Accuracy for Sentiment Analysis of Twitter Students on ELearning in Indonesia using Naive Bayes Algorithm Based on Particle Swarm Optimization
Mohamad Kartiko, Sfenrianto Sfenrianto · Journal of Physics Conference Series · 2019
Abstract Students can use social media such as Twitter for online learning (E-Learning). This study aims to analyse an accuracy for the sentiments of students about E-Learning who use Indonesian on Twitter social media both positive and negative opinions. The algorithms used are Naive Bayes (NB). Then to optimize the accuracy of the calculation results, the Particle Swarm Optimization (NB-PSO) approach is used. In order to optimize accurate results, this study uses three experimental sequences (scenario 1, scenario 2, and scenario 2) for both NB and NB-PSO algorithms. Each scenario uses different positive and negative comments. The results of the experiment show that in scenario 1 an increase in accuracy is 10.00% for NB-PSO. Scenario 2 there is an increase in accuracy of 13.33% on NB-PSO. Meanwhile, in scenario 3 an increase in accuracy is 27.22% for NB-PSO. These results prove that the accuracy of NB-PSO is better than NB for all scenarios.