Analisis Sentimen Penggunaan Galon Bisphenol A Menggunakan Algoritma Support Vector Machine Melalui Chi-Square Test

Aurelia, Cenditya Ayu (2024) Analisis Sentimen Penggunaan Galon Bisphenol A Menggunakan Algoritma Support Vector Machine Melalui Chi-Square Test. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 20083010023_cover.pdf Download (1MB)
	Text (Bab 1) 20083010023_bab1.pdf Download (206kB)
	Text (Bab 2) 20083010023_bab2.pdf Restricted to Repository staff only until 31 May 2028. Download (433kB)
	Text (Bab 3) 20083010023_bab3.pdf Restricted to Repository staff only until 31 May 2028. Download (614kB)
	Text (Bab 4) 20083010023_bab4.pdf Restricted to Repository staff only until 31 May 2028. Download (2MB)
	Text (Bab 5) 20083010023_bab5.pdf Download (188kB)
	Text (Daftar pustaka) 20083010023_daftarpustaka.pdf Download (247kB)
	Text (Lampiran) 20083010023_lampiran.pdf Restricted to Repository staff only until 31 May 2028. Download (883kB)

Abstract

Bottled Drinking Water (AMDK) is the main element that is important to maintain the balance of the body. One of the bottled drinking water is gallons that generally use Polycarbonate material containing Bisphenol A (BPA) which has the potential to have a negative impact on health and Polyethylene Terephthalate does not contain BPA which has the potential to cause environmental problems. This condition causes public unrest on Twitter between the use of BPA gallons and non-BPA gallons after the spread of news related to the impact caused by BPA gallons so that sentiment analysis is needed that can categorize positive and negative sentiments. This research was conducted to analyze the sentiment of using BPA gallons using Chi-Square feature selection and Support Vector Machine algorithm with Linear, Polynomial, and RBF kernel. The research stages include data collection of 1257 tweets, data preprocessing, data labeling, TF-IDF word weighting, Chi-Square feature selection, split dataset, data classification, model evaluation, and result analysis. The purpose of this research is to increase public awareness in choosing safe and environmentally friendly gallon bottled drinking water. This research shows the results of the application of Chi-Square feature selection with a real level value of 0.90 can increase accuracy up to 94% on Linear and Polynomial kernel.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Trimono, Trimono	NIDN0008099501	trimono.stat@upnjatim.ac.id
Thesis advisor	Diyasa, I Gede Susrama Mas	NIDN0019067008	igsusrama.if@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Data Science

Depositing User:

Cenditya Ayu Aurelia

Date Deposited:

31 May 2024 07:45

Last Modified:

31 May 2024 08:59

URI:

https://repository.upnjatim.ac.id/id/eprint/23675