Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer)
Navidkya, Abriel
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management

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

Found 1 Documents
Search

 1 
Analisis Sentimen Isu Artificial Intelligence di Twitter dengan SVM dan Random Forest Navidkya, Abriel; Yusuf, Mohamad
JURNAL FASILKOM Vol. 16 No. 1 (2026): Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer)
Publisher : Unversitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/jf.v16i1.10037

Abstract

Artificial Intelligence (AI) has become a widely discussed topic on social media, particularly Twitter, as public opinions about this technology grow. This study aims to analyze the sentiment of Twitter posts related to AI issues using two classification algorithms: Support Vector Machine (SVM) and Random Forest (RF). The research method involves data collection via the Twitter API, followed by text preprocessing steps including case folding, tokenization, stopword removal, and stemming. The data is then manually or semi-automatically labeled with sentiments (positive, negative, neutral) to support supervised learning. Vectorization using TF-IDF is applied before training and testing the SVM and RF models to compare their classification performance. Results indicate that SVM outperforms RF in accuracy and class balance across sentiments. The application of Synthetic Minority Oversampling Technique (SMOTE) enhances performance, especially in detecting the less frequent negative sentiment. Post-SMOTE, SVM achieves an accuracy of 89.12% and an F1-score of 0.7122 for the negative class, demonstrating its ability to handle data imbalance. Although RF also improves after SMOTE, its performance remains below SVM. This study is expected to contribute significantly to public opinion monitoring and serve as a foundation for decision-making regarding AI-based technology development. 
Co-Authors Mohamad Yusuf