Indihome is one of the largest internet service providers in Indonesia with an increasing number of subscribers every year. Indihome subscribers until the end of March 2022 were recorded at 8.7 million, growing 7.2 percent over the same period last year. However, over time, many customers have complained to IndiHome about slow internet access, sudden increases in billing and so on. Based on the description above, it is interesting to conduct research on the use of Indihome tweets which are the result of channeling opinions and comments on Twitter social media. This study uses the Smote method, Support vector machine, Adaboost and Particle swarm optimization so that the results can be compared with the level of accuracy. The results of this research show that by using the Smote method, Support vector machine obtained values of Accuracy 80.48, Precision 85.29, Recall 73.75 and AUC 0.907. As for the Smote, Support vector machine and AdaBoost methods, the Accuracy values are 80.21, Precision 85.01, Recall 73.36 and AUC 0.861. Finally, the results of the Smote and Particle swarm optimization methods obtained Accuracy values of 76.59, Precision 76.57, Recall 80.35 and AUC 0.868. Based on the research results, the Smote method and the Support vector machine (SVM) have the largest results and are considered effective with the existing dataset
Copyrights © 2023