Claim Missing Document
Check
Articles

Found 1 Documents
Search

Twitter Sentiment Analysis on the Relocation of Indonesia's Capital City Using the Convolutional Neural Network Algorithm Ramadhani Ari Putra; Herman Yuliansyah
Journal of Applied Statistics and Data Mining Vol. 6 No. 1 (2025): Journal Applied Statistics and Data Mining
Publisher : Institut Teknologi Statistika dan Bisnis Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63229/jasdm.v6i1.90

Abstract

Background: The relocation of the Indonesian capital (IKN) has become a hot topic on social media, particularly Twitter, with diverse public opinions. Sentiment analysis is necessary to comprehensively understand public perception. Objective:  This study aims to analyze public sentiment on Twitter regarding the relocation of the IKN using the CNN algorithm to identify tendencies of positive, negative, or neutral opinions. Methods: Data was obtained through Twitter crawling, followed by preprocessing, automatic labeling with VADER, and resampling (oversampling). Text features were extracted using pre-trained Word2Vec and classified with CNN. Testing was conducted with varying epochs (25, 50, 100) and data splits (70:30 and 80:20). Conclusion: The highest accuracy was achieved with the 70:30 scheme with 100 epochs, namely 83.2% (precision 83.8%, recall 83.2%, and F1-score 83.0%). The analysis shows a dominant positive sentiment regarding the new capital city as a future solution and hope for Indonesia, although there are also negative criticisms.