(Similarity) Entimen Analisis Untuk Mengukur Kepercayaan Masyarakat Terhadap Pengadaan VaksinCOVID-19 Berbasis BernoulliNaive Bayes

Azizah, Hanifatul and Rintyarna, Bagus Setya and Cahyanto, Triawan Adi (2022) (Similarity) Entimen Analisis Untuk Mengukur Kepercayaan Masyarakat Terhadap Pengadaan VaksinCOVID-19 Berbasis BernoulliNaive Bayes. Jurnal Teknologi Informasi dan Rekayasa Komputer.

[img] Text
14 Sentimen Analisis Untuk Mengukur Kepercayaan Masyarakat.pdf.pdf

Download (369kB)

Abstract

his study contains an analysis of Indonesian people's sentiments on Twitter towards government policies in handling cases of the COVID-19 pandemic. This study uses the BernoulliNaive Bayesmethod in modeling and testing the classification of sentiment data. The performance measurement methods of accuracy, precision and recallare also used to measure the performance of the BernoulliNaive Bayesmethod. In the distribution and test scenarios, the K Fold Cross Validationmethod is used with values of k = 2, 4, 5, 8 and 10. To overcome the data imbalance, in this study the Synthetic Minority Oversampling Technique (SMOTE)technique was used. From the test results with the model without using the Synthetic Minority Oversampling Technique (SMOTE)technique, the results obtained with an accuracy rate of 80.58%, a precision level of 80.33% and a recallrate of 85.57%. while the test results using the Synthetic Minority Oversampling Technique (SMOTE)in modeling, obtained an accuracy rate of 80.20%, a precision level of 78.04% and a recallrate of 86.77%.The test results show that 55% positive sentiment and 45% negative sentiment were obtained using the model without SMOTE, while 53% positive sentiment and 47% negativesentiment were obtained using the model after SMOTEwas implemented. The model built without SMOTEimplementation has a classification result that is closer to the actual data with a percentage of 58% positive sentiment and 42% negative sentiment.

Item Type: Peer Review
Uncontrolled Keywords: Bernoulli,SentimentAnalysis,SMOTE
Subjects: 600 Technology and Applied Science > 620 Engineering
Divisions: Faculty of Engineering > Department of Electrical Engineering (S1)
Depositing User: Bagus Setya Rintyarna
Contact Email Address: bagus.setya@unmuhjember.ac.id
Date Deposited: 23 Dec 2022 01:40
Last Modified: 24 Jan 2023 04:30
URI: http://repository.unmuhjember.ac.id/id/eprint/15688

Actions (login required)

View Item View Item