Home › Categories › Technology› Download (369kB)

Download (369kB).pdf

14 Sentimen Analisis Untuk Mengukur Kepercayaan Masyarakat.pdf.pdf

🔗 Source: repository.unmuhjember.ac.id

📊 Size: 360 KB

📄 Pages: 10 pages

⬇️ Downloads: 47

Summary

The study analyzes Indonesian people's sentiments on Twitter towards government policies in handling COVID-19 cases using the Bernoulli Naive Bayes method. The performance measurement methods of accuracy, precision, and recall are used to measure the performance of the Bernoulli Naive Bayes method. The study uses the Synthetic Minority Oversampling Technique (SMOTE) to overcome data imbalance. The results show that the model without SMOTE has an accuracy rate of 80.58%, precision level of 80.33%, and recall rate of 85.57%, while the model with SMOTE has an accuracy rate of 80.20%, precision level of 78.04%, and recall rate of 86.77%. The study finds that 55% of the sentiments are positive and 45% are negative without SMOTE, while 53% are positive and 47% are negative with SMOTE. The model without SMOTE has a classification result closer to the actual data with 58% positive sentiment and 42% negative sentiment.

Download File

Description

The study analyzes Indonesian people's sentiments on Twitter towards government policies in handling COVID-19 cases using the Bernoulli Naive Bayes method.

Technical Information

File Format: PDF
File Size: 360 KB
Pages: 10
Language: EN
Total Downloads: 47
Last Updated: 1 week ago

Document Overview

This PDF document about Download (369kB) provides comprehensive information and guidance. Whether you're a beginner or advanced user, this resource offers valuable insights into Download (369kB).