Analisis Sentimen Terhadap Akun Tokoh Publik Berdasarkan Tweet Reply Dengan Metode Naïve Bayes
Total View This Week0
Total View This Week0
Institusion
Politeknik Negeri Jember
Author
Kholiq, Abdul
Subject
458 - Teknik Informatika
Datestamp
2022-07-15 08:57:33
Abstract :
Twitter is a social media platform that provides services for users to communicate online or see various things that are currently happening. Public figures both among celebrities, artists and politics are often discussed and trending topics. The impact is that the pros and cons among users of the accounts of public figures being discussed cause a lot of sentiment, either positive or negative. Therefore, we need a system that can classify each user's reply to the account of a public figure as a consideration for changing communication patterns for the better. The classification system that will be made is based on 1500 datasets that have been previously labeled and divided into 80% training data, 20% test data. The results of the confusion matrix testing process obtained the highest accuracy of 79% with a comparison of training data and test data of 8: 2, 76% with a data comparison of 9: 1, 77% with a data comparison of 7:3 and 74% with a data comparison of 6:4.
Twitter is a social media platform that provides services for users to communicate online or see various things that are currently happening. Public figures both among celebrities, artists and politics are often discussed and trending topics. The impact is that the pros and cons among users of the accounts of public figures being discussed cause a lot of sentiment, either positive or negative. Therefore, we need a system that can classify each user's reply to the account of a public figure as a consideration for changing communication patterns for the better. The classification system that will be made is based on 1500 datasets that have been previously labeled and divided into 80% training data, 20% test data. The results of the confusion matrix testing process obtained the highest accuracy of 79% with a comparison of training data and test data of 8: 2, 76% with a data comparison of 9: 1, 77% with a data comparison of 7:3 and 74% with a data comparison of 6:4.
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
