, and the results indicated that the effectiveness of the methods largely depends on the complexity of the nonogram. The algorithm employing permutations consistently produced stable results, while the DFS method did not always guarantee a complete solution.
Prediksi Tingkat Kepuasan Pengguna Aplikasi Pojokcat dalam Pembelajaran Online Menggunakan Algoritma Naïve Bayes Nabilla Putri Sahara; Asti Herliana
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 2 (2025): Agustus: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i2.5543

Abstract

Technological developments in education have encouraged the use of online learning applications, one of which is PojokCAT, used by prospective students (casis) to prepare for the National Police selection exam. However, the lack of a systematic evaluation of user satisfaction levels has led to questions about the extent to which this application is able to meet learning needs. This study aims to predict the level of satisfaction of PojokCAT application users using the Naïve Bayes algorithm. Data were obtained from a courage questionnaire completed by 384 active respondents using the application. The process analysis included preprocessing, data sharing, model training, and performance classification evaluation. The results showed that the Naïve Bayes algorithm was able to predict satisfaction levels with an accuracy of 91.38%. The precision value reached 86.67%, recall was 90.70%, and AUC was 0.971, indicating excellent classification performance. In general, this indicates that PojokCAT has been able to meet the needs of its users. However, there are still certain aspects that require further improvement. These findings indicate that the Naïve Bayes algorithm is effective for classifying user satisfaction levels in online learning applications.
The Application of Deep Learning in Qur’anic Tafsir Retrieval Using SBERT, FAISS and BERT-QA Asti Herliana; Ina Najiyah; Sari Susanti; Lutfhi Muayyad Billah
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1000

Abstract

Accurate understanding of the Qur’an requires access to reliable tafsir, yet many classical tafsir resources remain non-digital, making search and retrieval time-consuming. This study presents a semantic-based retrieval system for Tafsir Ibn Kathir, covering 114 entries and 6,236 Verses, using SBERT embeddings and FAISS indexing. The system enables users to perform semantic queries, retrieving relevant passages in response to their questions. Evaluation was conducted using 50 representative queries spanning diverse topics, including Fiqh, Aqidah, History, and Spirituality. Relevance judgments were independently provided by three Qur’anic studies experts and reconciled through discussion, with inter-annotator agreement indicating substantial consistency. Each query included 20 non-relevant passages as negative samples to increase evaluation difficulty. Two approaches were tested: retrieval-only and retrieval combined with a zero-shot QA module for span extraction. Retrieval-only achieved slightly higher top-1 accuracy (0.72), but retrieval + QA improved ranking-oriented metrics, including Accuracy@5 (0.88), Mean Reciprocal Rank (MRR = 0.76), and normalized Discounted Cumulative Gain at 5 (nDCG@5 = 0.82), with the increase in Accuracy@5 statistically significant (p = 0.01). The zero-shot QA module enabled the system to extract more precise and contextually relevant information, enhancing overall retrieval quality and robustness. These results indicate that the proposed system effectively retrieves relevant tafsir passages and provides accurate, context-specific answers. The study demonstrates the potential and limitations of zero-shot QA for domain-specific religious texts and supports the development of web-based applications or Islamic chatbots, facilitating easier access to shahih tafsir knowledge for scholars and the broader Muslim community.
Comparative Analysis of a Simple CNN and Fine-Tuned ResNet50 for Deepfake Image Detection: Performance and Computational Efficiency Evaluation Rifda Triani Mutmainah; Asti Herliana
Journal of Deep Learning, Computer Vision, and Digital Image Processing Volume 4 Issue 2 June 2026
Publisher : CV. Sakura Digital Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61255/decoding.v4i2.1629

Abstract

Purpose – Deepfake-related cybercrime is an increasingly troubling cybersecurity threat, since such content can now be produced from a single facial photo using freely available face-swapping techniques, while human ability to distinguish real from fake images remains limited (48.2–59%). This study compares a simple CNN and a fine-tuned ResNet50 within an identical, controlled framework.Methods – A controlled experiment compared a simple CNN (trained from scratch) and ResNet50 (two-phase fine-tuning) on 20,000 images from the Kaggle Deepfake and Real Images dataset (80:10:10 split, seed = 42). Candidate images were deduplicated before the data split; zero cross-split duplicates were confirmed. ResNet50 used ResNet-specific preprocessing; the CNN used inputs normalized to [0,1]. Evaluation used accuracy, precision, recall, F1-score, AUC-ROC, and specificity, with a paired McNemar's test as the primary significance measure.Findings – The CNN outperformed ResNet50 on six of seven metrics (accuracy 90.90% vs. 89.80%; AUC-ROC 97.08% vs. 96.52%), while ResNet50 achieved higher recall (93.10% vs. 91.80%). The accuracy difference was not statistically significant (p = 0.200). The CNN was 69.5 times smaller and trained faster (12.2 vs. 16.5 minutes). Neither model showed clear overfitting. Research implications – The findings rest on a single subset, a single split, and a single training run per model, limited to 20 epochs; the potential of ResNet50 with longer training has not been explored.Originality – This study combines accuracy, generalization-related diagnostics, and efficiency in a single controlled comparison, applies a paired test appropriate for a shared test set, and filters duplicates before the data split.
ANALISIS SENTIMEN PENGGUNA APLIKASI SAPAWARGA - JABAR SUPER APPS MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE Raisya Nadzira Zahirahtush Shafa; Asti Herliana
Djtechno: Jurnal Teknologi Informasi Vol 6, No 2 (2025): Agustus
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/djtechno.v6i2.6877

Abstract

Pertumbuhan aplikasi layanan publik digital menjadi bagian penting dalam reformasi birokrasi dan transformasi pelayanan pemerintah kepada masyarakat. Salah satu implementasinya di Provinsi Jawa Barat adalah aplikasi Sapawarga – Jabar Super Apps, yang mempermudah akses masyarakat terhadap layanan publik. Penelitian ini bertujuan mengevaluasi opini publik terhadap aplikasi tersebut melalui pendekatan analisis sentimen berbasis teks ulasan pengguna di App Store, terutama pasca peralihan kepemimpinan daerah. Metode yang digunakan adalah pendekatan lexicon-based sentiment analysis dengan kamus Indonesian Sentiment Lexicon (InSet), dilanjutkan dengan klasifikasi menggunakan algoritma Support Vector Machine (SVM). Proses penelitian meliputi preprocessing data (cleansing, normalisasi, tokenisasi, dan penghapusan stopwords), pelabelan sentimen, ekstraksi fitur menggunakan TF-IDF, dan evaluasi model melalui confusion matrix. Data diperoleh melalui web scraping, menghasilkan 229 ulasan valid, yang diklasifikasikan menjadi 166 sentimen negatif, 47 positif, dan 16 netral. Hasil evaluasi menunjukkan akurasi tertinggi sebesar 86% pada skenario pembagian data latih dan uji 90:10. Penelitian ini memberikan gambaran objektif mengenai persepsi pengguna terhadap layanan digital publik serta rekomendasi berbasis data bagi pengambil kebijakan dan pengembang aplikasi dalam meningkatkan kualitas dan responsivitas pelayanan.
Analisis Sentimen Publik atas Kebijakan Efisiensi Anggaran 2025 dengan Text Mining dan Natural Language Processing Vina Agustina; Asti Herliana
Jurnal Media Informatika Vol. 6 No. 3 (2025): Jurnal Media Informatika
Publisher : Lembaga Dongan Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55338/jumin.v6i3.6301

Abstract

Kebijakan efisiensi anggaran merupakan langkah strategis pemerintah untuk mengoptimalkan penggunaan belanja negara. Langkah konkret terbaru di tahun 2025, yakni Instruksi Presiden Nomor 1 Tahun 2025 yang dikeluarkan pada tanggal 22 Januari 2025, menetapkan pemangkasan anggaran belanja negara sebesar Rp 306,69 triliun. Namun, implementasi kebijakan ini sering menimbulkan pro dan kontra di masyarakat. Penelitian ini bertujuan untuk menganalisis sentimen masyarakat terhadap kebijakan efisiensi anggaran tahun 2025 dengan pendekatan Text Mining dan Natural Language Processing (NLP). Data dikumpulkan dari media sosial Twitter menggunakan teknik web crawling berbasis Python, dengan kata kunci tertentu dan filter waktu tertentu, sehingga diperoleh 1.614 tweet yang relevan. Proses pre-processing meliputi pembersihan data, case folding, tokenisasi dan stopword removal. Data kemudian diberi label sentimen secara manual (positif, negatif, netral), dibagi menjadi data latih (70%) dan data uji (30%) dengan teknik stratified sampling, serta ditransformasikan menjadi bentuk numerik menggunakan metode TF-IDF. Hasil klasifikasi menggunakan algoritma Naive Bayes menunjukkan bahwa mayoritas sentimen masyarakat bersifat negatif (74,53%), dengan akurasi model mencapai 93,01%. Temuan ini menunjukkan bahwa masih terdapat ketidakpuasan publik terhadap kebijakan tersebut. Penelitian ini memberikan kontribusi dalam pemanfaatan teknologi untuk mendukung pengambilan keputusan berbasis data (evidence-based policy), serta dapat menjadi acuan bagi pemerintah dalam merumuskan strategi komunikasi publik yang lebih responsif.
Co-Authors Ade Mubarok Aldi Supriyadi Aldi Supriyadi Ali Akbar Rismayadi Ambi Nur Akbar Annisa Risqi Sulistya Kusuma Wardhani Ardianto, Rian Arif Armansyah Bayu Saputra Dasril Aldo Dwiza Riana El Miana Assni Ernamia Fira Fathonah Firza Novaldy Fitriyani Fitriyani Fitriyani Fitriyani Freddy Agus Renaldi Fuady, Tb. Dedy Holis Holis Ina Najiyah Ina Najiyah Lina Lulus Destianti Lutfhi Muayyad Billah Mayya Nurbayanti Shobary Moh Siri, Moh Muawiyah, Shofiyah Siti Muckti, Masaldi Kharisma Muhammad Ali Zafar Sidiq Muhammad Ali Zafar Sidiq Muhammad Rivai Nabilla Putri Sahara Oktaviani, Fani Rahma Pratiwi Pratiwi Prima Muhamad Rasyid Raisya Nadzira Zahirahtush Shafa Rangga Sanjaya Rian Ardianto Rian Ardianto Rifda Triani Mutmainah Rizki Tri Prasetio, Rizki Tri Salman Khemaludin Yoesoef Sari Susanti Sari Susanti, Sari Syarif Hidayatulloh Taufik Hidayatulloh Tb. Dedy Fuady Titin Suhartini Toni Arifin Vina Agustina Visqia Ade Setiawan Yayu Sri Rahayu Yudhiono, Noor Fuadillah Yudi Ramdhani