Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal International Journal Software Engineering and Computer Science (IJSECS)
Andreas Perdana
Universitas Dharma Wacana
Computer Science & IT

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

Found 2 Documents
Search

 1 
Sentiment Analysis of Public Comments on YouTube Regarding the Inaugural Speech of the 8th President of Indonesia Using VADER and BERT Methods Alwi Ahmad Bastian; Andreas Perdana
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 1 (2025): APRIL 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i1.3472

Abstract

The research examines public reactions toward President Prabowo Subianto first presidential address in 2024 by studying YouTube comment sentiments. By utilizing sentiment analysis methods, this research combines two main approaches: The research combines VADER (Valence Aware Dictionary and Sentiment Reasoner) for initial sentiment labeling through predefined dictionary categories with BERT (Bidirectional Encoder Representations from Transformers) for more advanced classification. The dataset contains 10,306 comments which display a range of public opinions. Positive sentiment represents 4,943 comments which make up 49.26% of the total while neutral sentiment accounts for 4,336 comments at 43.21% and negative sentiment represents 756 comments at 7.53%. The BERT model reached an accuracy level of 97.01% which illustrates its capability to process contextual details and subtle data elements. VADER delivers rapid preliminary labeling results and BERT improves classification precision through its analysis of complex contexts. The study reveals how people perceive the new government while providing chances for creating public opinion monitoring techniques for social and political topics. Researchers, academics, and policymakers will find these findings valuable for comprehending public opinion dynamics during the digital age's continuous evolution
Forecasting Chili Prices in Metro City Using Long Short-Term Memory (LSTM) Gusti Made Gunadi; Andreas Perdana
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 1 (2025): APRIL 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i1.3526

Abstract

Cayenne pepper is one of the important commodities in the staple market in Indonesia which has a vital role in people's daily lives. Fluctuations in the price of cayenne pepper are often a challenge that impacts farmers and consumers, causing uncertainty in production and distribution planning. This research aims to develop a cayenne pepper price prediction model using the Long Short-Term Memory (LSTM) method, utilizing historical data from the data.metrokota.go.id portal for the period October 2023 to October 2024. By using LSTM, this model successfully captures long-term patterns in cayenne price data, with a Final Validation Loss of 0.00249 which indicates a high level of accuracy. The prediction results are expected to help farmers determine the optimal selling time, traders in managing stocks efficiently, and policy makers in formulating strategies to mitigate the impact of price fluctuations. In addition, this study highlights practical implications for stabilizing commodity markets, particularly in Metro City, as well as the relevance of these findings to be applied to other agricultural commodities.
Co-Authors Alwi Ahmad Bastian Gusti Made Gunadi