Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Antivirus : Jurnal Ilmiah Teknik Informatika Prosiding Seminar Nasional Sisfotek (Sistem Informasi dan Teknologi Informasi) Teknologi Informasi dan Digital (TRIDI)
Belinda Eka Sarah Dewi
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Materials Science & Nanotechnology Other

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

Found 3 Documents
Search

 1 
SENTIMENT ANALYSIS MODEL ON ELECTRIC VEHICLES USING INDOBERTWEET AND INDOBERT ALGORITHM Belinda Eka Sarah Dewi
Antivirus : Jurnal Ilmiah Teknik Informatika Vol 19 No 2 (2025): November 2025
Publisher : Universitas Islam Balitar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35457/w5r3g517

Abstract

The increasing adoption of electric vehicles in Indonesia has sparked various public opinions, necessitating sentiment analysis to understand societal perspectives. This study aims to compare the performance of two transformer-based models, IndoBERTweet and IndoBERT, in analyzing sentiments towards electric vehicles in Indonesia. Using a dataset collected from Indonesian language tweets and online comments, the data undergoes preprocessing, sentiment labelling into positive, negative, and neutral sentiments, and subsequent fine-tuning of both models. The models are evaluated based on accuracy, precision, recall, and F1-score. Experimental results demonstrate that IndoBERTweet achieves superior performance compared to IndoBERT in sentiment classification. The best performance recorded for IndoBERTweet was an accuracy of 82,40%, with an F1-score of 82,39%, while IndoBERT achieved an accuracy of 75,98% and an F1-score of 75,46%. These findings highlight the importance of using domain-spesific models for sentiment analysis and contribute to advancements in Indonesia-language natural language processing (NLP).
Penerapan Clustering Kinerja Pengelolaan Sampah Daerah Indonesia dengan Algoritma K- Means Marisa; Belinda Eka Sarah Dewi; Satria, Satria; Panca Indah Lestari
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

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

Abstract

Waste management is a major problem in Indonesia that requires a comprehensive assessment. This study utilizes data from 2024 obtained from the National Waste Management Information System (SIPSN) managed by the Ministry of Environment and Forestry (KLHK), with performance indicators including the level of waste management and waste handling. The technique applied is K-Means Clustering with the use of the Elbow Method to determine the number of the most efficient clusters. The findings indicate that the most efficient clusters consist of three categories: cluster 0 (low-performance areas), cluster 1 (medium-performance areas), and cluster 2 (high-performance areas). Areas that show high performance are characterized by a high proportion of managed and handled waste that is almost 100%. Based on the analysis results, Bogor Regency is included in the group with the best performance in waste management, so it can be used as a reference for other regions in implementing successful and sustainable waste management strategies.
PENGUKURAN KEMIRIPAN KALIMAT BAHASA INDONESIA MENGGUNAKAN REPRESENTASI WORD EMBEDDING FASTTEXT Belinda Eka Sarah Dewi
Jurnal Teknologi Informasi dan Digital Vol. 3 No. 1 (2025): Teknologi Informasi dan Digital
Publisher : LPPM Universitas Bani Saleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65624/tridi.v3i1.99

Abstract

Pengukuran kemiripan kalimat merupakan komponen penting dalam berbagai aplikasi pemrosesan bahasa alami (NLP), seperti pencarian semantik, sistem tanya jawab, dan deteksi plagiarisme. Penelitian ini bertujuan untuk mengevaluasi kemampuan model word embedding FastText dalam mengukur kemiripan semantik antar kalimat berbahasa Indonesia. Dataset yang digunakan adalah Semantic Textual Similarity Benchmark (STS-B) versi Bahasa Indonesia, yang memuat pasangan kalimat beserta skor kemiripan berdasarkan penilaian manusia. Setiap kalimat direpresentasikan sebagai rata-rata vektor dari kata-kata penyusunnya menggunakan model FastText pralatih untuk Bahasa Indonesia. Kemiripan antar kalimat dihitung menggunakan cosine similarity, dan hasilnya dibandingkan dengan skor referensi manusia menggunakan korelasi Pearson dan Spearman. Hasil evaluasi menunjukkan bahwa FastText mampu menangkap sebagian besar makna semantik antar kalimat, dengan nilai korelasi Pearson sebesar 0.3658 dan Spearman sebesar 0.4260. Meskipun demikian, hasil tersebut mengindikasikan bahwa pendekatan berbasis word-level embedding seperti FastText memiliki keterbatasan dalam memahami konteks yang lebih kompleks. Penelitian ini memberikan gambaran awal mengenai efektivitas FastText dalam tugas pengukuran similarity semantik untuk Bahasa Indonesia dan membuka peluang pengembangan metode representasi yang lebih kontekstual di masa depan.
Co-Authors Marisa Panca Indah Lestari Satria Satria, Satria