PENGARUH SYNTHETIC MINORITY OVERSAMPLING TECHNIQUE (SMOTE) PADA ANALISIS SENTIMEN MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE (SVM)

FARIZKI, HELMI and Yusliani, Novi and Darmawahyuni, Annisa (2023) PENGARUH SYNTHETIC MINORITY OVERSAMPLING TECHNIQUE (SMOTE) PADA ANALISIS SENTIMEN MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE (SVM). Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021281924037.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021281924037_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_55201_09021281924037_008118205_896834002_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (863kB)
	Text RAMA_55201_09021281924037_008118205_896834002_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (422kB) | Request a copy
	Text RAMA_55201_09021281924037_008118205_896834002_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (153kB) | Request a copy
	Text RAMA_55201_09021281924037_008118205_896834002_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021281924037_008118205_896834002_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (148kB) | Request a copy
	Text RAMA_55201_09021281924037_008118205_896834002_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (54kB) | Request a copy
	Text RAMA_55201_09021281924037_008118205_896834002_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (131kB) | Request a copy

Abstract

Imbalanced data is a problem that often occurs when conducting research in the field of sentiment analysis. This problem occurs when the dataset being analyzed has more positive classes than negative classes or vice versa so that the terms majority and minority data appear. If the majority data is more dominant then the classification process tends to produce a classification into the majority class. This causes the need for a solution to overcome the problem of imbalanced data. One of the methods to overcome this data is by using the Synthetic Minority Oversampling Technique (SMOTE) by creating synthetic data on minority data so that the data will be balanced with the majority data. This study aims to see the effect of SMOTE on sentiment analysis using the Support Vector Machine (SVM) algorithm. Based on the evaluation results using two different datasets, it was found that the results of the analysis using the SVM method resulted in an average accuracy of around 79.1% in the covid-19 dataset and 75% in the tv dataset. There was an increase in accuracy when applying the SVM + SMOTE method with an average accuracy of around 93.2% in the covid-19 dataset and 84,7% in the tv dataset.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Imbalanced data, Support Vector Machine (SVM), Synthetic Minority Oversampling Technique (SMOTE), analisis sentimen.
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Helmi Farizki
Date Deposited:	04 Apr 2023 06:27
Last Modified:	04 Apr 2023 06:27
URI:	http://repository.unsri.ac.id/id/eprint/93069

Actions (login required)

View Item