Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal The Eastasouth Journal of Information System and Computer Science
Renaldiansyah Gumay
President University
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Improving Sentiment Classification of Indonesia's School Zoning Admission Policy on Twitter Renaldiansyah Gumay; Wiranto Herry Utomo
The Eastasouth Journal of Information System and Computer Science Vol. 4 No. 01 (2026): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v4i01.1162

Abstract

Since 2016, the Indonesian government has implemented a zoning-based policy for its online New Student Admission (Penerimaan Peserta Didik Baru, PPDB) system to ensure equitable access to quality education. Despite this intent, the policy has repeatedly drawn mixed public reactions, and in 2024 the debate intensified on social media, particularly on Twitter (X), which has become a primary channel for the public to express opinions on the policy. Understanding this sentiment at scale requires an approach that can cope with the unstructured, informal, and slang-heavy nature of Indonesian social media text. This study proposes a hybrid sentiment analysis approach that combines the InSet (Indonesia Sentiment) Lexicon with a Recurrent Neural Network (RNN) based on Long Short-Term Memory (LSTM) to classify public sentiment toward the 2024 PPDB zoning policy from 1,771 crawled tweets. Two scenarios were tested: Scenario 1 used an LSTM model trained on text alone, while Scenario 2 combined the LSTM with InSet Lexicon polarity scores as an auxiliary input. Scenario 1 achieved a training accuracy of 94.61% but only 66.18% on validation data, indicating overfitting, whereas Scenario 2 achieved a validation accuracy of 95%, with 92% precision, 96% recall, and a 93% F1-score. The results indicate that combining lexicon-based scoring with LSTM substantially improves classification accuracy and generalization on Indonesian-language, informal social media text, and that the overall public sentiment toward the 2024 zoning policy tended to be positive.
Co-Authors Wiranto Herry Utomo