SENTIMEN ANALISIS TERHADAP LAYANAN FIRST MEDIA MENGGUNAKAN METODE NAÃVE BAYES
Total View This Week0
Total View This Week0
Institusion
Universitas Pembangunan Nasional Veteran Jakarta
Author
Rizki Indah Pratiwi, .
Subject
Z719 Libraries (General)
Datestamp
2021-12-21 07:49:47
Abstract :
Twitter is one of the social media that is often used by consumers to submit complaints or opinions regarding the services provided by a company. Where complaints or opinions submitted through the tweet can be processed to find out the sentiments contained in the tweet. Therefore, this research was conducted to carry out the process of classifying tweet data in which it contains positive or negative sentiments regarding the services of one company, First Media. The method used for the classification process in this study is the Naïve Bayes method. Tweet data is retrieved using the Twitter API (Application Programming Interface) available on the Twitter platform. Where the tweet data will be labeled positive and negative to make it easier for the data to be processed. Retrieved tweets are tweets that include @FirstMediaCares as a keyword. Furthermore, the tweet data collected is divided into training data by 70% and test data by 30%. The results of the evaluation that serves to test the performance of the Naïve Bayes method in classifying tweets into positive and negative categories show the accuracy value obtained is 89.47%.
Twitter is one of the social media that is often used by consumers to submit complaints or opinions regarding the services provided by a company. Where complaints or opinions submitted through the tweet can be processed to find out the sentiments contained in the tweet. Therefore, this research was conducted to carry out the process of classifying tweet data in which it contains positive or negative sentiments regarding the services of one company, First Media. The method used for the classification process in this study is the Naïve Bayes method. Tweet data is retrieved using the Twitter API (Application Programming Interface) available on the Twitter platform. Where the tweet data will be labeled positive and negative to make it easier for the data to be processed. Retrieved tweets are tweets that include @FirstMediaCares as a keyword. Furthermore, the tweet data collected is divided into training data by 70% and test data by 30%. The results of the evaluation that serves to test the performance of the Naïve Bayes method in classifying tweets into positive and negative categories show the accuracy value obtained is 89.47%.
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
