Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Jusikom : Jurnal Sistem Komputer Musirawas Jurnal Ilmiah Betrik : Besemah Teknologi Informasi dan Komputer Journal of Social Sciences and Technology for Community Service
Yustida Bellini
Institut Teknologi Sumatera
Humanities Computer Science & IT Engineering Languange, Linguistic, Communication & Media Library & Information Science

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Vader Meets Multilingual Voices: Klasifikasi Sentimen Ulasan Pada Aplikasi Babble Dengan Bantuan Deep Translator Yustida Bellini; Ayu Okta Pratiwi
BETRIK Vol. 16 No. 02 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/fwyg7r05

Abstract

 The rapid advancement of technology today greatly facilitates our access to information—within seconds, we can obtain whatever information we need. This also makes it easier to learn various languages around the world, as seen in the Babbel application. This study aims to identify sentiment in user reviews of the Babbel app by utilizing a combination of Deep Translator, VADER (Valence Aware Dictionary and Sentiment Reasoner), and Logistic Regression. User reviews were collected from the Google Play Store, resulting in 1,000 multilingual reviews. All reviews in different languages were translated into English using Deep Translator. After translation, sentiment labeling was performed using VADER. Then, the text data were transformed into numerical form using TF-IDF vectorization. After all these steps, the classification process was carried out using a Machine Learning model, namely Logistic Regression. The evaluation phase used a Confusion Matrix, and the sentiment classification achieved an accuracy of 89%. This study concludes that the combination of lexical-based analysis and machine learning can provide reliable results for multilingual sentiment analysis. In the future, this approach can be further developed by evaluating the performance of other classification algorithms.
Peningkatan Kompetensi Web Modern melalui Pelatihan Framework Next.js bagi siswa SMKN 7 Bandar Lampung Febri Dwi Irawati; Mika Alvionita Sitinjak; Ardika Satria; Ahmad Luky Ramdani; Ira Safitri; Tirta Setiawan; Luluk Muthoharoh; Rohmi Dyah Astuti; Yoga Aji Sukma; Dimas Dwi Randa; Vina Nurmadani; Yustida Bellini
Journal Social Science And Technology For Community Service Vol. 7 No. 1 (2026): Volume 7 Nomor 1 Maret 2026
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jsstcs.v7i1.1689

Abstract

Kesenjangan kompetensi siswa Sekolah Menengah Kejuruan (SMK) dengan kebutuhan industri pengembangan perangkat lunak yang dinamis menjadi latar belakang utama pelaksanaan pengabdian ini. Framework Next.js, sebagai teknologi modern berbasis React, dipilih untuk meningkatkan kapasitas teknis siswa dalam membangun aplikasi web modern dan berkinerja tinggi. Kegiatan ini bertujuan untuk meningkatkan pemahaman dan keterampilan praktis siswa SMKN 7 Bandar Lampung melalui metode project-based learning. Subjek pengabdian terdiri dari 56 siswa yang dievaluasi menggunakan instrumen pre-test dan post-test. Analisis data dilakukan secara komprehensif menggunakan statistika deskriptif dan inferensia non-parametrik Wilcoxon Signed-Rank Test karena distribusi data yang tidak normal (p < 0,05). Hasil analisis menunjukkan adanya peningkatan skor rata-rata yang signifikan dari 28,39 menjadi 37,04. Wilcoxon test menghasilkan nilai statistik V = 3 dengan signifikansi p < 0,001, yang mengonfirmasi adanya perbedaan kompetensi yang nyata setelah intervensi diberikan. Selain itu, capaian effect size sebesar 0,571 (kategori besar) memperkuat bukti bahwa metode pelatihan berbasis praktik efektif dalam mereduksi disparitas pemahaman siswa, terutama pada indikator inisiasi proyek dan struktur folder. Kesimpulannya, pelatihan ini berhasil mentransformasi pengetahuan siswa dari kategori ragu-ragu menjadi paham, sekaligus memberikan fondasi teknologi yang relevan dengan standar industri terkini.
IMPLEMENTASI FACE RECOGNITION DENGAN CONVOLUTIONAL NEURAL NETWORK (CNN) DAN LIVENESS DETECTION PADA SISTEM ABSENSI PT. XYZ: IMPLEMENTASI FACE RECOGNITION DENGAN CONVOLUTIONAL NEURAL NETWORK (CNN) DAN LIVENESS DETECTION PADA SISTEM ABSENSI PT. XYZ Nolan Efranda; Berta Erwin SLAM; Feri Irawan; Rifaldi Herikson; Yustida Bellini
Jusikom : Jurnal Sistem Komputer Musirawas Vol. 11 No. 1 (2026): Jurnal Sistem Komputer Musirawas JUNI
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jusikom.v11i1.3202

Abstract

Employee attendance management is a crucial aspect in improving organizational efficiency and productivity. However, in practice, fraudulent activities such as buddy punching are still frequently encountered. Therefore, PT.XYZ requires an efficient and secure attendance system to address this issue. This study aims to implement a face recognition-based attendance system using the Convolutional Neural Network (CNN) method combined with liveness detection. The system is developed on both mobile and desktop platforms using Python, TensorFlow, and Firebase technologies. The research process includes collecting a dataset of 320 facial images from 32 employees, image preprocessing, CNN model training, and the integration of liveness detection based on facial movement analysis to verify user authenticity. System evaluation is conducted based on accuracy, response time, and robustness under varying conditions such as lighting and facial positions. The results show that the system is capable of recognizing faces in real-time with an accuracy rate of 97.81% and a response time ranging from 2 to 5 seconds. The system also demonstrates stability under various lighting conditions and shows good scalability. Therefore, the CNN and liveness detection-based attendance system is effective in improving accuracy, security, and supporting a more efficient, professional, and transparent employee attendance management system.
Co-Authors Ardika Satria Ayu Okta Pratiwi Dimas Dwi Randa Efranda, Nolan Febri Dwi Irawati Feri Irawan Ira Safitri Luluk Muthoharoh Mika Alvionita Sitinjak Ramdani, Ahmad Luky Rohmi Dyah Astuti SLAM, Berta Erwin Tirta Setiawan Vina Nurmadani Yoga Aji Sukma