Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal JITK (Jurnal Ilmu Pengetahuan dan Komputer) Djtechno: Jurnal Teknologi Informasi
J PRAYOGA
Universitas Dharmawangsa
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
SENTIMENT CLASSIFICATION MODEL BASED ON COMPARATIVE STUDIES USING MACHINE LEARNING TECHNOLOGY J PRAYOGA; T. Irfan Fajri; Febri Dristyan
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 3 (2026): JITK Issue February 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i3.7105

Abstract

The development of social media has generated large amounts of text data, which is a valuable source for sentiment analysis. This study aims to conduct a comparative study of sentiment classification models on Indonesian-language YouTube comments, specifically comparing lexicon-based approaches, traditional machine learning models (Naive Bayes), and deep learning models (LSTM). Data was collected from YouTube videos themed around the youth generation and demographic bonuses, totaling 9,162 comments that underwent comprehensive text preprocessing. Model performance evaluation was conducted using accuracy, precision, recall, and F1-score metrics. The results show that the LSTM model outperforms Naive Bayes with an accuracy of 78.78% and an average F1-score of 0.79, compared to Naive Bayes, which only achieves an accuracy of 62.08% and an F1-score of 0.54. Although LSTM offers higher performance, the Naive Bayes model remains relevant due to its simplicity and efficiency. This study makes an important contribution to the selection of sentiment classification models for the Indonesian language and suggests the development of hybrid models and the use of contextual features for more optimal results. The LSTM model outperforms Naive Bayes with an accuracy of 82.15% (improved from 78.78% through enhanced regularization) and an average F1-score of 0.84. Comprehensive hyperparameter tuning via grid search and expanded manual annotation (40% of the dataset with κ=0.83) ensures robust model evaluation and reduces labeling bias. The study provides methodologically sound benchmarks for Indonesian sentiment analysis
KLASIFIKASI GAYA DESAIN POSTER MENGGUNAKAN EFFICIENTNETB0 BERBASIS TRANSFER LEARNING DAN FINE-TUNING Putri Annisa; Rama Prameswara Ritonga; Amru Yasir; J Prayoga
Djtechno: Jurnal Teknologi Informasi Vol 7, No 1 (2026): April
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/djtechno.v7i1.8605

Abstract

AbstrakPenelitian ini bertujuan mengklasifikasikan gaya desain poster menggunakan arsitektur EfficientNetB0. Pendekatan ini dilakukan untuk mengatasi subjektivitas dalam identifikasi manual gaya visual melalui pemanfaatan teknologi deep learning. Metode penelitian yang diterapkan berbasis transfer learning, yang mencakup tahap pelatihan awal dan dilanjutkan dengan proses fine-tuning untuk mengoptimalkan pengenalan fitur visual. Data penelitian yang diambil kemudian diolah menggunakan Google Colaboratory. Hasil eksperimen menunjukkan bahwa penerapan fine-tuning berhasil meningkatkan performa model secara signifikan hingga mencapai tingkat akurasi sebesar 84%. Berdasarkan hasil confusion matrix, model terbukti mampu membedakan karakteristik antar gaya desain secara stabil dan konsisten. Simpulan dari penelitian ini adalah penggunaan model EfficientNetB0 dengan strategi fine-tuning sangat efektif dalam melakukan klasifikasi citra poster dengan akurasi yang tinggi. Hasil ini diharapkan dapat mempermudah pengarsipan dan manajemen aset visual digital secara otomatis.Kata Kunci: EfficientNetB0, Gaya Desain Poster, Transfer Learning, Fine-Tuning, Klasifikasi Citra.AbstractThis research aims to classify poster design styles using the EfficientNetB0 architecture. This approach is undertaken to mitigate subjectivity in the manual identification of visual styles by leveraging deep learning technology. The research methodology is based on transfer learning, encompassing an initial training phase followed by a fine-tuning process to optimize visual feature recognition. The collected research data were processed using Google Colaboratory. Experimental results demonstrate that the application of fine-tuning significantly improved model performance, achieving an accuracy rate of 84%. Based on the confusion matrix analysis, the model proved capable of distinguishing characteristics between design styles with stability and consistency. This study concludes that the EfficientNetB0 model, combined with a fine-tuning strategy, is highly effective for poster image classification with high accuracy. These findings are expected to facilitate automated archiving and digital visual asset management.Keywords: EfficientNetB0, Poster Design Style, Transfer Learning, Fine-Tuning, Image Classification.
Co-Authors Febri Dristyan Mutasar Putri Annisa Rama Prameswara Ritonga Yasir, Amru