ANALISIS SENTIMEN KOMENTAR VIDEO ARTIS KOREA DI KANAL YOUTUBE RANS ENTERTAINMENT MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE

Sa'diyah Nur Itsna, Halimatus (2023) ANALISIS SENTIMEN KOMENTAR VIDEO ARTIS KOREA DI KANAL YOUTUBE RANS ENTERTAINMENT MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE. Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

	Text COVER.pdf Download (810kB)
	Text ABSTRACT.pdf Download (326kB)
	Text ABSTRAK.pdf Download (310kB)
	Text BAB I.pdf Download (392kB)
	Text BAB II.pdf Download (612kB)
	Text BAB III.pdf Download (522kB)
	Text BAB IV.pdf Restricted to Registered users only Download (689kB) | Request a copy
	Text BAB V.pdf Download (355kB)
	Text DAFTAR PUSTAKA.pdf Download (249kB)
	Text LAMPIRAN.pdf Restricted to Registered users only Download (309kB) | Request a copy

Abstract

Korean Wave fever hit Indonesia along with the development of Youtube social media. Youtube is one of the social media that provides a comment feature. One of the Youtube content creators that often collaborates with Korean artists is RANS Entertainment. It is important for content creators to know how people respond to the videos they produce. However, monitoring and organizing public opinion is not easy. There are too many opinions that must be processed manually. Therefore, there is a need for special methods or techniques that can automatically categorize the comments, whether they are positive, negative or neutral. One of the machine learning-based data analysis techniques is sentiment analysis. In this research, sentiment analysis is carried out using the Support Vector Machine algorithm. The approach taken in this research begins with collecting data from Youtube comments on the RANS Entertainment channel related to Korean artist collaboration videos, preprocessing, labeling using the InSet Lexicon dictionary, split data, feature extraction with TF-IDF, classification using Support Vector Machine and evaluation. This study classifies 9,091 positive comments, 5,817 neutral comments, and 5,744 negative comments and produces a Support Vector Machine algorithm accuracy of 92% so that it falls into the Excellent classification category. Keywords: Sentiment Analysis, Support Vector Machine, Youtube, Korea, RANS Entertainment

Actions (login required)

View Item