ANALISIS SENTIMEN PRODUK KECANTIKAN THE ORIGINOTE MENGGUNAKAN METODE NAIVE BAYES

Iroh, Setiya Ningsih (2024) ANALISIS SENTIMEN PRODUK KECANTIKAN THE ORIGINOTE MENGGUNAKAN METODE NAIVE BAYES. Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

	Text TA2_COVER1. (1) (2).pdf Download (1MB)
	Text TA2_ABSTRACK B.INGG.pdf Download (11kB)
	Text TA2_ABSTRAK B.INDO.pdf Download (9kB)
	Text TA2_BAB 1.pdf Download (105kB)
	Text TA2_BAB 2.pdf Download (245kB)
	Text TA2_BAB 3.pdf Download (535kB)
	Text TA2_BAB 4.pdf Restricted to Registered users only Download (4MB)
	Text TA2_BAB 5.pdf Download (7kB)
	Text TA2_DAFTAR PUSTAKA.pdf Download (78kB)
	Text TA2_LAMPIRAN.pdf Restricted to Registered users only Download (487kB)

Abstract

The development of the beauty product industry is increasingly rapid in line with the era of globalization, including in Indonesia which is the third largest beauty industry market in Asia. The Originote, a Chinese skincare brand, ranked first as the best-selling facial care product on the YouTube platform in 2024. In this context, Twitter sentiment analysis of South Korean artists as local beauty product ambassadors offers valuable insights into consumer perceptions and opinions towards the brand. This research aims to classify review comments on YouTube on The Originote products using the Naïve Bayes method and evaluate the level of accuracy of this method. The data used is 1840 comments reviewing The Originote beauty products on YouTube, with review comments classified into positive and negative. The results of sentiment analysis will help understand consumer opinions and identify aspects that need to be improved in product marketing. that the sentiment classification model has good performance, with a accuracy 0.60, precision value of 0.55, recall of 0.96, and F1-score of 0.77. This model can be a useful tool for brand owners to understand customer views and formulate more effective marketing strategies in the future. As well as expanding the dataset by adding a wider variety of beauty product reviews. This is expected to improve the model's performance in classifying sentiment more accurately Keywords: Naïve Bayes, Komentar Review, YouTube

Actions (login required)

View Item