Comparison of Kernel Support Vector Machine Multi-Class in PPKM Sentiment Analysis on Twitter

Jurnal RESTI: Rekayasa Sistem dan Teknologi Informasi

article

Andi Nurkholis¹  Debby Alita¹  Aris Munandar¹ 

[1] Department of Informatics, Faculty Engineering and Computer Science, Teknokrat Indonesia University

关键词: PPKM;    Support Vector Machine;    One Against One;    One Against Rest;    Polynomial;    RBF;   

DOI  :  10.29207/resti.v6i2.3906

来源: Ikatan Ahli Indormatika Indonesia

【 摘 要 】

PPKM is the Indonesian government's policy to deal with the spread of the coronavirus since early 2021. Until now, PPKM isstill the main topic to prevent the spread of COVID-19. This policy has generated various responses from the public, especiallyon Twitter. A sentiment analysis process is needed to process the text obtained from Twitter. Sentiment analysis is a form ofrepresentation of text mining and text processing. This study aims to analyze public sentiment towards PPKM through dataobtained from Twitter using the multi-class SVM algorithm. In implementing multi-class SVM, an analysis of the Polynomialand RBF kernels was carried out on the One Against One and One Against Rest methods which showed that the combinationof One Against Rest and the Polynomial kernel obtained the best accuracy, which was 98.9%. Unlike the case with thecombination of One Against One and Kernel RBF, which obtained the worst accuracy, 77.6%. The best model producesprecision, recall, and f1-score values of 97%, 98%, and 97%. Based on the confusion matrix results, the best model has apositive class distribution = 912, neutral = 51, and negative = 26. Overall, the model that uses polynomial kernel produceshigher accuracy, both applied to the One Against One and One Against Rest methods. In contrast, the model that uses the RBFkernel produces lower accuracy and is significantly different when applied to the One Against One and One Against Restmethods. The model results show that public sentiment towards the PPKM policy is positive to be continued consistently tosuppress the spread of the COVID-19 virus.

【 授权许可】

Unknown