Article Per Year (5 Year)
p-Index From 2021 - 2026
1.197
P-Index
This Author published in this journals
All Journal Jurnal Nasional Komputasi dan Teknologi Informasi Jurnal Tata Kelola dan Kerangka Kerja Teknologi Informasi Infotek : Jurnal Informatika dan Teknologi VISA: Journal of Vision and Ideas JIKTEKS : Jurnal Ilmu Komputer dan Teknologi Informasi INOVTEK Polbeng - Seri Informatika Indonesian Community Service Journal of Computer Science (IndoComs)
Yusnia Budiarti
Universitas Bina Sarana Informatika
Aerospace Engineering Humanities Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Neuroscience Public Health Social Sciences Transportation

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
Analisis Sentimen Ulasan Aplikasi Vision+ pada Google Play Store Menggunakan Algoritma Naive Bayes Classifier Eko Pangestu Aji; Yusnia Budiarti
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 8, No 5 (2025): Oktober 2025
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v8i5.9846

Abstract

Abstrak - Perkembangan teknologi digital telah mendorong meningkatnya penggunaan aplikasi streaming, salah satunya adalah Vision+. Pengguna secara aktif memberikan ulasan di Google Play Store yang dapat digunakan sebagai bahan evaluasi untuk mengetahui tingkat kepuasan maupun keluhan terhadap layanan aplikasi tersebut. Penelitian ini bertujuan untuk melakukan analisis sentimen terhadap ulasan pengguna aplikasi Vision+ dengan mengklasifikasikannya ke dalam kategori positif, netral, dan negatif. Metode yang digunakan adalah Text Mining dengan tahapan preprocessing berupa case folding, tokenisasi, stopword removal, dan stemming. Fitur diekstraksi menggunakan metode Term Frequency-Inverse Document Frequency (TF-IDF), lalu dilakukan proses klasifikasi menggunakan algoritma Naïve Bayes Classifier dengan varian Multinomial. Data yang digunakan sebanyak 4.026 ulasan yang dibagi menjadi 80% data latih dan 20% data uji. Hasil evaluasi model menunjukkan akurasi sebesar 77%, precision sebesar 80%, recall sebesar 91%, dan f1-score sebesar 85%. Berdasarkan hasil tersebut, model dapat digunakan untuk mendeteksi sentimen secara otomatis guna mendukung pengambilan keputusan pengembangan layanan aplikasi.Kata kunci : Analisis Sentimen; Vision+; TF-IDF; Naïve Bayes Classifier; Ulasan Pengguna; Abstract - The advancement of digital technology has led to a surge in the use of streaming applications, one of which is Vision+. Users actively provide reviews on Google Playstore, which can be utilized to evaluate user satisfaction and identify complaints. This research aims to conduct sentiment analysis on user reviews of the Vision+ application by classifying them into positive, neutral, and negative categories. The method used is Text Mining with preprocessing stages such as case folding, tokenization, stopword removal, and stemming. Feature extraction is performed using Term Frequency-Inverse Document Frequency (TF-IDF), followed by classification using the Naïve Bayes Classifier algorithm with the Multinomial variant. A total of 4,026 reviews were used and split into 80% training data and 20% testing data. The model evaluation results show an accuracy of 77%, precision of 80%, recall of 91%, and an f1-score of 85%. Based on these results, the model can be used to automatically detect sentiment to support application service improvement decisions.Keywords: Sentiment Analysis; Vision+; TF-IDF; Naïve Bayes Classifier; User Reviews;
PEMANFAATAN TEKNOLOGI AI UNTUK PENINGKATAN KREATIVITAS ANAK ASUH YAYASAN AS-SYAMSURIYAH JAKARTA Yusnia Budiarti; Ahmad Setiadi; Norma Yunita; Wahyutama Fitri Hidayat
Indonesian Community Service Journal of Computer Science Vol. 2 No. 2 (2025): Periode Juli 2025
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/indocoms.v2i2.9228

Abstract

Community service activities with the theme of Increasing Creativity Using AI at the As-Syamsuriyah Foundation aim to enhance the skills of the children under the care of the As-Syamsuriyah Foundation in utilizing Artificial Intelligence (AI) technology through visual arts in the form of videos that can be used for effective documentation and publication. In this digital era, AI offers great potential to boost human creativity, but its use must be carried out carefully and responsibly. By understanding and addressing ethical challenges, we can ensure that AI becomes a partner that enriches the creative world, rather than a threat that undermines it. Wise implementation of AI allows humans to continue to evolve, creating works that harmoniously blend technology and human touch. This training includes visual arts in the form of videos utilizing AI technology that can be used for documentation and publication. Participants will learn to utilize AI using software to create easily accessible animation videos suitable for the foundation's documentation needs. This activity is expected to help the foundation's children improve their creativity using AI while still paying attention to ethical aspects. The output of this community service activity will be in the form of articles in print or electronic media, increased knowledge and skills of the partners.
Implementasi Sistem Verifikasi Keaslian Ijazah Berbasis Tanda Tangan Digital Menggunakan RSA dan SHA-256 Ainus Sya’adah; Yusnia Budiarti; Aprillia Ayu Fadhilah; Elvita Febrianti; Fadillah Akbar; Rangga Adi Saputra; Rio Singgih Daniswara
JIKTEKS : Jurnal Ilmu Komputer dan Teknologi Informasi Vol. 4 No. 03 (2026): Agustus
Publisher : Faatuatua Media Karya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70404/jikteks.v4i03.680

Abstract

Digitalisasi dokumen akademik meningkatkan efisiensi pengelolaan data, namun juga menimbulkan risiko pemalsuan dan manipulasi ijazah dalam format Portable Document Format (PDF). Penelitian ini mengimplementasikan sistem verifikasi keaslian ijazah berbasis tanda tangan digital menggunakan kombinasi algoritma Rivest-Shamir-Adleman (RSA) dan Secure Hash Algorithm 256 (SHA-256). Metode yang digunakan adalah pendekatan eksperimental-implementatif yang meliputi identifikasi masalah, studi literatur, perancangan sistem, implementasi, pengujian, dan analisis hasil. Pada tahap penandatanganan, dokumen PDF diproses dengan SHA-256 untuk menghasilkan nilai hash, lalu hash tersebut ditandatangani menggunakan kunci privat RSA dan disimpan dalam berkas signature berekstensi .sig. Proses verifikasi dilakukan dengan menghitung ulang nilai hash dokumen dan membandingkannya dengan nilai hash hasil verifikasi signature menggunakan kunci publik RSA. Hasil pengujian menunjukkan sistem mampu mengenali dokumen asli, mendeteksi dokumen yang dimodifikasi, dan menolak signature yang tidak sesuai. Dengan demikian, kombinasi RSA dan SHA-256 terbukti efektif menjaga integritas dan keaslian dokumen ijazah digital sebagai solusi verifikasi dokumen akademik elektronik.
Rancang Bangun Password Manager Berbasis Web Menggunakan Framework Django Dan Enkripsi Fernet Widarmawati Waruwu; Yusnia Budiarti; Mutiara Nazwah; Angga Wibowo Saputro; Diwan Mardianus Laia
Infotek: Jurnal Informatika dan Teknologi Vol. 9 No. 2 (2026): Infotek : Jurnal Informatika dan Teknologi
Publisher : Fakultas Teknik Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/jit.v9i2.35065

Abstract

Most prior password manager studies rely on basic encryption without strong key derivation and have not consistently implemented a zero-knowledge architecture, leaving encrypted user data potentially accessible to service providers or third parties. This research contributes by designing and building a web-based password manager that integrates three security layers within a unified Django ecosystem: PBKDF2 key derivation with 100,000 SHA-256 iterations, hardware-based unique random salt per user (os.urandom), and authenticated Fernet encryption (AES-128-CBC + HMAC-SHA256). The novelty of this research lies in the strict enforcement of the zero-knowledge principle, where the master password is never stored in the database, making credentials inaccessible even to system administrators. The combination of personalized salt and PBKDF2 also ensures that two users sharing an identical master password always produce distinct encryption keys — a feature not found in existing Django-based implementations. Black Box Testing across ten functional and security scenarios yielded a 100% success rate, covering CRUD operations, unauthorized access rejection, ciphertext tampering detection, and cross-user salt uniqueness verification. The results demonstrate that integrating PBKDF2, unique salt, and Fernet within the Django framework produces a transparent, secure credential storage system resilient to brute force attacks, rainbow table attacks, and database-level data manipulation.
Perbandingan Algoritma K-Nearest Neighbor (K-NN) dan Naive Bayes dalam Klasifikasi Tingkat Kemiskinan di Indonesia Juanuari Juanuari; Maulana Ilyas; Rahmat Tri Widodo; Ilham Manzis; Yusnia Budiarti; Musriatun Napiah
VISA: Journal of Vision and Ideas Vol. 6 No. 1 (2026): Journal of Vision and Ideas (VISA)
Publisher : IAI Nasional Laa Roiba Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Poverty is a major issue in sustainable development in Indonesia that requires a data-driven analysis approach to produce more accurate identification. This study aims to compare the performance of the K-Nearest Neighbor (K-NN) and Naive Bayes algorithms in classifying poverty levels in Indonesia based on social and economic data. The dataset was obtained from the Kaggle platform with the title "Classification of Poverty Levels in Indonesia", which contains 514 district/city data with various poverty indicators. The data was divided with a ratio of 80% for training and 20% for testing, then classification was carried out using the K-NN algorithm with a value of K = 5 and Naive Bayes. Evaluation was carried out using a confusion matrix with metrics of accuracy, precision, recall, and F1-score. The results showed that K-NN provided the best results with an accuracy of 97.09%, precision of 100%, recall of 75.00%, and F1-score of 85.71%, while Naive Bayes achieved an accuracy of 95.15%, precision of 73.33%, recall of 91.67%, and F1-score of 81.48%. This study resulted in better performance of this model compared to the results of previous studies. Therefore, the K-NN algorithm with the right parameters can be used as an effective method to support the data-based poverty level classification process and assist the government in poverty alleviation management and planning policies.
Implementation of Interior Design Project Monitoring Application using Appsheet Achmad Galih Prasetyo; Yusnia Budiarti
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/hfmd6y81

Abstract

To achieve project success, careful and continuous monitoring of progress, resources, and potential risks is essential in this context. A real-time application-based project monitoring system has been developed and implemented. This system is designed to provide comprehensive project visibility, making it easier for staff to monitor task progress, resource utilization, and proactively identify potential problems. With an intuitive, responsive, and communicative application interface, it makes performance more efficient between office staff and field teams. The results of this study prove that this application system is a very valuable tool for ensuring that projects are completed on schedule and within budget at PT. Generasi General Contractor. The project monitoring application with the waterfall method is a very classic method and its main characteristic is a linear and structured workflow. Where each stage must be completed before moving on to the next stage without the opportunity to return to the previous stage. This method is very suitable to be developed into a project monitoring application. And the results of usability testing using the single ease question (SEQ) method were tested with 10 questions selected based on experience in using the application. The results of the Usability testing from each staff showed a positive response with an average SEQ score of 5.31. Proving that the project monitoring application helps in reducing the problems that exist at PT. Generasi General Contractor.
Penerapan Business Intelligence Dengan Metode Nine-Step Kimball Untuk Analisis Penjualan Diamond Game (Studi Kasus: Aplikasi Otak Pulsa) Anno Achmat Istiana; Yusnia Budiarti
Jurnal Tata Kelola dan Kerangka Kerja Teknologi Informasi Vol. 12 No. 2 (2026): Agustus 2026
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/jtk3ti.v12i2.21294

Abstract

This study aims to implement Business Intelligence using the Nine-Step Kimball method and develop an dashboard using Microsoft Power BI. A descriptive case study was conducted on 21,143 transactions recorded from February 1, 2025 to February 28, 2026, covering 288 products, 1,032 resellers, and 4 suppliers. Data processing included selection, cleaning, transformation, dimensional modeling, visualization, and interpretation. The resulting sales data mart uses a star schema consisting of the TRANSAKSI fact table and four dimensions: time, Product, RESELLER, and SUPPLIER. The dashboard contains six analytical pages connected through cross-filtering. User acceptance reached 91.43%, categorized as Very Good. The analysis found that transactions peaked in April 2025 and on weekends; FFP70 had the highest transaction volume; GFFR50 generated the highest profit; 73.4% of transactions originated from West Java, Banten, and Jakarta; transaction success reached 98.4%; and the profit margin was approximately 3.1%. These findings can support decisions on promotion, balance availability, supplier capacity, and reseller network development.
Co-Authors Achmad Galih Prasetyo Ahmad Setiadi Ainus Sya’adah Angga Wibowo Saputro Anno Achmat Istiana Aprillia Ayu Fadhilah Diwan Mardianus Laia Eko Pangestu Aji Elvita Febrianti Fadillah Akbar Ilham Manzis Juanuari Juanuari Maulana Ilyas Musriatun Napiah Mutiara Nazwah Norma Yunita Rahmat Tri Widodo Rangga Adi Saputra Rio Singgih Daniswara Wahyutama Fitri Hidayat Widarmawati Waruwu