Penentuan Respon Masyarakat Terhadap Kebijakan Pilkada pada masa Pandemi Covid-19 menggunakan Metode Algoritma Naïve Bayes-Classifier (NBC) dan Support Vector Machine (SVM)

Abstrak

Purpose: The purpose of this study is to identify the sentiment analysis of the public response to the Indonesian Government's policy to carry out regional elections (pilkada) during the Covid-19 pandemic using the Naïve Bayes Classifier (NBC) algorithm and the Support Vector Machine (SVM) method.

Research methodology: The research method used in this study is to use quantitative research methods. The data used in this study were taken from public comments on a tweet in a Twitter post that is stored in the .csv format.

Results: The results obtained from this study are to compare 2 (two) algorithms, namely Naïve Bayes and SVM into 3 test scenarios. The test results show that the accuracy value obtained by SVM is much better than Naïve Bayes with the value in the first scenario Naïve Bayes 76%: 88% SVM, the second scenario Naïve Bayes 76%: 88% SVM, and the third scenario Naïve Bayes 78%: 90 % SVM.

Limitations: There are several limitations in this study, such as the data used only comes from the Twitter platform, the data used only focuses on Indonesian language posts, and only 2 (two) sentiment classification class labels are used, namely positive and negative.

Contribution: This research can be used as a reference by the General Election Commission (KPU) to determine election policies for the regions in the future during the Covid-19 period. This research is included in the disciplines of data mining and machine learning.