Analisis Sentimen Kenaikan Pajak Hiburan Pada X Menggunakan Majority Vote Pada Metode Naive Bayes dan Support Vector Machine

Samodera, Bayu (2024) Analisis Sentimen Kenaikan Pajak Hiburan Pada X Menggunakan Majority Vote Pada Metode Naive Bayes dan Support Vector Machine. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 20081010048.-cover.pdf Download (2MB)
	Text (Bab 1) 20081010048.-bab1.pdf Download (31kB)
	Text (Bab 2) 20081010048.-bab2.pdf Restricted to Repository staff only until 23 July 2026. Download (397kB)
	Text (Bab 3) 20081010048.-bab3.pdf Restricted to Repository staff only until 23 July 2026. Download (712kB)
	Text (Bab 4) 20081010048.-bab4.pdf Restricted to Repository staff only until 23 July 2026. Download (1MB)
	Text (Bab 5) 20081010048.-bab5.pdf Download (15kB)
	Text (Daftar Pustaka) 20081010048.-daftarpustaka.pdf Download (157kB)

Abstract

Entertainment tax is a tax imposed on entertainment activities or services such as cinemas, concerts, or others. The increase in entertainment tax rates can significantly impact the entertainment industry and public perception of government policies. Therefore, it is crucial to conduct sentiment analysis related to the increase in entertainment tax to understand public response and attitude. This research utilizes data from the social media platform X to gather public opinions regarding the entertainment tax hike. The Support Vector Machine and Naive Bayes methods are applied individually and then integrated through the Majority Vote method to classify sentiments as positive, negative, or neutral. In this study, a total of 4012 tweets were used. The research was conducted with three scenarios. In the first scenario (90% training data, 10% test data), Naive Bayes achieved an accuracy of 71.82%, Support Vector Machine 77.56%, and Majority Vote 80.35%. In the second scenario (80% training data, 20% test data), Naive Bayes achieved an accuracy of 70.32%, Support Vector Machine 75.06%, and Majority Vote 79.08%. In the third scenario (70% training data, 30% test data), Naive Bayes achieved an accuracy of 68.16%, Support Vector Machine 72.82%, and Majority Vote 76.25%. This indicates that combining Naive Bayes and Support Vector Machine through the Majority Vote technique can improve accuracy in sentiment classification

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Kartini, Kartini	NIDN0710116102	kartini.if@upnjatim.ac.id
Thesis advisor	Al Haromainy, Muhammad Muharrom	NIDN0701069503	muhammad.muharrom.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Mr Bayu Samodera

Date Deposited:

23 Jul 2024 07:53

Last Modified:

23 Jul 2024 08:05

URI:

https://repository.upnjatim.ac.id/id/eprint/27216