Article Per Year (5 Year)
p-Index From 2020 - 2025
0.562
P-Index
This Author published in this journals
All Journal Bulletin of Computer Science Research INOVTEK Polbeng - Seri Informatika
Reflan Nuari
Unknown Affiliation
Computer Science & IT

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

Found 3 Documents
Search

 1 
Performance Comparison Of BERT Metrics and Classical Machine Learning Models (SVM,Naive Bayes) for Sentiment Analysis Adib Ulinuha El Majid; Reflan Nuari
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/wmh3rg23

Abstract

Sentiment analysis is one of the important methods in understanding public opinion from large amounts of text, such as product reviews or user comments. Many studies have shown that the BERT (BiDirectional Encoder Representations from Transformers) model has advantages over classical machine learning models such as Support Vector Machine (SVM) and Naïve Bayes. However, there are still few studies that systematically compare the performance of the two on datasets from various topics and languages, especially those with imbalanced label distributions. This study compares four BERT variants (bert-base-uncased, distilbert-base-uncased, indobert-base-uncased, and distilbert-base-indonesian) with two classical models using three datasets of IMDb 50K (English), Amazon Food Reviews (English), and Gojek App Review (Indonesian). The classical model uses the TF-IDF vectorisation method, while the BERT model is optimised through a further training process (fine-tuning) with a layer freezing technique. The evaluation is carried out using accuracy, precision, recall, and F1-score. The results show that the BERT model excels on English data, while on imbalanced Indonesian data, SVM and Naïve Bayes produce higher F1-score results. These findings indicate that the selection of the right model must be adjusted to the characteristics of the data used.
Penerapan Desain UI/UX pada Aplikasi Web Portal Berita Dengan Metode Design Thinking Melanda Sari; Reflan Nuari
Bulletin of Computer Science Research Vol. 5 No. 6 (2025): October 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i6.808

Abstract

The rapid advancement of technology and digitalization has significantly transformed how people access information, making web applications a primary platform for reading news. In this context, User Interface (UI) and User Experience (UX) design play crucial roles in determining the success of a news platform. This study aims to explore the application of the Design Thinking method in designing the UI/UX of the Paparan Lampung news application to enhance reader engagement and optimize user experience. The Design Thinking approach was chosen because it focuses on user needs through stages of empathy, problem definition, ideation, prototyping, and testing, enabling the creation of relevant and innovative design solutions. This research employs a descriptive quantitative method, utilizing the System Usability Scale (SUS) to assess the application’s usability level. The results show that Paparan Lampung achieved a SUS score of 88.5, categorized as “Excellent” (Grade A) and exceeding the industry acceptance threshold of 68. Furthermore, the MAUS score of 80.3 reinforces that the application is not only efficient and effective but also delivers a highly satisfying user experience. Overall, the implementation of Design Thinking has proven to enhance UI/UX design quality, directly improving user comfort and engagement. Despite the highly positive results, this study has limitations in terms of the number of respondents and the controlled testing environment. Therefore, future research is recommended to involve a larger and more diverse group of participants to obtain more comprehensive and generalizable findings.
Application Of K-Means Algorithm to Cluster Students' Reading Patterns in the Digital Age Permana Putra, Yongky; Reflan Nuari
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 1 (2025): March
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/j8gz8h32

Abstract

This study aims to group students' reading patterns in the digital era using the K-Means algorithm. This algorithm divides data into clusters, such as reading duration, type of reading, reading frequency, and devices used. Data were obtained through questionnaires distributed to 224 students of SMK Negeri 4 Bandar Lampung, with 214 valid data analysed after the preprocessing stage. The selection of vocational high school students as this study was based on previous journal references that examined reading patterns in PAUD to SMA students, so special attention is paid to vocational high school students, understanding reading patterns that have different needs compared to references with other levels of education. The clustering process produced four clusters with unique characteristics, reflecting differences in reading patterns based on the type of media used, intensity, and digital devices. The results of the study showed that clusters with high digital reading intensity can be directed to utilise e-books and online learning platforms optimally, while clusters with a preference for printed books require strengthening physical reading habits through literacy activities. With a Davies-Bouldin index value of -2.224, the quality produced is proven to be very good. These findings provide guidance for educators to develop technology-based education policies and personal approaches to improving student literacy. Designing learning programs with methods and student reading patterns to support the quality of education in the digital era.
Co-Authors Adib Ulinuha El Majid Melanda Sari Permana Putra, Yongky