Claim Missing Document
Check
Articles

Analisis Sentimen Ulasan Aplikasi dengan Multinomial Naïve Bayes, Logistic Regression, dan SVM Rahelita Pasaribu; Ida Ayu Gde Suwiprabayanti Putra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 4 No. 1 (2025): JNATIA Vol. 4, No. 1, November 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v04.i01.p08

Abstract

The swift uptake of mobile health applications has led to an increase in user-generated feedback, providing important insights into public satisfaction. To explore user sentiments, this study analyzes 9,848 reviews from a health-oriented application utilizing three machine learning methods: Multinomial Naïve Bayes, Logistic Regression, and Support Vector Machine (SVM). The feedbacks were classified as positive or negative. The methodology included standard preprocessing such as cleaning and stemming, feature extraction using Term Frequency-Inverse Document Frequency (TF-IDF), and addressing class imbalance with the Synthetic Minority Oversampling Technique (SMOTE). Models were fine-tuned and verified through 5-fold cross-validation. Effectiveness was measured by accuracy, precision, recall, and F1-score. Logistic Regression and SVM reached the greatest accuracy at 92%, while Naïve Bayes trailed at 86%. Logistic Regression showed strong precision (95%) and recall (94%) for positive reviews, with SVM performing comparably. These results emphasize the capability of sentiment analysis in enhancing digital health services through information-based user feedback.
SISTEM INFORMASI PENJADWALAN KEGIATAN BIDANG REHABILITASI BNNP BALI Putu Bagus Ananta Wijaya, Ngakan; Ida Ayu Gde Suwiprabayanti Putra; Putu Praba Santika
Jurnal Pengabdian Informatika Vol. 4 No. 1 (2025): JUPITA Volume 4 Nomor 1, November 2025
Publisher : Jurusan Informatika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Udayana

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

Abstract

Bidang Rehabilitasi di Badan Narkotika Nasional Provinsi (BNNP) Bali bertanggung jawab untuk mengatur dan mengawasi berbagai program rehabilitasi untuk penyalahgunaan narkoba. Sistem Informasi Penjadwalan Kegiatan dibuat untuk membantu operasional sehari-hari agar pengelolaan kegiatan lebih efisien dan produktif. Sistem ini dimaksudkan untuk memudahkan penjadwalan, pengelolaan, dan pengawasan kegiatan rehabilitasi. Tujuannya adalah untuk meningkatkan transparansi dan akuntabilitas sekaligus mengurangi kemungkinan kesalahan manual. Sistem ini menggunakan teknologi web yang memungkinkan admin untuk menambah, mengubah, dan menghapus jadwal kegiatan serta membuat laporan aktivitas secara otomatis dan user untuk mengecek jadwal serta laporan. Akibatnya, diharapkan bahwa sistem ini akan memberikan kontribusi yang signifikan dalam manajemen program rehabilitasi BNNP Bali serta membantu mencapai tujuan rehabilitasi dengan cara yang lebih efisien dan terorganisir
PENGEMBANGAN APLIKASI PEMINJAMAN BARANG BERBASIS WEB UNTUK MENINGKATKAN EFISIENSI OPERASIONAL DI PT PILAR PERSADA SOLUTION Ni Putu Meita Kartika Dewi; Ida Ayu Gde Suwiprabayanti Putra; Putu Praba Santika
Jurnal Pengabdian Informatika Vol. 4 No. 2 (2026): JUPITA Volume 4 Nomor 2, Februari 2026
Publisher : Jurusan Informatika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Udayana

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

Abstract

Pengelolaan barang yang efisien menjadi kebutuhan penting bagi perusahaan di bidang pengadaan barang dan jasa untuk mendukung kelancaran operasional. Saat ini, PT Pilar Persada Solution menghadapi tantangan dalam pengelolaan peminjaman barang yang masih dilakukan secara manual, sehingga mengakibatkan ketidakakuratan dan inefisiensi. Untuk mengatasi hal ini, dikembangkan aplikasi peminjaman barang berbasis web dengan tujuan mempermudah pencatatan dan pengelolaan barang. Pengembangan aplikasi dilakukan menggunakan metodologi Software Development Life Cycle (SDLC) model Waterfall, yang meliputi tahapan analisis kebutuhan, perancangan, implementasi, dan pengujian. Aplikasi ini menyediakan fitur utama untuk pengelolaan data peminjaman, pengembalian, dan inventaris barang. Hasil pengujian menunjukkan bahwa seluruh fitur dapat digunakan dengan baik dan aplikasi ini mampu meminimalkan kesalahan pencatatan, serta mempermudah akses informasi inventaris.
Mengoptimalisasi Styling Pada Aplikasi Help Desk Salsabila, Zerina Nur Salsabila; I Gusti Ngurah Anom Cahyadi Putra; Ida Ayu Gde Suwiprabayanti Putra
Jurnal Pengabdian Informatika Vol. 4 No. 2 (2026): JUPITA Volume 4 Nomor 2, Februari 2026
Publisher : Jurusan Informatika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Udayana

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

Abstract

The optimization of the Help-Desk application's interface styling was carried out to enhance its responsiveness, modern appearance, and user comfort. The scope of this activity includes redesigning the user interface (UI), improving layout structure, and applying responsive design principles to ensure optimal usability across various devices. The process involved user needs analysis, interface design using Figma, development of an interactive prototype that represents the application's workflow, and design evaluation by internal users. The results showed an increase in positive user perception regarding the application's appearance, readability, and navigation. In addition to enhancing the application's professional impression, the new design is also expected to support user productivity in performing daily tasks through the Help-Desk system. The validated final design is ready to be used as a visual guideline for future application development in a more efficient and standardized manner
Klasifikasi Cuaca Menggunakan Algoritma Fuzzy Mamdani dan CART I Dewa Ayu Agung Rai Ratna Karang; Ida Ayu Gde Suwiprabayanti Putra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 4 No. 2 (2026): JNATIA Vol. 4, No. 2, Februari 2026
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2026.v04.i02.p14

Abstract

Weather prediction plays a vital role in sectors such as agriculture, transportation, and disaster mitigation. Extreme weather conditions can lead to unpredictable deviations that may cause significant harm to society. This study aims to predict weather conditions using the Fuzzy Mamdani algorithm and CART (Classification and Regression Tree). A total of 1,461 daily historical weather records from Seattle, United States, were obtained from the Kaggle website “Weather Prediction.” The fuzzy system was applied to convert numerical weather parameters—precipitation, maximum temperature, minimum temperature, and wind speed—into representative scores based on expert-defined rules. These fuzzy scores were then used as additional features in training the CART model to enhance weather classification accuracy. The dataset was split into 80% training data (1,168 records) and 20% testing data (293 records). Evaluation results show that the integration of Fuzzy and CART achieved an accuracy of 81.23% on the testing set, with high precision, recall, and F1 score for dominant categories such as sun and rain. This study demonstrates that the combination of fuzzy logic and decision trees is effective for weather classification based on historical data.
SISTEM PENDETEKSI KESEHATAN MENTAL REMAJA MENGGUNAKAN METODE FORWARD CHAINING DAN NAIVE BAYES Ida Ayu Gde Suwiprabayanti Putra; Ni Luh Putu Trisnawati
Jurnal Sistem Informasi dan Informatika (Simika) Vol. 8 No. 1 (2025): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/simika.v8i1.3901

Abstract

A very important first step in helping people with mental health disorders get medical care is detection. Mental health problems and drug abuse can be detected with a tool called SDQ (for adolescents aged 10 to 17 years). The twenty-five statements in the SDQ fall into five measurable behavioral categories: (1) emotional symptoms (5 statements), (2) behavioral problems (5 statements), (3) hyperactivity (5 statements), (4) friendship problems (5 statements), and (5) prosocial behavior (5 statements). By using SDQ, this research will create an expert system, a computer-based application, to detect adolescent mental health. Expert systems can be used to solve problems in ways thought by experts. This research will build a web-based expert system that uses the PHP programming language. System and accuracy testing will be carried out using black box testing and accuracy value testing to find out whether the symptoms and diagnosis results are appropriate. The research results in the form of a prototype will be available online so that teenagers can check their mental health freely.
Analisis Prediksi Ukuran Baju dengan Metode Regresi Polinomial Desak Putu Tia Rusilia Wati; Ida Ayu Gde Suwiprabayanti Putra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 3 No. 3 (2025): JNATIA Vol. 3, No. 3, Mei 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v03.i03.p18

Abstract

In the modern era, online shopping for clothing presents the challenge of determining the correct size. This research aims to predict clothing sizes using Polynomial Regression, which can capture the non-linear relationships between body metrics and clothing sizes. The study utilizes a dataset from Kaggle comprising weight, height, age, and clothing size attributes. Through data preprocessing, including feature transformation, engineering, selection, and cleaning, the dataset is prepared for analysis. Various models are evaluated, and Polynomial Regression is identified as the most effective, achieving an R² score of 0.70755203. Hyperparameter tuning using GridSearchCV further optimizes the model, resulting in a final R² score of 72.555511% with degree 5 and alpha 1. The evaluation indicates that while the model accurately predicts sizes, it sometimes struggles with adjacent sizes, particularly in medium ranges. This research demonstrates the potential of Polynomial Regression in improving the accuracy of clothing size predictions, thereby facilitating better online shopping experiences. 
Perancangan Desain UI/UX Aplikasi Somnia untuk Manajemen Pola Tidur Berbasis Mobile Ni Putu Meita Kartika Dewi; Ida Ayu Gde Suwiprabayanti Putra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 3 No. 2 (2025): JNATIA Vol. 3, No. 2, Februari 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v03.i02.p22

Abstract

Sleep is an essential basic need for human health and well-being. However, in the midst of a busy modern lifestyle, achieving ideal sleep becomes a challenge due to several factors. Consequently, lack of sleep can cause a negative impact on both physical and mental health. Based on these problems, this research aims to design the sleep management application "Somnia" using the prototype method. The application design is then evaluated using the System Usability Scale method. The evaluation results show that the average value of user satisfaction reaches 85.5, indicating that the design results is considered acceptable, with the adjective category being excellent, and received grade A. It was concluded, the design of the Somnia application is believed to have met user needs. 
Deteksi Hate Speech pada Unggahan Media Sosial dengan Naive Bayes Menggunakan Seleksi Fitur Chi-Square Putu Steven Belva Chan; Ida Ayu Gde Suwiprabayanti Putra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 3 No. 1 (2024): JNATIA Vol. 3, No. 1, November 2024
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2024.v03.i01.p20

Abstract

In the digital age, social media's pervasive use has revolutionized global communication but also introduced challenges like hate speech. This study proposes a Multinomial Naive Bayes model optimized with Chi-square feature selection to detect hate speech efficiently from large-scale social media data. Leveraging machine learning, this approach aims to combat harmful content by identifying relevant text features crucial for distinguishing hate speech from non-hate speech. The study utilizes TF-IDF for feature extraction and Chi-square for feature selection, showing significant performance improvements in hate speech detection. The Chi-square feature selection model yielded average precision, recall, F1-score, and accuracy values of 92%, 92%, 91%, and 92% respectively. In contrast, the model without feature selection achieved values of 89%, 89%, 88%, and 89% for the same metrics. Results demonstrate enhanced accuracy, precision, recall, and F1-score across various hate speech categories. 
Evaluasi pada Aplikasi Belajar Programming Menggunakan System Usability Scale I Komang Bisma Bendesa Jaya; Ida Ayu Gde Suwiprabayanti Putra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 2 No. 4 (2024): JNATIA Vol. 2, No. 4, Agustus 2024
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2024.v02.i04.p18

Abstract

In this digital era, using learning applications is an alternative way to master programming. Conventional methods are considered less efficient, so a programming learning application is needed that can be adapted to user needs and provide a satisfactory user experience. Usability is an important factor in determining effectiveness and user comfort level. To meet success, a system or application must meet user expectations and produce a positive user experience. The data collected is primary data of a qualitative nature. To evaluate the system, the system usability scale method is used. The research results show that on average 23 respondents, the system usability scale score is 40 (worst imaginable). This score is still below the average, namely 68, so a redesign is needed to improve the user experience of the system.