Support Vector Machine for Sentiment Analysis of Presidential Candidate Proker Number 2 2024
Nathaniel Ambrossi Warint · Universitas Kristen Satya Wacana Institutional Repository (Universitas Kristen Satya Wacana) · 2024
This research investigates the application of Support Vector Machine (SVM) in sentiment analysis to evaluate public sentiment regarding the work programs of presidential candidate number 2 in the 2024 Indonesian election. Utilizing social media data from the X platform, the study aims to measure SVM's efficiency in terms of accuracy, processing speed, and computational resource usage. The sentiment data, categorized into positive, negative, and neutral classes, underwent preprocessing techniques such as cleaning, tokenization, and stemming. The results demonstrate an 83% accuracy rate, highlighting SVM's capability in handling high-dimensional data efficiently, although challenges remain in identifying positive sentiments effectively. This study provides valuable insights for researchers in sentiment analysis and offers strategic input for political campaign teams to better understand public perceptions. Additionally, it serves as a foundation for future studies involving large-scale sentiment data analysis..