Sentiment Analysis on Reviews of the Documentary Film "Dirty Vote" Using Lexicon-Based and Support Vector Machine Approaches

Ramadhan, Apri and Yusuf Irianto, Suhendro Sentiment Analysis on Reviews of the Documentary Film "Dirty Vote" Using Lexicon-Based and Support Vector Machine Approaches. Jurnal CoreIT, 11 (1). pp. 9-19. ISSN 2599-3321

	Text 1. Cover - Laporan Jalur Publikasi Apri V.3 - Prodi MTI IIB Darmajaya.pdf Download (141kB)
	Text 2. Pernyataan-Persetujuan-Pengesahan.pdf Download (375kB)
	Text Jurnal Pertamaku Publish - Apri.pdf Download (560kB)

Official URL: https://ejournal.uin-suska.ac.id/index.php/coreit/...

Abstract

The general election is a state agenda in Indonesia held every five years. On February 11, 2024, during the silence period, a video titled "Dirty Vote" was uploaded on YouTube, drawing significant public attention. Its release during the silence period sparked controversy and prompted various opinions in the video’s comment section. Sentiment analysis is a suitable method to determine whether public opinions regarding the video are predominantly positive, negative, or neutral. This study utilized the Support Vector Machine (SVM) classification method with different kernels, including linear and non-linear (polynomial, RBF, and sigmoid). Support Vector Machine (SVM) was chosen in this study because it has a high accuracy value. It also requires labels and training data. To accelerate labeling for large datasets for example 10,000 – 60,000 data such as in this study, a Lexicon-Based approach was employed. The SVM approach can contribute to lexicon-based, and lexicon-based can help label datasets on SVM to produce good accuracy. The combination of SVM and Lexicon-Based methods demonstrated that the linear kernel outperformed others, achieving evaluation metrics of 91.1% accuracy, 91.1% recall, 90.9% precision, and 90.8% F1-score. Based on these values, the linear kernel model demonstrates good performance in classifying sentiment in textual data, such as comments or reviews. This model can be used to determine whether a comment or review is positive, negative, or neutral.

Item Type:	Article
Subjects:	Ilmu Komputer eBooks
Divisions:	Pasca Sarjana > Magister Teknik Informatika
Depositing User:	APRI RAMADHAN
Date Deposited:	21 Jul 2025 01:27
Last Modified:	21 Jul 2025 01:27
URI:	http://repo.darmajaya.ac.id/id/eprint/20769

Actions (login required)

View Item